Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems
Multi-agent systems built on large language models have shown strong performance on complex reasoning tasks, yet most work focuses on agent roles and orchestration while treating inter-agent communication as a fixed interface. Latent communication through internal representations such as key-value caches offers a promising alternative to text-based protocols, but existing approaches do not jointly optimize communication with multi-agent reasoning. Therefore we propose DiffMAS, a training framework that treats latent communication as a learnable component of multi-agent systems. DiffMAS performs parameter-efficient supervised training over multi-agent latent trajectories, enabling agents to jointly learn how information should be encoded and interpreted across interactions. Experiments on mathematical reasoning, scientific QA, code generation, and commonsense benchmarks show that DiffMAS consistently improves reasoning accuracy and decoding stability over single-agent inference, text-based multi-agent systems, and prior latent communication methods, achieving 26.7% on AIME24, 20.2% on GPQA-Diamond, and consistent gains across reasoning benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
Mathematical ReasoningCode GenerationSimilar Papers 제목 키워드 기반
Large Language Model-Enabled Multi-Agent Manufacturing Systems
Traditional manufacturing faces challenges adapting to dynamic environments and quickly responding to manufacturing changes. The use of multi-agent systems has improved adaptability and coordination but requires further …
Decision MakingLanguage ModelingLanguage ModellingLarge Language Model+1Optimization for Reinforcement Learning: From Single Agent to Cooperative Agents
This article reviews recent advances in multi-agent reinforcement learning algorithms for large-scale control systems and communication networks, which learn to communicate and cooperate. We provide an overview of this e…
Distributed OptimizationMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+1OMAC: A Broad Optimization Framework for LLM-Based Multi-Agent Collaboration
Agents powered by advanced large language models (LLMs) have demonstrated impressive capabilities across diverse complex applications. Recently, Multi-Agent Systems (MAS), wherein multiple agents collaborate and communic…
Arithmetic ReasoningCode GenerationInsider Attacks in Multi-Agent LLM Consensus Systems
Large language models (LLMs) are increasingly deployed in multi-agent systems where agents communicate in natural language to solve tasks jointly. A key capability in such systems is consensus formation, where agents ite…
Reinforcement LearningDistributed Differentially Private Control Synthesis for Multi-Agent Systems with Metric Temporal Logic Specifications
In this paper, we propose a distributed differentially private receding horizon control (RHC) approach for multi-agent systems (MAS) with metric temporal logic (MTL) specifications. In the MAS considered in this paper, e…