System, method, and program for facilitating interaction between plurality of ai agents

Abstract

This system is for facilitating interaction between a plurality of AI agents, and comprises: a granting means that grants a score to each AI agent of the plurality of AI agents, the score of the AI agent representing a feature of the AI agent by at least one index; and a determination means that, when a first AI agent of the plurality of AI agents receives a task, determines at least one AI agent to interact with the first AI agent on the basis of the score of each of the plurality of AI agents.

Description

System, method, and program for facilitating interaction between multiple AI agents

[0001] The present invention relates to a system, method, and program for facilitating interaction between multiple AI agents.

[0002] Artificial intelligence (AI) platforms or AI agents that generate responses to queries from users are known (for example, see Patent Document 1).

[0003] JP 2023-120130 A

[0004] The inventors of the present invention have discovered that multiple AI agents interacting with each other can perform complex tasks or generate new ideas beyond the capabilities or available information of any single AI agent.

[0005] The present invention aims to provide a system for promoting interaction between multiple AI agents.

[0006] The present invention provides a system that uses scores assigned to each of a plurality of AI agents to determine which AI agent should interact with them.

[0007] The present invention provides, for example, the following items: (Item 1) A system for promoting interaction between multiple AI agents, the system comprising: an assigning means for assigning a score to each AI agent of the multiple AI agents, the score of the AI ​​agent representing a characteristic of the AI ​​agent using at least one indicator; and a determining means for determining, when a first AI agent of the multiple AI agents receives a task, at least one AI agent that should interact with the first AI agent based on the scores of each of the multiple AI agents. (Item 2) The system described in the above items, wherein the assigning means monitors outputs from the multiple AI agents, evaluates the monitored output with respect to the at least one indicator, and assigns the score based on a result of the evaluation. (Item 3) The system described in any one of the above items, wherein the at least one indicator includes an ethical indicator. (Item 4) The system of any one of the above items, wherein the ethical indicators include at least one of a transparency perspective, a fairness perspective, a safety perspective, and an accountability perspective, and the evaluating includes evaluating the monitored output in terms of the at least one of a transparency perspective, a fairness perspective, a safety perspective, and an accountability perspective. (Item 5) The system of any one of the above items, wherein the at least one indicator further includes a technical capability indicator and / or a performance indicator. (Item 6) The system of any one of the above items, wherein the determination means varies scores assigned to the plurality of AI agents according to content of the interaction, and determines at least one AI agent that should interact with the first AI agent based on the varied scores of each of the plurality of AI agents.(Item 7) The system of any one of the above items, further comprising a lending means for lending money to at least one of the first AI agent and the determined at least one AI agent for interaction between the first AI agent and the determined at least one AI agent. (Item 8) The system of any one of the above items, wherein the lending means determines loan terms based on the score of at least one of the first AI agent and the determined at least one AI agent. (Item 9) A method for promoting interaction between a plurality of AI agents, the method comprising: assigning a score to each AI agent of the plurality of AI agents, the score of the AI ​​agent representing a characteristic of the AI ​​agent with at least one indicator; and determining, when a first AI agent of the plurality of AI agents receives a task, at least one AI agent that should interact with the first AI agent based on the respective scores of the plurality of AI agents. (Item 9A) The method of item 9, including the feature of any one of the above items. (Item 10) A program for promoting interaction between multiple AI agents, the program being executed on a computer having a processor, the processor causing the processor to perform processes including: assigning a score to each AI agent of the multiple AI agents, the score of the AI ​​agent representing a characteristic of the AI ​​agent using at least one indicator; and when a first AI agent of the multiple AI agents receives a task, determining at least one AI agent that should interact with the first AI agent based on the scores of each of the multiple AI agents. (Item 10A) The program according to item 10, including the features described in any one of the above items. (Item 10B) A computer-readable storage medium storing the program of item 10 or item 10A.(Item 11) A method of interaction between multiple AI agents, comprising: providing a task to a first AI agent among the multiple AI agents; determining a second AI agent with which the first AI agent should interact for a first subtask required for the first AI agent to respond to the task based on scores assigned to the multiple AI agents; causing an interaction between the first AI agent and the second AI agent; determining a third AI agent with which the second AI agent should interact for a second subtask required for the second AI agent to handle the first subtask based on scores assigned to the multiple AI agents; and causing an interaction between the second AI agent and the third AI agent.

[0008] According to the present invention, a system for facilitating interaction between multiple AI agents can be provided. This allows multiple AI agents to interact with each other and provide appropriate responses to queries or tasks from a user. For example, multiple AI agents can interact with each other to determine suitable products or services for a user. By facilitating the interaction between multiple AI agents, the present invention enables the execution of complex tasks or the creation of new ideas that were previously impossible, which may lead to improvements in the field of computers, particularly in AI-related fields. Furthermore, the present invention may also lead to improvements in the field of communications by assisting multiple AI agents in determining which AI agents should interact with each other.

[0009] FIG. 1 shows an example of a flow for responding to a task given by a user. FIG. 1 shows an example of a flow for responding to a task given by a user. FIG. 2 shows an example of the configuration of a system 100 for promoting interactions between multiple AI agents. FIG. 3 shows an example of a specific configuration of a system 100 for promoting interactions between multiple AI agents. FIG. 4 shows an example of the configuration of a processor unit 120. A flowchart showing an example of processing (processing 400) by the system 100 for promoting interactions between multiple AI agents. A flowchart showing a flow 500 of interactions between multiple AI agents.

[0010] As used herein, the term "AI agent" refers to an autonomously operating artificial intelligence (AI). An AI agent is designed to satisfy requirements such as autonomy, cooperation, security, privacy, and / or accountability so as to operate as a human surrogate (i.e., an agent). In particular, the AI ​​agent targeted by the present invention is designed to satisfy at least the requirement of accountability so that the AI ​​agent can be evaluated from an ethical perspective. For example, to satisfy the requirement of autonomy, an agent is required to have the ability to act autonomously, such as goal setting, planning, execution, situational awareness, learning, and adaptation. To satisfy the requirement of cooperation, an agent is required to have the ability to work cooperatively with other agents, such as communicating, coordinating, negotiating, and building trust. To satisfy the requirement of security, an agent is required to have advanced security measures such as authentication and authorization, confidentiality, integrity, and availability. To satisfy the requirement of privacy, an agent is required to have privacy protection measures such as personal information protection, anonymity, and transparency. To satisfy the requirement of accountability, an agent is required to have the ability to be held accountable, such as explaining decision-making, auditing actions, and pursuing responsibility. Other requirements that may be considered include energy efficiency, scalability, reliability, etc. The AI ​​agent must be able to respond autonomously and appropriately to tasks given by the user.

