无需训练，用结构化记忆图实现多智能体高效自适应。
ConMem: Structured Memory-Guided Adaptation in Training-Free Multi-Agent Systems
- 将历史交互转化为有关系的结构化记忆卡
- 运行时通过记忆图修剪超50%候选，降低80%规划开销
- 适合追求轻量级、无训练的多智能体系统研究者
近期基于大模型的多智能体系统（MAS）通过记忆、技能和学习方法提升了自适应能力，但仍面临轨迹噪声、记忆与技能关系建模不足以及依赖额外训练或高质量监督的问题。为此，我们提出ConMem——一种关系感知且无需训练的框架，通过跨经验协调实现多智能体高效自适应。ConMem将历史交互轨迹提炼为结构化记忆卡，捕捉可复用策略与提示，并组织成关系感知的记忆图。运行时，ConMem根据任务需求检索记忆卡，并通过记忆图协调策略冲突、恢复依赖关系。该机制提供结构化且关系感知的引导，实现无需额外训练的鲁棒轻量级自适应。在多个基准和主流MAS架构上的实验表明，其性能持续优于现有记忆架构，推理时通过剪枝超过50%的扩展候选，计划开销降低超过80%。代码已公开于https://anonymous.4open.science/r/ConMemCode。
原文摘要 · Abstract (English)
Recent advances have improved the adaptive capabilities of LLM-based multi-agent systems (MAS) through memory-, skill-, and learning-based approaches, yet these approaches remain challenged by noisy trajectories, insufficient modeling of memory-skill relations, and reliance on additional training or high-quality supervision. To address these limitations, we propose ConMem, a relation-aware and training-free framework that enables efficient multi-agent adaptation through cross-experience coordination. Specifically, ConMem distills historical interaction trajectories into structured memory cards to capture reusable strategies and cues, organizing them into a relation-aware memory graph. At runtime, ConMem retrieves cards according to task needs and coordinates them through the card graph to resolve strategy conflicts and recover their dependencies. Combined, these modules yield structured and relation-aware guidance, enabling robust, lightweight adaptation in multi-agent systems without additional training. Extensive experiments across multiple benchmarks and mainstream MAS architectures show consistent gains over existing memory architectures, with improved inference-time efficiency through pruning more than 50% of expanded candidates and reducing planning overhead by over 80%. Our codes are available at https://anonymous.4open.science/r/ConMemCode
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。