#Multi-Agent Systems
Latest news articles tagged with "Multi-Agent Systems". Follow the timeline of events, related topics, and entities.
Articles (30)
-
πΊπΈ GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems
[USA]
arXiv:2603.19677v1 Announce Type: cross Abstract: Large language model (LLM)-based multi-agent systems (MAS) have demonstrated exceptional capabilities in solving complex tasks, yet their effectivene...
Related: #LLM Communication -
πΊπΈ MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution
[USA]
arXiv:2603.18718v1 Announce Type: new Abstract: Memory-augmented LLM agents maintain external memory banks to support long-horizon interaction, yet most existing systems treat construction, retrieval...
Related: #AI Memory Management -
πΊπΈ Conflict-Based Search for Multi Agent Path Finding with Asynchronous Actions
[USA]
arXiv:2603.18866v1 Announce Type: new Abstract: Multi-Agent Path Finding (MAPF) seeks collision-free paths for multiple agents from their respective start locations to their respective goal locations...
Related: #Path Planning -
πΊπΈ Governed Memory: A Production Architecture for Multi-Agent Workflows
[USA]
arXiv:2603.17787v1 Announce Type: new Abstract: Enterprise AI deploys dozens of autonomous agent nodes across workflows, each acting on the same entities with no shared memory and no common governanc...
Related: #Memory Architecture -
πΊπΈ When Only the Final Text Survives: Implicit Execution Tracing for Multi-Agent Attribution
[USA]
arXiv:2603.17445v1 Announce Type: new Abstract: When a multi-agent system produces an incorrect or harmful answer, who is accountable if execution logs and agent identifiers are unavailable? Multi-ag...
Related: #AI Accountability -
πΊπΈ Cascade-Aware Multi-Agent Routing: Spatio-Temporal Sidecars and Geometry-Switching
[USA]
arXiv:2603.17112v1 Announce Type: new Abstract: A common architectural pattern in advanced AI reasoning systems is the symbolic graph network: specialized agents or modules connected by delegation ed...
Related: #Routing Algorithms -
πΊπΈ Loosely-Structured Software: Engineering Context, Structure, and Evolution Entropy in Runtime-Rewired Multi-Agent Systems
[USA]
arXiv:2603.15690v1 Announce Type: cross Abstract: As LLM-based multi-agent systems (MAS) become more autonomous, their free-form interactions increasingly dominate system behavior. However, scaling t...
Related: #Software Engineering -
πΊπΈ MAC: Multi-Agent Constitution Learning
[USA]
arXiv:2603.15968v1 Announce Type: new Abstract: Constitutional AI is a method to oversee and control LLMs based on a set of rules written in natural language. These rules are typically written by hum...
Related: #AI Ethics -
πΊπΈ DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs
[USA]
arXiv:2603.15661v1 Announce Type: new Abstract: Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable collaborative reasoning capabilities but introduce new attack surface...
Related: #Cybersecurity -
πΊπΈ SAGE: Multi-Agent Self-Evolution for LLM Reasoning
[USA]
arXiv:2603.15255v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards improves reasoning in large language models (LLMs), but many methods still rely on large human-labeled d...
Related: #AI Reasoning -
πΊπΈ Orla: A Library for Serving LLM-Based Multi-Agent Systems
[USA]
arXiv:2603.13605v1 Announce Type: new Abstract: We introduce Orla, a library for constructing and running LLM-based agentic systems. Modern agentic applications consist of workflows that combine mult...
Related: #AI Development -
πΊπΈ Brain-Inspired Graph Multi-Agent Systems for LLM Reasoning
[USA]
arXiv:2603.15371v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of language tasks, yet complex multi-step reasoning remains ...
Related: #AI Reasoning -
πΊπΈ Training-Free Agentic AI: Probabilistic Control and Coordination in Multi-Agent LLM Systems
[USA]
arXiv:2603.13256v1 Announce Type: cross Abstract: Multi-agent large language model (LLM) systems enable complex, long-horizon reasoning by composing specialized agents, but practical deployment remai...
Related: #AI Coordination -
πΊπΈ Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning
[USA]
arXiv:2603.15054v1 Announce Type: new Abstract: Effective communication is pivotal for addressing complex collaborative tasks in multi-agent reinforcement learning (MARL). Yet, limited communication ...
Related: #Reinforcement Learning -
πΊπΈ LLM Constitutional Multi-Agent Governance
[USA]
arXiv:2603.13189v1 Announce Type: cross Abstract: Large Language Models (LLMs) can generate persuasive influence strategies that shift cooperative behavior in multi-agent populations, but a critical ...
Related: #AI Governance -
πΊπΈ Multi-Agent Guided Policy Optimization
[USA]
arXiv:2507.18059v2 Announce Type: replace Abstract: Due to practical constraints such as partial observability and limited communication, Centralized Training with Decentralized Execution (CTDE) has ...
