为LLM代理构建一个简单却强大的长期对话记忆基线
A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents
AI总结：
本文提出基于事件的对话记忆方法，通过异构图结构实现高效检索，提升LLM代理的长期对话能力。
摘要：
基于LLM的对话代理仍然难以在多个会话中保持连贯且个性化的互动：固定上下文窗口限制了能保留在视图中的历史信息量，而大多数外部记忆方法在粗粒度检索大型块和细粒度但碎片化的对话视图之间进行权衡。受neo-Davidsonian事件语义的启发，我们提出了一种以事件为中心的替代方案，将对话历史表示为短而事件-like的命题，这些命题将参与者、时间线索和最小的局部上下文捆绑在一起，而不是作为独立的关系三元组或不透明的总结。与那些激进压缩或遗忘过去内容的工作不同，我们的设计旨在以非压缩的形式保留信息，并使其更易于访问，而不是更损失性。具体来说，我们指导LLM将每个会话分解为丰富化的基本话语单元（EDUs）-- 自包含的陈述，具有标准化的实体和来源轮次归因 -- 并将会话、EDUs及其论点组织成一个异构图，以支持关联回忆。在该表示之上，我们构建了两个简单的检索基变体，使用密集相似性搜索和LLM过滤，可选的图基传播步骤用于连接和聚合相关EDUs的证据。在LoCoMo和LongMemEval_S基准测试中，这些以事件为中心的记忆匹配或超越了强大的基线，同时在问答上下文中使用了远更短的上下文。我们的结果表明，结构简单、以事件级别记忆提供了长期对话代理的原理化和实用的基础。我们的代码和数据将在https://github.com/KevinSRR/EMem上发布。
英文摘要：
LLM-based conversational agents still struggle to maintain coherent, personalized interaction over many sessions: fixed context windows limit how much history can be kept in view, and most external memory approaches trade off between coarse retrieval over large chunks and fine-grained but fragmented views of the dialogue. Motivated by neo-Davidsonian event semantics, we propose an event-centric alternative that represents conversational history as short, event-like propositions which bundle together participants, temporal cues, and minimal local context, rather than as independent relation triples or opaque summaries. In contrast to work that aggressively compresses or forgets past content, our design aims to preserve information in a non-compressive form and make it more accessible, rather than more lossy. Concretely, we instruct an LLM to decompose each session into enriched elementary discourse units (EDUs) -- self-contained statements with normalized entities and source turn attributions -- and organize sessions, EDUs, and their arguments in a heterogeneous graph that supports associative recall. On top of this representation we build two simple retrieval-based variants that use dense similarity search and LLM filtering, with an optional graph-based propagation step to connect and aggregate evidence across related EDUs. Experiments on the LoCoMo and LongMemEval$_S$ benchmarks show that these event-centric memories match or surpass strong baselines, while operating with much shorter QA contexts. Our results suggest that structurally simple, event-level memory provides a principled and practical foundation for long-horizon conversational agents. Our code and data will be released at https://github.com/KevinSRR/EMem.
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。
