SEPM:基于任务图的自演进过程记忆,用于多智能体协作
SEPM: Self-Evolving Procedural Memory Grounded in Task Graphs for Multi-Agent Collaboration
AI总结:
本研究针对多智能体协作的记忆缺陷,提出SEPM框架,以任务依赖图为通用表示实现过程记忆自演进,在三个基准场景下较基线显著提升任务得分。
摘要:
长程多智能体协作需要既能保留成功行动又能保留其底层协调结构的记忆系统。现有记忆系统支持信息共享或过程复用,但常使共享过程的演进与协作智能体的任务依赖关系及执行状态脱节,这种耦合也限制了为单个智能体设计的过程记忆向团队场景的直接迁移。我们提出自演进过程记忆(Self-Evolving Procedural Memory,SEPM),该框架以任务依赖图作为在线协调和过程记忆演进的通用表示。执行期间,轻量共享黑板记录结构化证据及任务依赖关系,支持目标、计划和世界状态分歧的检测及基于证据的实时调整。执行完成后,已验证的行动和依赖关系被提炼为可复用过程,反复出现的失败则生成警告和约束。共享过程池在成功与成本效用的引导下,依据证据和安全约束通过创建、优化、特化和退役实现演进。这些机制共同保留了跨任务复用经验所需的协作结构和适用条件。在AutoGen和DyLAN下对ALFWorld、WebArena和OfficeBench的评估显示,SEPM在所有6个基准场景中均达到对比方法中最高的任务得分;在AutoGen下,其任务得分较无额外记忆基线分别提升29.85、25.86和13.00个百分点。代码库可在该https URL获取。
英文摘要:
Long-horizon multi-agent collaboration requires memory that preserves both successful actions and the coordination structure underlying them. Existing memory systems support information sharing or procedural reuse, but often leave the evolution of shared procedures disconnected from the task dependencies and execution states of collaborating agents. This coupling also limits the direct transfer of procedural memory designed for individual agents to team settings. We propose Self-Evolving Procedural Memory (SEPM), a framework that uses task dependency graphs as a common representation for online coordination and procedural memory evolution. During execution, a lightweight shared blackboard records structured evidence alongside task dependencies, supporting the detection of goal, plan, and world-state divergence and evidence-based realignment. After execution, verified actions and dependencies are distilled into reusable procedures, while recurring failures inform warnings and constraints. The shared procedure pool evolves through creation, refinement, specialization, and retirement, guided by success and cost utility and constrained by evidence and safety requirements. Together, these mechanisms preserve the collaborative structure and applicability conditions needed to reuse experience across tasks. Evaluations on ALFWorld, WebArena, and OfficeBench under AutoGen and DyLAN show that SEPM achieves the highest task scores among the compared methods in all six benchmark settings. Under AutoGen, it improves task scores over the no-added-memory baseline by 29.85, 25.86, and 13.00 percentage points, respectively. The codebase is available at https://github.com/cookieApril/SEPM.
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。