To enable reliable long-term interaction, LLM agents require a memory system that can faithfully store, efficiently retrieve, and deeply reason over accumulated dialogue history. Most existing methods adopt an extracted fact based paradigm: handcrafted static prompts compress raw dialogues into atomic facts, which are then stored, matched, and injected into downstream reasoning. Nevertheless, such fact-centric designs inevitably discard fine-grained details in original dialogues and fail to support deep reasoning over scattered isolated facts. Moreover, static prompts cannot maintain consistent extraction granularity across diverse dialogue styles. To address these limitations, we propose TriMem, which maintains three coexisting representation granularities, including raw dialogue segments anchored by source identifiers for storage fidelity, extracted atomic facts for efficient memory retrieval, synthesized profiles that aggregate dispersed facts into holistic semantic understanding for deep reasoning. We further adopt TextGrad-based prompt optimization, which iteratively refines extraction and profiling prompts via response quality feedback, achieving lifelong evolution without any parameter updating. Extensive experiments on LoCoMo and PerLTQA across multiple LLM backbones demonstrate that TriMem consistently outperforms strong memory baselines. The code is available at https://TMLR-TriMem.github.io .

翻译：为了实现可靠的长期交互，LLM智能体需要一个能够忠实存储、高效检索并深度推理累积对话历史的记忆系统。现有方法大多采用基于提取事实的范式：手工构建的静态提示将原始对话压缩为原子事实，再将其存储、匹配并注入下游推理中。然而，这种以事实为中心的设计不可避免地丢弃了原始对话中的细粒度细节，且无法支持对分散孤立事实的深度推理。此外，静态提示无法在不同对话风格中保持一致的信息提取粒度。为解决这些局限，我们提出TriMem，它维护了三种共存的表示粒度：基于源标识符锚定的原始对话片段以确保存储保真度；提取的原子事实用于高效记忆检索；综合配置文件将分散事实聚合为整体语义理解以支持深度推理。我们进一步采用基于TextGrad的提示优化方法，通过响应质量反馈迭代优化提取与配置文件生成提示，在不更新任何参数的情况下实现终身演化。在LoCoMo和PerLTQA上使用多种LLM骨干网络进行的广泛实验表明，TriMem始终优于强记忆基线模型。代码地址为https://TMLR-TriMem.github.io。