paper-with-me

Papers

Improving Multi-Agent Debate with Sparse Communication Topology

2024-06-17 · Yunxuan Li, Yibing Du, Jiageng Zhang, Le Hou, Peter Grabowski, Yeqing Li, Eugene Ie

Multi-agent debate has proven effective in improving large language models quality for reasoning and factuality tasks. While various role-playing strategies in multi-agent debates have been explored, in terms of the communication among agents, existing approaches adopt a brute force algorithm -- each agent can communicate with all other agents. In this paper, we systematically investigate the effect of communication connectivity in multi-agent systems. Our experiments on GPT and Mistral models reveal that multi-agent debates leveraging sparse communication topology can achieve comparable or superior performance while significantly reducing computational costs. Furthermore, we extend the multi-agent debate framework to multimodal reasoning and alignment labeling tasks, showcasing its broad applicability and effectiveness. Our findings underscore the importance of communication connectivity on enhancing the efficiency and effectiveness of the "society of minds" approach.

📄 PDF Abstract BibTeX arXiv:2406.11776

Code (0)

등록된 구현이 없습니다.

Tasks

Multimodal Reasoning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Weight Decay 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

Similar Papers 제목 키워드 기반

RUMAD: Reinforcement-Unifying Multi-Agent Debate

2026-02-27 · Chao Wang, Han Lin, Huaze Tang, Huijing Lin 외 arxiv

Multi-agent debate (MAD) systems leverage collective intelligence to enhance reasoning capabilities, yet existing approaches struggle to simultaneously optimize accuracy, consensus formation, and computational efficiency…

Zero-shot GeneralizationComputational EfficiencyReinforcement Learning

Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus

2026-06-01 · Wanshuang Gou, Zihan Liu arxiv

Large language model-driven multi-agent systems enhance the reliability of complex reasoning tasks through multi-round deliberation, role specialization, and cross-validation. However, existing multi-agent debate and col…

Mathematical ReasoningLogical Reasoning

PEAR: Permutation-Equivariant Adaptive Routing Multi-Agent Debate

2026-05-26 · Yang Feng, Ziwei Xu, Xia Hu, Fengxiang He arxiv

Multi-agent debate improves the reliability of large language models (LLMs) through iterative peer critiques. However, fixed topologies often introduce persistent positional biases, amplify unreliable agents, and cause h…

TopoDIM: One-shot Topology Generation of Diverse Interaction Modes for Multi-Agent Systems

2026-01-15 · Rui Sun, Jie Ding, Chenghua Gong, Tianjun Gu 외 arxiv

Optimizing communication topology in LLM-based multi-agent system is critical for enabling collective intelligence. Existing methods mainly rely on spatio-temporal interaction paradigms, where the sequential execution of…

Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems

2025-05-29 · Xu Shen, Yixin Liu, YiWei Dai, Yili Wang 외

The communication topology in large language model-based multi-agent systems fundamentally governs inter-agent collaboration patterns, critically shaping both the efficiency and effectiveness of collective decision-makin…

Decision MakingLanguage ModelingLanguage ModellingLarge Language Model