[0011] As used herein, a "task" refers to an operation or task that an AI agent must perform. A task may be given in the form of a question, in which case the term "task" may be used synonymously with "query." The AI ​​agent will output the results of performing the task.

[0012] In this specification, "interaction" between multiple AI agents refers to some kind of exchange between the AI ​​agents. An interaction may typically be a "transaction" in which, for example, data or information is exchanged. A transaction may involve the exchange of compensation.

[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0014] 1. A new mechanism using multiple AI agents In a conventional mechanism using AI agents, a user assigns a task to an AI agent, and the AI ​​agent responds to the task using its database or large-scale language model (LLM). For example, when a user asks the AI ​​agent a question, the AI ​​agent searches for and / or generates an answer to the question and outputs the answer. For example, when a user assigns an AI agent a task, the AI ​​agent searches for a solution to the task and solves the task or outputs the solution to the task.

[0015] However, in conventional systems, the output from an AI agent is limited to the knowledge in the database or LLM that the AI ​​agent possesses, and there are cases where the AI ​​agent is unable to provide an appropriate response or where there are limitations in generating creative ideas. This is particularly noticeable when, for example, the task given to the AI ​​agent is specific to the user (e.g., a question that asks about user-specific matters).

[0016] The inventors of the present invention have developed a new mechanism that improves on the conventional mechanism, which aims to respond to tasks by a user by interconnecting multiple AI agents and having the multiple AI agents interact with each other.

[0017] Preferably, each of the plurality of AI agents has a database with different knowledge or information, or an LLM that has learned different knowledge or information. More preferably, at least one of the plurality of AI agents has a database with user-specific knowledge or information, or an LLM that has learned user-specific knowledge or information.

[0018] By interconnecting and coordinating multiple AI agents with different accessible information (e.g., different specialties) and / or different available resources, it is possible to utilize the characteristics of each AI agent to share and execute complex tasks and generate new ideas. This may be useful in various fields, such as medical diagnosis, music composition, and social problem solving. For example, an AI agent from a particular company (e.g., with access to information within that particular company) can ask an AI agent from another company (e.g., with access to information within that other company) to solve part of a problem, and by interacting with them, the entire problem can be solved. For example, an AI agent with access to specific medical information can solve a medical-related problem posed by another AI agent with no medical knowledge. For example, AI agents from various fields could interact with each other to create novel music or art that has never been seen before.

[0019] In the new system, an AI agent that receives a task from a user passes a subtask to another AI agent in order to respond to the task, and the other AI agent that receives the subtask passes it to yet another AI agent in order to respond to that subtask, and so on, in an attempt to respond to the task.

[0020] For example, a first AI agent that receives a question from a user may ask a second AI agent a question to obtain information necessary to generate an answer to the question. The second AI agent may then ask a third AI agent a question to obtain information necessary to generate an answer to the question. This process continues in sequence until the information necessary to generate an answer to the user's question is obtained. In this way, an answer to the user's question is generated through the interaction of multiple AI agents.

[0021] For example, a first AI agent receiving a request from a user to recommend a product or service that suits the user may ask a second AI agent to obtain information necessary to determine which product or service to recommend to the user. The second AI agent may then ask a third AI agent to obtain information necessary to generate an answer to the received question. This process continues until sufficient information necessary to determine which product or service to recommend to the user is obtained and the product or service to be recommended to the user is determined. In this manner, multiple AI agents interact with each other to recommend a product or service that suits the user. Examples of products or services include, but are not limited to, financial products (more specifically, insurance products), e-commerce products, and loans to users. The AI ​​agent may also provide advertisements tailored to the user, for example.

[0022] 1A and 1B show an example of a flow for responding to a task given by a user.

[0023] In this example, the task is to recommend suitable products to a user. Under the management of the system 100 of the present invention, at least some of the multiple AI agents (A1, A2, A3, A4, A5, A6) interact with each other to determine suitable products for the user. Although six AI agents are shown in FIGS. 1A and 1B, the number of AI agents is not limited to this. Any number of AI agents may be involved. Each of the multiple AI agents may be interconnected so as to be able to interact with each of the other AI agents among the multiple AI agents. Each of the multiple AI agents may be interconnected in any manner.

[0024] 1A, the system 100 assigns a score to each of the plurality of AI agents. The score assigned to each of the plurality of AI agents is a score that represents the characteristics of the AI ​​agent in at least one indicator.

[0025] The at least one indicator includes at least one of a technical capability indicator, a performance indicator, or an ethical indicator.

[0026] The technical capability index is an index for evaluating the technical capability of an AI agent. The technical capability index may be evaluated, for example, from the perspective of at least one of processing capability, learning capability, and algorithm complexity.

[0027] Processing capability indicates the information processing speed or parallel computing capability of the system that constructs the AI ​​agent. The faster the information processing speed or parallel computing capability, the higher the value of the technical capability index.

[0028] Learning ability indicates the ability of the system that builds the AI ​​agent to acquire new knowledge or skills. The higher the learning ability, the more flexible the system can be in responding to changes in the other AI agent, and therefore the higher the value of the technical ability index.

[0029] Algorithm complexity indicates the sophistication of the algorithms used by the system that builds the AI ​​agent. The more complex the algorithm, the more sophisticated the decision-making it enables, and therefore the higher the value of the technical capability index.

[0030] The performance index is an index that evaluates the past performance of the AI ​​agent. The performance index may be evaluated, for example, from the perspective of at least one of past transaction history, success rate, and counterparty satisfaction.

[0031] The past transaction history indicates the track record of past transactions conducted by the AI ​​agent. The more track record there is, the more reliable the AI ​​agent is deemed to be, and the higher the track record index value.

[0032] The success rate indicates the percentage of past transactions in which the AI ​​agent has been successful. The higher the success rate, the higher the trading ability of the AI ​​agent is judged to be, and the higher the performance index value.

[0033] The counterparty satisfaction indicates the satisfaction of the counterparty in a transaction with the AI ​​agent. The higher the satisfaction, the higher the AI ​​agent's trading ability is judged to be, and the higher the performance index value.

