paper-with-me

홈 › Papers

Communication Learning in Multi-Agent Systems from Graph Modeling Perspective

2024-11-01 · Shengchao Hu, Li Shen, Ya zhang, DaCheng Tao

In numerous artificial intelligence applications, the collaborative efforts of multiple intelligent agents are imperative for the successful attainment of target objectives. To enhance coordination among these agents, a distributed communication framework is often employed. However, indiscriminate information sharing among all agents can be resource-intensive, and the adoption of manually pre-defined communication architectures imposes constraints on inter-agent communication, thus limiting the potential for effective collaboration. Moreover, the communication framework often remains static during inference, which may result in sustained high resource consumption, as in most cases, only key decisions necessitate information sharing among agents. In this study, we introduce a novel approach wherein we conceptualize the communication architecture among agents as a learnable graph. We formulate this problem as the task of determining the communication graph while enabling the architecture parameters to update normally, thus necessitating a bi-level optimization process. Utilizing continuous relaxation of the graph representation and incorporating attention units, our proposed approach, CommFormer, efficiently optimizes the communication graph and concurrently refines architectural parameters through gradient descent in an end-to-end manner. Additionally, we introduce a temporal gating mechanism for each agent, enabling dynamic decisions on whether to receive shared information at a given time, based on current observations, thus improving decision-making efficiency. Extensive experiments on a variety of cooperative tasks substantiate the robustness of our model across diverse cooperative scenarios, where agents are able to develop more coordinated and sophisticated strategies regardless of changes in the number of agents.

📄 PDF Abstract BibTeX arXiv:2411.00382

Code (1)

charleshsc/CommFormer 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems

2026-03-20 · Hongjiang Chen, Xin Zheng, Yixin Liu, Pengfei Jiao 외 arxiv

Large language model (LLM)-based multi-agent systems (MAS) have demonstrated exceptional capabilities in solving complex tasks, yet their effectiveness depends heavily on the underlying communication topology that coordi…

GAMMS: Graph based Adversarial Multiagent Modeling Simulator

2026-02-04 · Rohan Patil, Jai Malegaonkar, Xiao Jiang, Andre Dion 외 arxiv

As intelligent systems and multi-agent coordination become increasingly central to real-world applications, there is a growing need for simulation tools that are both scalable and accessible. Existing high-fidelity simul…

Counterfactual Multi-Agent Reinforcement Learning with Graph Convolution Communication

2020-04-01 · Jianyu Su, Stephen Adams, Peter A. Beling

We consider a fully cooperative multi-agent system where agents cooperate to maximize a system's utility in a partial-observable environment. We propose that multi-agent systems must have the ability to (1) communicate a…

counterfactualMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+1

Active Learning for Communication Structure Optimization in LLM-Based Multi-Agent Systems

2026-05-07 · Huchen Yang, Xinghao Dong, Dan Negrut, Jin-Long Wu arxiv

Optimizing the communication structure of large language model based multi-agent systems (LLM-MAS) has been shown to improve downstream performance and reduce token usage. Existing methods typically rely on randomly samp…

Active Learning

G2CP: A Graph-Grounded Communication Protocol for Verifiable and Efficient Multi-Agent Reasoning

2026-02-13 · Karim Ben Khaled, Davy Monticolo arxiv

Multi-agent systems powered by Large Language Models face a critical challenge: agents communicate through natural language, leading to semantic drift, hallucination propagation, and inefficient token consumption. We pro…