Related: #Reinforcement Learning, #AI Optimization -
πΊπΈ Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization
[USA]
arXiv:2603.12933v1 Announce Type: new Abstract: Large Language Model (LLM)-driven Multi-Agent Systems (MAS) have demonstrated strong capability in complex reasoning and tool use, and heterogeneous ag...
Related: #AI Optimization -
πΊπΈ Exploiting Expertise of Non-Expert and Diverse Agents in Social Bandit Learning: A Free Energy Approach
[USA]
arXiv:2603.11757v1 Announce Type: cross Abstract: Personalized AI-based services involve a population of individual reinforcement learning agents. However, most reinforcement learning algorithms focu...
Related: #Machine Learning -
πΊπΈ Multi-Agent Memory from a Computer Architecture Perspective: Visions and Challenges Ahead
[USA]
arXiv:2603.10062v1 Announce Type: cross Abstract: As LLM agents evolve into collaborative multi-agent systems, their memory requirements grow rapidly in complexity. This position paper frames multi-a...
Related: #Computer Architecture -
πΊπΈ Learning to Negotiate: Multi-Agent Deliberation for Collective Value Alignment in LLMs
[USA]
arXiv:2603.10476v1 Announce Type: cross Abstract: The alignment of large language models (LLMs) has progressed substantially in single-agent settings through paradigms such as RLHF and Constitutional...
Related: #AI Ethics -
πΊπΈ Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language Models
[USA]
arXiv:2603.10098v1 Announce Type: cross Abstract: Recent advances in multi-agent reinforcement learning, particularly Policy-Space Response Oracles (PSRO), have enabled the computation of approximate...
Related: #AI Interpretability -
πΊπΈ KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization
[USA]
arXiv:2603.10085v1 Announce Type: cross Abstract: Improving GPU kernel efficiency is crucial for advancing AI systems. Recent work has explored leveraging large language models (LLMs) for GPU kernel ...
Related: #GPU Optimization -
πΊπΈ Multi-Agent Reinforcement Learning with Communication-Constrained Priors
[USA]
arXiv:2512.03528v3 Announce Type: replace Abstract: Communication is one of the effective means to improve the learning of cooperative policy in multi-agent systems. However, in most real-world scena...
Related: #Artificial Intelligence, #Machine Learning -
πΊπΈ MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games
[USA]
arXiv:2603.09022v1 Announce Type: new Abstract: Multi-turn, multi-agent LLM game evaluations often exhibit substantial run-to-run variance. In long-horizon interactions, small early deviations compou...
Related: #AI Optimization -
πΊπΈ Reinforcing the World's Edge: A Continual Learning Problem in the Multi-Agent-World Boundary
[USA]
arXiv:2603.06813v1 Announce Type: new Abstract: Reusable decision structure survives across episodes in reinforcement learning, but this depends on how the agent--world boundary is drawn. In stationa...
Related: #Continual Learning -
πΊπΈ Breaking the Martingale Curse: Multi-Agent Debate via Asymmetric Cognitive Potential Energy
[USA]
arXiv:2603.06801v1 Announce Type: new Abstract: Multi-Agent Debate (MAD) has emerged as a promising paradigm for enhancing large language model reasoning. However, recent work reveals a limitation:st...
Related: #AI Reasoning -
πΊπΈ The Yerkes-Dodson Curve for AI Agents: Emergent Cooperation Under Environmental Pressure in Multi-Agent LLM Simulations
[USA]
arXiv:2603.07360v1 Announce Type: new Abstract: Designing environments that maximize the rate of emergent behavior development in AI agents remains an open problem. We present the first systematic st...
Related: #AI Psychology, #Emergent Behavior -
πΊπΈ MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing
[USA]
arXiv:2603.06007v1 Announce Type: cross Abstract: Large language model-based (LLM-based) multi-agent systems (MAS) are increasingly used to extend agentic problem solving via role specialization and ...
Related: #LLM Orchestration -
πΊπΈ EigenData: A Self-Evolving Multi-Agent Platform for Function-Calling Data Synthesis, Auditing, and Repair
[USA]
arXiv:2603.05553v1 Announce Type: cross Abstract: Function-calling agents -- large language models that invoke tools and APIs -- require high-quality, domain-specific training data spanning executabl...
Related: #AI Data Management -
πΊπΈ SCoUT: Scalable Communication via Utility-Guided Temporal Grouping in Multi-Agent Reinforcement Learning
[USA]
arXiv:2603.04833v1 Announce Type: cross Abstract: Communication can improve coordination in partially observed multi-agent reinforcement learning (MARL), but learning \emph{when} and \emph{who} to co...
Related: #Reinforcement Learning
Key Entities (4)
- Large language model (2 news)
- MEMO model (wind-flow simulation) (1 news)
- AI agent (1 news)
- Sage (1 news)
About the topic: Multi-Agent Systems
The topic "Multi-Agent Systems" aggregates 30+ news articles from various countries.