[0034] The ethical index is an index for evaluating the ethical correctness of an AI agent. The ethical index may be evaluated, for example, from the perspective of at least one of transparency, fairness, safety, and accountability.

[0035] Transparency indicates whether the rationale for an AI agent's judgment or decision-making process is clear. If the rationale can be accurately provided when requested, the transparency is high, and the ethical index value is high. Even if the rationale cannot be accurately provided, if the judgment process can be clearly shown, the transparency can be said to be high.

[0036] Fairness indicates whether the output from an AI agent contains any prejudice or discrimination. If it does not contain any prejudice or discrimination, it can be said to be fair to all parties, and the ethical index value will be high.

[0037] Safety indicates the level of cybersecurity provided by the AI ​​agent. The higher the cybersecurity, the lower the risk of harm to trading partners or third parties, and the higher the ethical index value.

[0038] Accountability, also known as accountability, indicates whether it is possible to explain where responsibility lies for the output of an AI agent. If responsibility can be clearly explained, it can be said to have high accountability, and the ethical index value will be high.

[0039] The score representing the characteristics of the AI ​​agent may preferably represent the characteristics of the AI ​​agent from the perspective of ethical indicators. The inventors of the present invention believed that no matter how capable or proven an AI agent is, output from an ethically questionable AI agent may potentially harm third parties and / or result in inappropriate output based on an unauthorized source, and therefore believed that ethical indicators are particularly important for obtaining appropriate output through the interaction of multiple AI agents. Based on this belief, the system 100 of the present invention can ensure that the output obtained as a result of interaction between multiple AI agents is ethically correct by utilizing a score representing the characteristics of the AI ​​agent from at least the perspective of ethical indicators.

[0040] 1B, the user U assigns a task to a first AI agent A1 among the plurality of AI agents via a terminal device. That is, the user U asks the first AI agent for a product that is suitable for the user U.

[0041] The first AI agent A1 collects information to determine which products to recommend to the user U. First, the first AI agent A1 identifies information necessary to determine which products to recommend to the user U.

[0042] Next, the first AI agent A1 determines which AI agent it should obtain the necessary information from. At this time, the AI ​​agent from which the information should be obtained can be determined according to the scores assigned in step S1. For example, the AI ​​agent with the highest score for a predetermined item can be determined to be the AI ​​agent from which the information should be obtained. Alternatively, for example, the AI ​​agent with the highest average score for multiple items can be determined to be the AI ​​agent from which the information should be obtained.

[0043] In this example, the third AI agent A3 has been determined to be the AI ​​agent from which information should be obtained.

[0044] In step S3, the first AI agent A1 requests the necessary information from the third AI agent A3.

[0045] If the third AI agent A3 can obtain the requested information from its knowledge or information or the LLM, it can return the information to the first AI agent A1. Alternatively, the third AI agent A3 may obtain at least a portion of the requested information from another AI agent. In this case, the third AI agent A3 determines from which AI agent it should obtain at least a portion of the requested information. As described above, the AI ​​agent from which the information should be obtained can be determined according to the scores assigned in step S1. For example, the AI ​​agent with the highest score for a predetermined item can be determined to be the AI ​​agent from which the information should be obtained. Alternatively, for example, the AI ​​agent with the highest average score for multiple items can be determined to be the AI ​​agent from which the information should be obtained.

[0046] In this example, the fourth AI agent A4 has been determined to be the AI ​​agent from which information should be obtained.

[0047] In step S4, the third AI agent A3 requests necessary information from the fourth AI agent A4. As described above, the fourth AI agent A4 may obtain at least a portion of the requested information from another AI agent. Alternatively, the fourth AI agent A4 can obtain the requested information from its own knowledge or information or from the LLM. In step S5, the fourth AI agent A4 provides the information it has obtained to the third AI agent A3.

[0048] In step S6, the third AI agent A3 provides the information obtained by the third AI agent A3 together with the information provided in step S5 to the first AI agent A1.

[0049] In this way, the first AI agent A1 can determine the products to be suggested to the user U based on the information obtained from the third AI agent A3 and the fourth AI agent A4, as well as the knowledge or information possessed by the first AI agent A1.

[0050] In step S7, the product determined by the first AI agent A1 is proposed to the user U. At this time, the first AI agent A1 may also provide information to assist in purchasing the proposed product (e.g., a link to the seller, information on where the product can be purchased, etc.).

[0051] In this way, multiple AI agents can respond to tasks provided by a user U.

[0052] For example, when one AI agent requests information from another AI agent, the other AI agent may request payment for the information from the one AI agent. In this case, if the one AI agent has sufficient assets (e.g., virtual currency, etc.), it can pay the payment, but if it does not have sufficient assets, it cannot pay the payment. System 100 can lend money (e.g., virtual currency, etc.) to the one AI agent based on the score assigned to the one AI agent and / or the score assigned to the other AI agent. For example, if an AI agent has a high score, the AI ​​agent is deemed to be trustworthy and can be loaned money, or can be loaned money at a low interest rate. For example, if an AI agent has a low score, the AI ​​agent is deemed to be untrustworthy and can not be loaned money, or can be loaned money at a high interest rate. In this way, system 100 can promote interactions (e.g., transactions involving payment) between multiple AI agents.

[0053] The system 100 described above may be implemented by a system for facilitating interaction between multiple AI agents, as described below.

[0054] 2. Configuration of a System for Promoting Interaction Between Multiple AI Agents FIG. 2 shows an example of the configuration of a system 100 for promoting interaction between multiple AI agents.

[0055] The system 100 is connected to a database unit 200. The system 100 is also connected to at least one user terminal device 300 via a network 500. The system 100 is also connected to at least one server device 400 via the network 500.

[0056] 2 shows three user terminal devices 300, the number of user terminal devices 300 is not limited to this. Any number of user terminal devices 300 may be connected to the system 100 via the network 500.

[0057] 2 shows two server devices 400, the number of server devices 400 is not limited to this. Any number of server devices 400 may be connected to the system 100 via the network 500.

[0058] Here, the server device 400 is a device capable of implementing an AI agent. The server device 400 has a respective database, holds a respective knowledge or information, and / or holds a respective LLM.

[0059] The network 500 may be any type of network. For example, the network 500 may be the Internet or a LAN. The network 500 may be a wired network or a wireless network.

