PlugMem: 一种通用插件记忆模块用于LLM代理
PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
AI总结:
PlugMem是一种通用记忆模块,通过知识中心的记忆图结构提升LLM代理在复杂任务中的记忆检索与推理能力。
摘要:
长期记忆对于在复杂环境中运行的大型语言模型(LLM)代理至关重要,但现有记忆设计要么是任务特定且不可转移的,要么是任务无关的,但效果较差,因为从原始记忆检索中导致任务相关性低和上下文爆炸。我们提出了PlugMem,一种任务无关的插件记忆模块,可以附加到任意LLM代理上,而无需任务特定的重新设计。受决策相关信息集中为抽象知识而非原始经验的事实启发,我们借鉴认知科学,将事件记忆结构化为紧凑、可扩展的知识中心记忆图,明确表示命题性和规范性知识。这种表示使能够高效检索记忆并进行任务相关知识的推理,而不是冗长的原始轨迹,并与其他基于图的方法如GraphRAG不同,将知识作为记忆访问和组织的单位,而不是实体或文本块。我们评估PlugMem在三个异构基准(长视界对话问答、多跳知识检索和网络代理任务)上不变的表现。结果表明,PlugMem在任务无关基线中表现一致,并超过任务特定的记忆设计,同时在统一的信息论分析下也实现了最高信息密度。代码和数据可在https://github.com/TIMAN-group/PlugMem上获得。
英文摘要:
Long-term memory is essential for large language model (LLM) agents operating in complex environments, yet existing memory designs are either task-specific and non-transferable, or task-agnostic but less effective due to low task-relevance and context explosion from raw memory retrieval. We propose PlugMem, a task-agnostic plugin memory module that can be attached to arbitrary LLM agents without task-specific redesign. Motivated by the fact that decision-relevant information is concentrated as abstract knowledge rather than raw experience, we draw on cognitive science to structure episodic memories into a compact, extensible knowledge-centric memory graph that explicitly represents propositional and prescriptive knowledge. This representation enables efficient memory retrieval and reasoning over task-relevant knowledge, rather than verbose raw trajectories, and departs from other graph-based methods like GraphRAG by treating knowledge as the unit of memory access and organization instead of entities or text chunks. We evaluate PlugMem unchanged across three heterogeneous benchmarks (long-horizon conversational question answering, multi-hop knowledge retrieval, and web agent tasks). The results show that PlugMem consistently outperforms task-agnostic baselines and exceeds task-specific memory designs, while also achieving the highest information density under a unified information-theoretic analysis. Code and data are available at https://github.com/TIMAN-group/PlugMem.
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。