让大模型协作像团队一样实时调整沟通策略，提升整体表现
OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration
- 用动态认知感知模型让每个智能体了解其他人的思考状态
- 实测在复杂任务中显著提升完成率与沟通效率
- 适合研究多智能体协同和大模型交互的学者参考
本文提出 OSC（Orchestrating Cognitive Synergy），一种面向多智能体大语言模型协作的认知协同增强框架。尽管已有研究在智能体选择与结果聚合方面取得进展，但专家智能体间深度协作所需的高效语言交互仍是关键瓶颈。OSC作为介于选择与聚合之间的中间层，引入协作认知模型（CKM），使各智能体能够动态感知协作方的认知状态。通过实时认知差距分析，智能体可自适应调整沟通行为，包括内容焦点、细节层次与表达风格，采用学习到的策略。在复杂推理与问题解决基准测试中，实验表明 OSC 显著提升了任务性能与沟通效率，将原本‘并行工作的个体’转化为‘深度协作的认知团队’。该框架不仅优化了多智能体协作，也为大语言模型智能体交互行为提供了新视角。
原文摘要 · Abstract (English)
This paper introduces OSC (Orchestrating Cognitive Synergy), a knowledge-aware adaptive collaboration framework designed to enhance cognitive synergy in multi-agent systems with large language models. While prior work has advanced agent selection and result aggregation, efficient linguistic interactions for deep collaboration among expert agents remain a critical bottleneck. OSC addresses this gap as a pivotal intermediate layer between selection and aggregation, introducing Collaborator Knowledge Models (CKM) to enable each agent to dynamically perceive its collaborators' cognitive states. Through real-time cognitive gap analysis, agents adaptively adjust communication behaviors, including content focus, detail level, and expression style, using learned strategies. Experiments on complex reasoning and problem-solving benchmarks demonstrate that OSC significantly improves task performance and communication efficiency, transforming "parallel-working individuals'' into a "deeply collaborative cognitive team.'' This framework not only optimizes multi-agent collaboration but also offers new insights into LLM agent interaction behaviors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。