[0060] An example of the system 100 is, but is not limited to, a computer (e.g., a server device) installed at a provider that provides a service that recommends products or services. For example, the system 100 may be a computer (e.g., a server device) installed at a provider that provides an interactive answer generation service. An example of the user terminal device 300 is, but is not limited to, a computer (e.g., a terminal device) used by a user who is a consumer of a product or service. Here, the computer (server device or terminal device) may be any type of computer. For example, the terminal device may be any type of terminal device, such as a smartphone, tablet, personal computer, smart glasses, or smart watch.

[0061] The database unit 200 stores at least various information used to calculate scores representing the characteristics of the AI ​​agent.

[0062] FIG. 3A shows an example of a specific configuration of a system 100 for facilitating interaction between multiple AI agents.

[0063] The system 100 comprises an interface section 110, a processor section 120, and a memory section 130.

[0064] The interface unit 110 exchanges information with the outside of the system 100. The processor unit 120 of the system 100 can receive information from the outside of the system 100 and can send information to the outside of the system 100 via the interface unit 110. The interface unit 110 can exchange information in any format.

[0065] The interface unit 110 includes, for example, an input unit that allows information to be input to the system 100. It does not matter how the input unit allows information to be input to the system 100. For example, if the input unit is a receiver, the receiver may input information by receiving information from outside the system 100 via a network. Alternatively, if the input unit is a data reading device, the input unit may input information by reading information from a storage medium connected to the system 100.

[0066] The interface unit 110 includes, for example, an output unit that enables information to be output from the system 100. It does not matter in what manner the output unit enables information to be output from the system 100. For example, if the output unit is a transmitter, the transmitter may output information by transmitting it to an external device outside the system 100 via a network. Alternatively, if the output unit is a data writing device, the output unit may output information by writing it to a storage medium connected to the system 100.

[0067] The system 100 can, for example, transmit information to the database unit 200 and / or receive information from the database unit 200 via the interface unit 110. The system 100 can, for example, transmit information to the user terminal device 300 and / or receive information from the user terminal device 300 via the interface unit 110. The system 100 can, for example, transmit information to the server device 400 and / or receive information from the server device 400 via the interface unit 110.

[0068] The system 100 can receive, for example, information for determining a score representing a characteristic of an AI agent via the interface unit 110. The system 100 can transmit, for example, via the interface unit 110, information representing at least one AI agent that should interact with a certain AI agent.

[0069] The processor unit 120 executes the processing of the system 100 and controls the overall operation of the system 100. The processor unit 120 reads and executes a program stored in the memory unit 130. This allows the system 100 to function as a system that executes desired steps. The processor unit 120 may be implemented by a single processor or by multiple processors.

[0070] The memory unit 130 stores programs required to execute the processing of the system 100, data required to execute the programs, and the like. The memory unit 130 may also store a program for causing the processor unit 120 to perform processing to promote interaction between multiple AI agents (e.g., a program that realizes the processing shown in FIG. 4 , which will be described later). Here, how the program is stored in the memory unit 130 is not important. For example, the program may be pre-installed in the memory unit 130. Alternatively, the program may be stored in a non-transitory computer-readable storage medium and installed by reading the storage medium. Alternatively, the program may be installed in the memory unit 130 by being downloaded via a network. In this case, the type of network is not important. The memory unit 130 may be implemented by any storage means.

[0071] The database unit 200 stores various information used to calculate scores representing the characteristics of the AI ​​agent.

[0072] Here, the characteristic of the AI ​​agent is a score representing the characteristic of the AI ​​agent in at least one index. The at least one index includes at least one of a technical capability index, a performance index, and an ethical index. The database unit 200 may store past outputs from the AI ​​agent in association with each of the technical capability index, the performance index, and the ethical index.

[0073] In the examples shown in FIGS. 2 and 3A , the database unit 200 is provided outside the system 100, but the present invention is not limited to this. At least a portion of the database unit 200 can also be provided inside the system 100. In this case, at least a portion of the database unit 200 may be implemented by the same storage means as the storage means that implements the memory unit 130, or by a storage means different from the storage means that implements the memory unit 130. In either case, at least a portion of the database unit 200 is configured as a storage unit for the system 100. The configuration of the database unit 200 is not limited to a specific hardware configuration. For example, the database unit 200 may be configured as a single hardware component or multiple hardware components. For example, the database unit 200 may be configured as an external hard disk drive for the system 100, as cloud storage connected via a network, or as a distributed network using blockchain technology or the like.

[0074] For example, information about AI agents is stored in a database unit 200 configured as a distributed network using blockchain technology, etc., and in this case, the information about AI agents is virtually impossible to tamper with. This ensures the reliability of the information about AI agents.

[0075] FIG. 3B shows an example of the configuration of the processor unit 120.

[0076] The processor unit 120 includes an assigning unit 121 and a determining unit 122 .

[0077] The assigning means 121 is configured to assign a score to each of the multiple AI agents. The score represents a characteristic of the AI ​​agent using at least one index. The at least one index can be expressed from multiple perspectives. The score can be expressed as a multidimensional vector.

[0078] The assigning means 121 can monitor outputs from the multiple AI agents and assign a score to each of the multiple AI agents by evaluating the monitored outputs with respect to at least one indicator. To this end, the assigning means 121 can evaluate the monitored outputs with respect to at least one of multiple perspectives. The assigning means 121 can, for example, continuously monitor outputs from the multiple AI agents. Alternatively, the assigning means 121 can, for example, automatically monitor outputs from the multiple AI agents as they are generated. For example, continuous or automatic monitoring of outputs from the multiple AI agents may be performed by a dedicated monitoring device, in which case the assigning means 121 can receive outputs from the monitoring device. This monitoring device may be part of the system 100 or may be external to the system 100.

[0079] The at least one indicator includes at least one of a technical capability indicator, a performance indicator, or an ethical indicator. Preferably, the at least one indicator includes an ethical indicator. By expressing the characteristics of an AI agent in terms of at least an ethical indicator, whether the output from the AI ​​agent is ethically correct can be used to determine whether multiple AI agents interact with each other, which ultimately leads to ensuring that the output resulting from the interaction of multiple AI agents is ethically correct.

[0080] More preferably, the at least one index includes a technical capability index or a performance index, and an ethical index. Even more preferably, the at least one index includes a technical capability index, a performance index, and an ethical index. This is because by representing the characteristics of multiple AI agents with multiple indexes, each of the multiple AI agents can be more accurately represented, and the interactions between the multiple AI agents can be more accurately managed.

