paper-with-me

Papers

Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems

2026-04-23 · Ye Yu, Heming Liu, Haibo Jin, Xiaopeng Yuan, Peng Kuang, Haohan Wang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.21794

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical ReasoningCode Generation

Similar Papers 제목 키워드 기반

Large Language Model-Enabled Multi-Agent Manufacturing Systems

2024-06-04 · Jonghan Lim, Birgit Vogel-Heuser, Ilya Kovalenko

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+1

Optimization for Reinforcement Learning: From Single Agent to Cooperative Agents

2019-12-01 · Donghwan Lee, Niao He, Parameswaran Kamalaruban, Volkan Cevher

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+1

OMAC: A Broad Optimization Framework for LLM-Based Multi-Agent Collaboration

2025-05-17 · Shijun Li, Hilaf Hasson, Joydeep Ghosh

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 Generation

Insider Attacks in Multi-Agent LLM Consensus Systems

2026-05-08 · Xiaolin Sun, Zixuan Liu, Yibin Hu, Zizhan Zheng arxiv

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 Learning

Distributed Differentially Private Control Synthesis for Multi-Agent Systems with Metric Temporal Logic Specifications

2022-10-04 · Nasim Baharisangari, Zhe Xu

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…