concept

multi-agent system

Also known as: multi-agent system, Multi-agent systems, multiagent system, MAS

Facts (17)

Sources

Unlocking the Potential of Generative AI through Neuro-Symbolic ... arxiv.org arXiv Feb 16, 2025 5 facts

claimIn mixture of experts (MoE)-based multi-agent systems, each expert operates as an autonomous agent specializing in distinct sub-tasks or data domains, while a dynamic gating mechanism orchestrates their contributions.

referenceDiego Maldonado, Edison Cruz, Jackeline Abad Torres, Patricio J. Cruz, and Silvana Gamboa published 'Multi-agent systems: A survey about its components, framework and workflow' in IEEE Access in 2024.

claimMixture of experts (MoE) architectures enhance scalability and specialization in collaborative frameworks for multi-agent systems.

claimThe integration of multi-agent systems with neuro-symbolic methods enables improved decision-making, transparency, and traceability, which are critical for sensitive applications.

claimMulti-agent systems explore the coordination and decision-making among multiple intelligent agents.

A Comprehensive Benchmark and Evaluation Framework for Multi ... arxiv.org arXiv Jan 6, 2026 3 facts

referenceA comparative analysis of medical AI implementation methods indicates that Prompt Engineering has very low implementation cost but low consistency, RAG has moderate implementation cost and high consistency, Fine-Tuning has high implementation cost and moderate consistency, and Multi-Agent systems have very high implementation cost and very high consistency.

claimThe integration of Retrieval-Augmented Generation (RAG) and Multi-Agent Systems (MAS) enables patient agents to interact with simulated Electronic Health Records (EHR) and external diagnostic tools.

procedureThe Multi-Step Record Generation stage uses a multi-agent system to generate patient records in stages (Disease Overview, Basic Information) while applying rules to ensure internal consistency, such as ensuring symptom progression aligns with the disease stage and preventing incompatible comorbid conditions.

Neuro-Symbolic AI: Explainability, Challenges, and Future Trends arxiv.org arXiv Nov 7, 2024 2 facts

referenceBowen Jiang, Yangxinyu Xie, Xiaomeng Wang, Weijie J Su, Camillo J Taylor, and Tanwi Mallick authored the survey 'Multi-Modal and Multi-Agent Systems Meet Rationality: A Survey', published as an arXiv preprint (arXiv:2406.00252) in 2024.

referenceJiyoun Moon proposed a plugin framework-based neuro-symbolic grounded task planning method for multi-agent systems in 2021.

A comprehensive overview on demand side energy management ... link.springer.com Springer Mar 13, 2023 1 fact

referenceWang and Paranjape (2015) proposed an optimal residential demand response framework for multiple heterogeneous homes using real-time price prediction in a multiagent system, published in IEEE Transactions on Smart Grid.

Cybersecurity Trends and Predictions 2025 From Industry Insiders itprotoday.com ITPro Today 1 fact

claimMulti-agent systems will emerge as a new challenge in 2025, as attackers will use these systems to orchestrate sophisticated, automated attacks, forcing defenders to adopt similarly sophisticated AI solutions.

KR 2026 : 23rd International Conference on Principles of ... - WikiCFP wikicfp.com WikiCFP 1 fact

claimThe 23rd International Conference on Principles of Knowledge Representation and Reasoning (KR 2026) covers research topics including argumentation, belief change, common-sense reasoning, computational aspects of knowledge representation, description logics, ethical considerations in knowledge representation, explanation, abduction and diagnosis, geometric, spatial, and temporal reasoning, inconsistency- and exception-tolerant reasoning, knowledge acquisition, knowledge compilation, automated reasoning, satisfiability and model counting, knowledge representation languages, logic programming, answer set programming, model learning for diagnosis and planning, modeling and reasoning about preferences, modeling constraints and constraint solving, multi- and order-sorted representations and reasoning, non-monotonic logics, ontologies and knowledge-enriched data management, philosophical foundations of knowledge representation, qualitative reasoning, reasoning about actions and change, action languages, reasoning about knowledge, beliefs, and other mental attitudes, reasoning in knowledge graphs, reasoning in multi-agent systems, semantic web, similarity-based and contextual reasoning, and uncertainty and vagueness.

The Synergy of Symbolic and Connectionist AI in LLM-Empowered ... arxiv.org arXiv Jul 11, 2024 1 fact

claimFoundational techniques for autonomous agent design originate from classic AI approaches, including Probabilistic Graphical Models, Reinforcement Learning, and Multi-Agent Systems, which manage uncertainty, learn optimal behaviors in dynamic environments, and enable agents to interact and share information efficiently.

A critical review on techno-economic analysis of hybrid renewable ... link.springer.com Springer Dec 6, 2023 1 fact

claimThe multi-agent system (MAS) is a viable option for distributed control systems and is frequently employed in power consolidation, recovery and reconstruction, and integrated system power management.

Call for Papers: Main Track - KR 2026 kr.org KR 1 fact

claimThe KR 2026 conference accepts submissions on topics including argumentation, belief change, common-sense reasoning, computational aspects of knowledge representation, description logics, ethical considerations in KR, explanation/abduction/diagnosis, geometric/spatial/temporal reasoning, inconsistency- and exception-tolerant reasoning, knowledge acquisition, knowledge compilation/automated reasoning/satisfiability/model counting, knowledge representation languages, logic programming/answer set programming, model learning for diagnosis and planning, modeling and reasoning about preferences, modeling constraints and constraint solving, multi- and order-sorted representations and reasoning, non-monotonic logics, ontologies and knowledge-enriched data management, philosophical foundations of KR, qualitative reasoning, reasoning about actions and change/action languages, reasoning about knowledge/beliefs/mental attitudes, reasoning in knowledge graphs, reasoning in multi-agent systems, semantic web, similarity-based and contextual reasoning, and uncertainty and vagueness.

LLM-empowered knowledge graph construction: A survey - arXiv arxiv.org arXiv Oct 23, 2025 1 fact

referenceThe KARMA framework (Lu & Wang, 2025) is a multi-agent system that unifies schema-level and instance-level fusion within an end-to-end workflow, using specialized agents to handle schema alignment, conflict resolution, and quality evaluation.