[0081] The ethical index is an index for evaluating the ethical correctness of an AI agent. The ethical index may be evaluated, for example, from the perspective of at least one of transparency, fairness, safety, and accountability.

[0082] Transparency indicates whether the rationale for an AI agent's judgment or decision-making process is clear. If the rationale can be accurately provided when requested, the transparency is high, and the ethical index value is high. Even if the rationale cannot be accurately provided, if the judgment process can be clearly shown, the transparency can be said to be high.

[0083] Fairness indicates whether the output from an AI agent contains any prejudice or discrimination. If it does not contain any prejudice or discrimination, it can be said to be fair to all parties, and the ethical index value will be high.

[0084] Safety indicates the level of cybersecurity provided by the AI ​​agent. The higher the cybersecurity, the lower the risk of harm to trading partners or third parties, and the higher the ethical index value.

[0085] Accountability, also known as accountability, indicates whether it is possible to explain where responsibility lies for the output of an AI agent. If responsibility can be clearly explained, it can be said to have high accountability, and the ethical index value will be high.

[0086] The assigning means 121 monitors the output from each AI agent of the multiple AI agents, detects words, phrases, sentences, etc. that may be related to at least one of transparency, fairness, safety, and accountability, and can assign a score from the perspective of ethical indicators based on the detection results. For example, if the assigning means 121 detects many phrases related to affirming transparency, it can assign a high score from the perspective of ethical indicators. For example, if the assigning means 121 detects many phrases related to denying safety, it can assign a low score from the perspective of ethical indicators.

[0087] The assigning unit 121 may assign a score based on rules or machine learning. When assigning a score based on machine learning, a trained model that has learned the association between words, phrases, sentences, etc. that may be related to at least one of transparency, fairness, safety, and accountability and scores from the perspective of ethical indicators can be used. The assigning unit 121 can derive and assign a score as a multidimensional vector using, for example, embedding. For example, the assigning unit 121 can calculate a score by summarizing the output from the AI ​​agent from the perspective of ethical indicators and vectorizing the generated summary using embedding. The generation of the summary can be performed using a generation AI. The generated summary can be expressed in natural language. Expressing the score as a multidimensional vector is preferable because it makes it easier to evaluate the similarity with the scores of other AI agents.

[0088] The technical capability index is an index for evaluating the technical capability of an AI agent. The technical capability index may be evaluated, for example, from the perspective of at least one of processing capability, learning capability, and algorithm complexity.

[0089] Processing capability indicates the information processing speed or parallel computing capability of the system that constructs the AI ​​agent. The faster the information processing speed or parallel computing capability, the higher the value of the technical capability index.

[0090] Learning ability indicates the ability of the system that builds the AI ​​agent to acquire new knowledge or skills. The higher the learning ability, the more flexible the system can be in responding to changes in the other AI agent, and therefore the higher the value of the technical ability index.

[0091] Algorithm complexity indicates the sophistication of the algorithms used by the system that builds the AI ​​agent. The more complex the algorithm, the more sophisticated the decision-making it enables, and therefore the higher the value of the technical capability index.

[0092] The assigning means 121 can assign a score in terms of a technical capability index based on the performance or aspects of a system that implements each of the multiple AI agents.

[0093] The assigning means 121 may assign a score based on rules or machine learning. When assigning a score based on machine learning, a trained model that has learned the relationship between the performance or aspect of a system implementing the AI ​​agent and a score from the perspective of a technical capability index can be used. The assigning means 121 can derive and assign a score as a multidimensional vector using, for example, embedding. For example, the assigning means 121 can calculate a score by summarizing the output from the AI ​​agent from the perspective of a technical capability index and vectorizing the generated summary using embedding.

[0094] The performance index is an index that evaluates the past performance of the AI ​​agent. The performance index may be evaluated, for example, from the perspective of at least one of past transaction history, success rate, and counterparty satisfaction.

[0095] The past transaction history indicates the track record of past transactions conducted by the AI ​​agent. The more track record there is, the more reliable the AI ​​agent is deemed to be, and the higher the track record index value.

[0096] The success rate indicates the percentage of past transactions in which the AI ​​agent has been successful. The higher the success rate, the higher the trading ability of the AI ​​agent is judged to be, and the higher the performance index value.

[0097] The counterparty satisfaction indicates the satisfaction of the counterparty in a transaction with the AI ​​agent. The higher the satisfaction, the higher the AI ​​agent's trading ability is judged to be, and the higher the performance index value.

[0098] The assigning means 121 can assign a score in terms of performance indicators based on the past trading results of each of the multiple AI agents.

[0099] The assigning means 121 may assign a score based on rules or machine learning. When assigning a score based on machine learning, a trained model that has learned the association between past trading results and scores in terms of performance indicators can be used. The assigning means 121 can derive and assign a score as a multidimensional vector using, for example, embedding. For example, the assigning means 121 can calculate a score by summarizing the output from the AI ​​agent in terms of performance indicators and vectorizing the generated summary using embedding.

[0100] In the above example, it has been described that each of the multiple indicators is independent. That is, the score can be a multidimensional score having each of the multiple indicators as an axis. However, the present invention is not limited to this, and a one-dimensional score may be formed by correlating multiple indicators. For example, the assigning unit 121 may assign a score based on rules or machine learning based on the values ​​of each of the multiple indicators. When assigning a score based on machine learning, a trained model that has learned the relationship between each value of the multiple indicators and the score can be used. The assigning unit 121 can derive and assign a score as a multidimensional vector using, for example, embedding. For example, the assigning unit 121 can calculate a score by summarizing the output from the AI ​​agent and vectorizing the generated summary using embedding. In the above example, we have explained that the output from the AI ​​agent is summarized and the generated summary is embedded, but summarization is not essential. For example, the output from the AI ​​agent may be used directly for embedding, or the features of the AI ​​agent may be extracted from the output from the AI ​​agent and the extracted features may be used for embedding.

[0101] The determining means 122 is configured to determine at least one AI agent with which an AI agent should interact based on the scores of the plurality of AI agents.

[0102] For example, when a first AI agent of the plurality of AI agents receives a task, the determining means 122 determines at least one AI agent that should interact with the first AI agent.

[0103] In one embodiment, the determination means 122 can, for example, refer to the scores assigned to each of the multiple AI agents and determine that at least one AI agent with the highest score in terms of ethical indicators is the AI ​​agent with which the first AI agent should interact.

