arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.34836cs.AIcs.MA
收藏

集体涌现对齐:测量与放大多智能体大语言模型中交互诱导的推理对齐

Collective Emergent Alignment: Measuring and Amplifying Interaction-Induced Reasoning Alignment in Multi-Agent LLMs

University of Liverpool(利物浦大学);University of Southampton(南安普顿大学)

Boxuan Wang, Zhuoyun Li, Sarvapali D. Ramchurn, Xiaowei Huang, Yi Dong

AI总结:

本研究提出REMAP框架量化多智能体LLM的交互诱导推理对齐,发现交互可提升推理对齐,进而引入事实级多智能体通信框架,实现性能提升与通信开销降低。

摘要:

多智能体大语言模型(LLM)系统可通过交互展现涌现行为,但推理对齐是否存在类似现象仍未被充分探索。本研究探究智能体交互是否会产生超出个体自我优化匹配的、基于参考的额外推理对齐,并引入REMAP(智能体过程的参考蕴含矩阵,Reference-Entailment-Matrix for Agentic Process)这一框架,通过语义覆盖率和交互特定对齐增益来量化该效应。在不同模型家族及两个多跳推理基准上,我们观察到普遍为正的交互增益,尤其在依赖整合跨智能体分布证据的推理内容上表现显著。这些增益与独立测量的同伴信息恢复能力一致,进一步分析揭示了依赖组合的异质性效应及跨智能体能力水平的非对称信息传递。基于这些发现,我们进一步引入事实级多智能体通信框架,该框架用紧凑、感知差距且选择性路由的信息替代完整推理轨迹交换。实验表明,紧凑事实交换可提升推理对齐与任务性能,同时降低通信开销,而更具选择性的通信则暴露出在获取分布式信息、保留本地内容与通信效率间的权衡。总体而言,我们的结果表明集体涌现对齐可被量化、与信息传递模式关联,并可用于指导更有效的多智能体通信。

英文摘要:

Multi-agent large language model (LLM) systems can exhibit emergent behaviors through interaction, yet whether a similar phenomenon exists for reasoning alignment remains largely unexplored. We study whether agent interaction produces additional reference-grounded reasoning alignment beyond matched individual self-refinement, and introduce REMAP (Reference-Entailment-Matrix for Agentic Process), a framework that quantifies this effect through Semantic Coverage and interaction-specific alignment gains. Across diverse model families and two multi-hop reasoning benchmarks, we observe broadly positive interaction gains, particularly on reasoning content that depends on integrating evidence distributed across agents. These gains are consistently associated with independently measured peer-information recovery, while further analysis reveals composition-dependent heterogeneity effects and asymmetric information transfer across agent capability levels. Motivated by these findings, we further introduce a fact-level multi-agent communication framework that replaces full reasoning-trace exchange with compact, gap-aware, and selectively routed information. Our experiments show that compact fact exchange improves reasoning alignment and task performance while reducing communication overhead, whereas more selective communication exposes a trade-off between acquiring distributed information, retaining local content, and communication efficiency. Overall, our results show that collective emergent alignment can be quantified, linked to information-transfer patterns, and used to guide more effective multi-agent communication.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