Planning has been a cornerstone of artificial intelligence for solving complex problems, and recent progress in LLM-based multi-agent frameworks have begun to extend this capability. However, the role of human-like memory within these frameworks remains largely unexplored. Understanding how agents coordinate through memory is critical for natural language planning, where iterative reasoning, constraint tracking, and error correction drive the success. Inspired by working memory model in cognitive psychology, we present EvoMem, a multi-agent framework built on a dual-evolving memory mechanism. The framework consists of three agents (Constraint Extractor, Verifier, and Actor) and two memory modules: Constraint Memory (CMem), which evolves across queries by storing task-specific rules and constraints while remains fixed within a query, and Query-feedback Memory (QMem), which evolves within a query by accumulating feedback across iterations for solution refinement. Both memory modules are reset at the end of each query session. Evaluations on trip planning, meeting planning, and calendar scheduling show consistent performance improvements, highlighting the effectiveness of EvoMem. This success underscores the importance of memory in enhancing multi-agent planning.

翻译：规划一直是人工智能解决复杂问题的基石，近期基于大语言模型的多智能体框架已开始扩展这一能力。然而，类人记忆在这些框架中的作用在很大程度上仍未得到探索。理解智能体如何通过记忆进行协调对于自然语言规划至关重要，其中迭代推理、约束跟踪和错误纠正驱动着成功。受认知心理学中工作记忆模型的启发，我们提出了EvoMem，这是一个基于双演化记忆机制的多智能体框架。该框架包含三个智能体（约束提取器、验证器和执行器）以及两个记忆模块：约束记忆（CMem）在查询间演化，存储任务特定规则和约束，而在单个查询内保持固定；查询反馈记忆（QMem）在查询内演化，通过跨迭代累积反馈以优化解决方案。两个记忆模块在每次查询会话结束时重置。在旅行规划、会议规划和日历调度任务上的评估显示了一致的性能提升，凸显了EvoMem的有效性。这一成功强调了记忆在增强多智能体规划中的重要性。