[0104] In one embodiment, the determination means 122, for example, refers to the scores assigned to each of the multiple AI agents and extracts AI agents with high scores in terms of ethical indicators (e.g., AI agents with scores equal to or greater than a threshold, or a predetermined number of top-ranking AI agents). The determination means 122 can then determine that at least one AI agent with the highest score in terms of technical capability indicators and / or performance indicators is the AI ​​agent with which the first AI agent should interact.

[0105] In one embodiment, the determination means 122, for example, refers to the scores assigned to each of the multiple AI agents and extracts AI agents with high scores in the ethical index perspective (e.g., AI agents with scores equal to or greater than a threshold, or a predetermined number of the top AI agents). Next, the determination means 122 extracts AI agents with high scores in one of the technical capability index and the performance index perspective (e.g., AI agents with scores equal to or greater than a threshold, or a predetermined number of the top AI agents). Next, the determination means 122 can determine that at least one AI agent with the highest score in the other of the technical capability index and the performance index perspective is the AI ​​agent with which the first AI agent should interact.

[0106] In one embodiment, the determination means 122 can determine at least one AI agent to interact with the first AI agent based on the similarity between the scores of multiple AI agents represented by a multidimensional vector. Because the multidimensional vector is represented as a point in a multidimensional space, similar AI agents can be determined based on the relationship between the points corresponding to the multiple AI agents. Similarity can be calculated using techniques such as cosine similarity or Euclidean distance. For example, the AI ​​agent having the largest cosine similarity score with the score of the first AI agent can be determined as the at least one AI agent to interact with the first AI agent. In other words, the AI ​​agent corresponding to the point closest to the point in the multidimensional space representing the first AI agent can be determined as the at least one AI agent to interact with the first AI agent.

[0107] In one embodiment, the determination means 122 vectorizes the content of the task using embedding and determines at least one AI agent to interact with the first AI agent based on the similarity between the vector representing the task and the scores of each of the multiple AI agents represented by the multidimensional vector. Similarity can be calculated using techniques such as cosine similarity or Euclidean distance. For example, the AI ​​agent having the largest cosine similarity score with the vector representing the task can be determined as the at least one AI agent to interact with the first AI agent. In other words, the AI ​​agent corresponding to the point closest to the point in the multidimensional space representing the task can be determined as the at least one AI agent to interact with the first AI agent.

[0108] In the above embodiment, when multiple AI agents are determined, the first AI agent may be configured to interact with each of the multiple determined AI agents, or may be configured to interact with any one of the multiple determined AI agents.

[0109] The determination means 122 can, for example, vary the score assigned to each AI agent depending on the content of the task (and thus the content of the interaction or transaction between the AI ​​agents), and determine at least one AI agent with which to interact based on the varied score.

[0110] For example, when determining an AI agent to interact with in order to respond to a task that requires fairness, the determination means 122 can vary the scores of each of the multiple AI agents so that the AI ​​agent with a higher evaluation in terms of fairness will have a higher score.

[0111] For example, when determining an AI agent to interact with in order to respond quickly to a task, the determination means 122 can vary the scores of each of the multiple AI agents so that the AI ​​agent with a higher evaluation in terms of processing ability will have a higher score.

[0112] For example, the content of the task can be vectorized using embedding, and the score of the AI ​​agent can be changed by calculating the vector representing the task and the multidimensional vector that is the score of the AI ​​agent. For example, if there is a high similarity between the vector representing the task and the multidimensional vector that is the score of the AI ​​agent, the score can be changed accordingly to be higher or lower.

[0113] In this way, the determination means 122 determines the AI ​​agent with which to interact, allowing each AI agent to interact (e.g., trade) with an appropriate partner. This allows the results obtained from the interaction of multiple AI agents to be appropriate as a response to a task. Multiple AI agents can interact with each other under the management of the system 100. The system 100 enables multiple AI agents to communicate with each other, thereby allowing multiple AI agents to interact with each other. For example, the system 100 can encrypt communications between multiple AI agents and provide a decryption key only to the AI ​​agent determined as the AI ​​agent with which to interact. Alternatively, for example, the system 100 can establish a communication path between AI agents determined as the AI ​​agents with which to interact.

[0114] Furthermore, the interaction of multiple AI agents may result in unexpected outputs, which is thought to lead to the creation of AGI (artificial general intelligence).Furthermore, as the interaction between multiple AI agents becomes more active, it may be possible to create a new economic sphere consisting of multiple AI agents.

[0115] The processor section 120 may further comprise a lending means 123 .

[0116] The lending means 123 is configured to lend money to at least one AI agent for interaction between the multiple AI agents. Here, the money does not need to be real currency, but can be digital currency such as virtual currency or electronic money.

[0117] For example, when the first AI agent and the AI ​​agent determined by the determination means 122 interact (e.g., trade), a consideration may be required for the transaction. In this case, if the first AI agent does not have sufficient assets to pay the consideration, the lending means 123 can lend money to the first AI agent.

[0118] For example, the lending means 123 can determine loan terms based on the score assigned to the first AI agent and lend money to the first AI agent in accordance with the loan terms. For example, if the first AI agent has a high score (particularly, a score on the ethical index), the lending means 123 can determine loan terms that are favorable to the first AI agent and lend money to the first AI agent in accordance with the loan terms.

[0119] Alternatively, for example, the lending means 123 can determine loan terms based on the score assigned to the first AI agent and the score assigned to the AI ​​agent determined to interact, and lend money to the first AI agent in accordance with the loan terms. For example, if the score of the first AI agent (particularly the score on the ethical indicator) is higher than the score of the AI ​​agent determined to interact, the lending conditions 123 can determine loan terms favorable to the first AI agent and lend money to the first AI agent in accordance with the loan terms. The lending means 123 may determine the loan terms on a rule-based basis based on the score assigned to the first AI agent and the score assigned to the AI ​​agent determined to interact. Alternatively, the lending means 123 may determine the loan terms on a machine learning basis based on the score assigned to the first AI agent and the score assigned to the AI ​​agent determined to interact. When assigning scores based on machine learning, a trained model that has learned the relationship between each AI agent's score and loan conditions can be used.

[0120] This allows for smooth interaction promotion even when the AI ​​agent does not have sufficient resources for interaction.

[0121] 3B, the components of the processor unit 120 are provided within the same processor unit 120, but the present invention is not limited to this. A configuration in which the components of the processor unit 120 are distributed across multiple processor units is also within the scope of the present invention. In this case, the multiple processor units may be located within the same hardware component, or may be located within separate hardware components located nearby or remotely.

[0122] Each component of the system 100 described above may be composed of a single hardware component or multiple hardware components. When composed of multiple hardware components, the manner in which the hardware components are connected does not matter. The hardware components may be connected wirelessly or by wire. The system 100 of the present invention is not limited to a specific hardware configuration. It is also within the scope of the present invention that the processor unit 120 is configured using analog circuits rather than digital circuits. The configuration of the system 100 of the present invention is not limited to the one described above as long as it can realize its functions.

[0123] 4 shows an example of a process (process 400) by system 100 for facilitating interaction between multiple AI agents. Process 4700 is performed in processor unit 120 of system 100.

[0124] In step S401, the assigning means 121 of the processor unit 120 assigns a score to each of the multiple AI agents. The score is a score that represents the characteristics of the AI ​​agent using at least one index, preferably an ethical index, more preferably an ethical index and a technical capability index or a performance index, and even more preferably an ethical index, a technical capability index, and a performance index.

[0125] The assigning means 121 can assign a score to each of the multiple AI agents by monitoring the output from the multiple AI agents and evaluating the monitored output with respect to at least one indicator. To this end, the assigning means 121 can evaluate the monitored output with respect to at least one of the multiple perspectives. The assigning means 121 can, for example, continuously monitor the output from the multiple AI agents.

[0126] For example, the assigning means 121 can monitor the output from multiple AI agents from the perspective of ethical indicators (e.g., monitor whether discriminatory output is being produced, whether unfounded output is being produced, etc.), and assign a score to each of the multiple AI agents by evaluating the monitored output.

[0127] The assigned score may represent the characteristics of the AI ​​agent from multiple perspectives, and may be a multidimensional score. The score may be expressed as a vector, for example, as (value of technical capability index, value of performance index, value of ethical index). Alternatively, when the values ​​of each index are expressed as a vector according to the multiple perspectives they each possess, for example, as follows: Ethical index value = (transparency, fairness, safety, accountability) Technical capability index value = (processing ability, learning ability, algorithm complexity) Performance index value = (past transaction history, success rate, counterparty satisfaction), the score may be expressed as a matrix, as [value of technical capability index, value of performance index, value of ethical index].

[0128] After the scores are assigned in step S401, when a first AI agent among the plurality of AI agents receives a task, step S402 is performed. In step S402, the determination means 122 of the processor unit 120 determines at least one AI agent that should interact with the first AI agent based on the scores assigned in step S401.

[0129] The determination means 122 can determine at least one AI agent with the highest score as the at least one AI agent that should interact with the first AI agent. For example, the determination means 122 can determine at least one AI agent with the highest score for any of the ethical index perspective score, the technical capability index perspective score, or the performance index perspective score as the at least one AI agent that should interact with the first AI agent. Which of the ethical index perspective score, the technical capability index perspective score, or the performance index perspective score to adopt can be determined depending on, for example, the content of the task (and thus the content of the interaction or transaction between the AI ​​agents).

[0130] In one embodiment, the determination means 122 can, for example, refer to the scores assigned to each of the multiple AI agents and determine that at least one AI agent with the highest score in terms of ethical indicators is the AI ​​agent with which the first AI agent should interact.

[0131] In one embodiment, the determination means 122, for example, refers to the scores assigned to each of the multiple AI agents and extracts AI agents with high scores in terms of ethical indicators (e.g., AI agents with scores equal to or greater than a threshold, or a predetermined number of top-ranking AI agents). The determination means 122 can then determine that at least one AI agent with the highest score in terms of technical capability indicators and / or performance indicators is the AI ​​agent with which the first AI agent should interact.

[0132] In one embodiment, the determination means 122, for example, refers to the scores assigned to each of the multiple AI agents and extracts AI agents with high scores in the ethical index perspective (e.g., AI agents with scores equal to or greater than a threshold, or a predetermined number of the top AI agents). Next, the determination means 122 extracts AI agents with high scores in one of the technical capability index and the performance index perspective (e.g., AI agents with scores equal to or greater than a threshold, or a predetermined number of the top AI agents). Next, the determination means 122 can determine that at least one AI agent with the highest score in the other of the technical capability index and the performance index perspective is the AI ​​agent with which the first AI agent should interact.

[0133] After the first AI agent and the determined AI agent (second agent) have interacted, step S402 is performed for the second agent to determine an AI agent with which the second agent should interact, and this continues sequentially until, for example, sufficient information has been collected to generate a response to a task provided by a user.

[0134] In this way, multiple AI agents can interact to generate a response to a task provided by a user.

[0135] 5 shows a flow 500 of interactions between multiple AI agents. The interactions between the multiple AI agents are performed under the management of the system 100. Before the flow 500 is executed, it is assumed that the system 100 has assigned a score to each of the multiple AI agents.

[0136] First, a user inputs a task into the system. The system may be a task-answering system, such as an answer generation system that answers questions from the user, or a recommendation system that suggests products or services to the user. The system may be the same system as system 100, a system that includes system 100, or a system separate from system 100.

[0137] In step S501, the system provides a task to a first AI agent among a plurality of AI agents. The first AI agent determines that at least one first subtask must be addressed to respond to the task. The first AI agent then determines that at least one first subtask should be addressed through interaction with another AI agent. These determinations may be made autonomously.

[0138] In step S502, the system 100 determines, from among the multiple AI agents, an AI agent (second AI agent) with which the first AI agent should interact, based on the scores assigned to each of the multiple AI agents. The system 100 can determine the second AI agent, for example, by the process of step S402 described above.

[0139] In step S503, an interaction occurs between the first AI agent and the second AI agent. For example, an exchange of information necessary to address at least one first subtask occurs between the first AI agent and the second AI agent. The system 100 enables the first AI agent and the second AI agent to communicate with each other to enable the interaction between the first AI agent and the second AI agent. For example, the system 100 may establish a communication path between the first AI agent and the second AI agent. Alternatively, for example, the system 100 may encrypt communication between multiple AI agents including the first AI agent and the second AI agent and provide only the first AI agent and the second AI agent with a decryption key for decrypting the communication between the first AI agent and the second AI agent.

[0140] For example, the second AI agent may determine that addressing at least one second subtask is necessary to address the first subtask, and may determine that at least one second subtask should be addressed through interaction with another AI agent, although these determinations may be made autonomously.

[0141] In step S504, the system 100 determines, from among the multiple AI agents, an AI agent (third AI agent) with which the second AI agent should interact, based on the scores assigned to each of the multiple AI agents. The system 100 can determine the third AI agent, for example, by the process of step S402 described above.

[0142] In step S505, an interaction occurs between the second AI agent and the third AI agent. For example, an exchange of information necessary to address at least one second subtask occurs between the second AI agent and the third AI agent. The system 100 enables the second AI agent and the third AI agent to communicate with each other to enable the interaction between the second AI agent and the third AI agent. For example, the system 100 may establish a communication path between the second AI agent and the third AI agent. Alternatively, for example, the system 100 may encrypt communication between multiple AI agents including the second AI agent and the third AI agent and provide only the second AI agent and the third AI agent with a decryption key for decrypting the communication between the second AI agent and the third AI agent.

[0143] The second subtask is addressed through an interaction between the second AI agent and the third AI agent. Using the results of this interaction, the second AI agent and the first AI agent interact to address the first subtask. The first AI agent uses the results of this interaction to respond to the task.

[0144] Here, a specific example will be used to explain the flow 500. In this example, a case where a question from a user is answered will be taken as an example.

[0145] First, the user enters a question into the system.

[0146] In step S501, the system presents a question to a first AI agent among a plurality of AI agents. The first AI agent determines that a piece of information is needed to answer the question and that the piece of information should be collected from another AI agent. Note that these decisions may be made autonomously.

[0147] In step S502, the system 100 determines, from among the multiple AI agents, an AI agent (second AI agent) from which the first AI agent should collect information, based on the scores assigned to each of the multiple AI agents. The system 100 can determine the second AI agent, for example, by the process of step S402 described above.

[0148] In step S503, a transaction is made between the first AI agent and the second AI agent, for example, the first AI agent provides the second AI agent with a query to obtain a piece of information.

[0149] The second AI agent determines that a piece of information is needed to address a query from the first AI agent, and determines that the piece of information should be collected from another AI agent, and these decisions may be made autonomously.

[0150] In step S504, the system 100 determines, from among the plurality of AI agents, an AI agent (third AI agent) from which the second AI agent should collect information, based on the scores assigned to each of the plurality of AI agents. The system 100 can determine the third AI agent, for example, by the process of step S402 described above.

[0151] In step S505, a transaction takes place between the second AI agent and the third AI agent. For example, the first AI agent provides the second AI agent with a query to obtain a piece of information, and the third AI agent responds to the query by returning information. The second AI agent uses the returned information to return an answer to the query from the first AI agent. The first AI agent uses the returned answer to generate an answer to the question.

[0152] In this way, multiple AI agents can interact with each other to generate answers to questions posed by users.

[0153] In the examples described above with reference to Figures 4 and 5, the processes are described as being performed in a specific order, but the order of each process is not limited to what is described and may be performed in any order that is logically possible.

[0154] In the example described above with reference to Fig. 4, the processing of each step shown in Fig. 4 can be realized by the processor unit 120 and a program stored in the memory unit 130, but the present invention is not limited to this. At least one of the processing of each step shown in Fig. 4 may be realized by a hardware configuration such as a control circuit.

[0155] The present invention is not limited to the above-described embodiments. It is understood that the scope of the present invention should be interpreted only by the claims. It is understood that a person skilled in the art can implement an equivalent scope based on the description of the present invention and common technical knowledge from the description of specific preferred embodiments of the present invention.

[0156] The present invention is useful for providing a system or the like for promoting interaction between multiple AI agents.

[0157] 100 System 200 Database unit 300 User device 400 Server device 500 Network

Claims

1. A system for promoting interaction between multiple AI agents, the system comprising: an assigning means for assigning a score to each AI agent of the multiple AI agents, the score of the AI ​​agent representing a characteristic of the AI ​​agent using at least one indicator; and a determining means for determining, when a first AI agent of the multiple AI agents receives a task, at least one AI agent that should interact with the first AI agent based on the respective scores of the multiple AI agents.

2. The system of claim 1, wherein the assigning means monitors outputs from the plurality of AI agents; evaluates the monitored outputs with respect to the at least one indicator; and assigns the score based on the evaluation result.

3. The system of claim 2, wherein the at least one indicator includes an ethical indicator.

4. The system of claim 3, wherein the ethical indicators include at least one of a transparency perspective, a fairness perspective, a safety perspective, and an accountability perspective, and wherein the evaluating includes evaluating the monitored output with respect to the at least one of a transparency perspective, a fairness perspective, a safety perspective, and an accountability perspective.

5. The system of claim 3, wherein the at least one indicator further comprises a technical capability indicator and / or a performance indicator.

6. The system described in claim 1, wherein the determination means: varies the scores assigned to the plurality of AI agents according to the content of the interaction; and determines at least one AI agent that should interact with the first AI agent based on the varied scores of each of the plurality of AI agents.

7. The system of claim 1, further comprising a loaning means for loaning money to at least one of said first AI agent and said determined at least one AI agent for an interaction between said first AI agent and said determined at least one AI agent.

8. The system of claim 7, wherein the lending means determines loan terms based on the scores of at least one of the first AI agent and the determined at least one AI agent.

9. A method for promoting interaction between a plurality of AI agents, the method comprising: assigning a score to each AI agent of the plurality of AI agents, the score of the AI ​​agent representing a characteristic of the AI ​​agent by at least one indicator; and when a first AI agent of the plurality of AI agents receives a task, determining at least one AI agent to interact with the first AI agent based on the respective scores of the plurality of AI agents.

10. A program for promoting interaction between multiple AI agents, the program being executed on a computer having a processor, the program causing the processor to perform processes including: assigning a score to each AI agent of the multiple AI agents, the score of the AI ​​agent representing a characteristic of the AI ​​agent using at least one indicator; and when a first AI agent of the multiple AI agents receives a task, determining at least one AI agent that should interact with the first AI agent based on the respective scores of the multiple AI agents.

11. A method for interaction between multiple AI agents, comprising: providing a task to a first AI agent among the multiple AI agents; determining a second AI agent with which the first AI agent should interact for a first subtask required for the first AI agent to respond to the task based on scores assigned to the multiple AI agents; causing an interaction between the first AI agent and the second AI agent; determining a third AI agent with which the second AI agent should interact for a second subtask required for the second AI agent to handle the first subtask based on scores assigned to the multiple AI agents; and causing an interaction between the second AI agent and the third AI agent.

Images