Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
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 .
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Learning what to remember
We consider a lifelong learning scenario in which a learner faces a neverending and arbitrary stream of facts and has to decide which ones to retain in its limited memory. We introduce a mathematical model based on the o…
Lifelong learningRethinking Rehearsal in Lifelong Learning: Does An Example Contribute the Plasticity or Stability?
Lifelong Learning (LL) is the sequential transformation of Multi-Task Learning, which learns new tasks in order like human-beings. Traditionally, the primary goal of LL is to achieve the trade-off between the Stability (…
Lifelong learningMulti-Task LearningGAN Memory with No Forgetting
As a fundamental issue in lifelong learning, catastrophic forgetting is directly caused by inaccessible historical data; accordingly, if the data (information) were memorized perfectly, no forgetting should be expected. …
FormLifelong learningAdaMem: Learning What to Remember for Personalized Long-Horizon LLM Agents
Long-term memory systems for Large Language Model (LLM) agents typically try to \emph{remember everything}, extracting memories uniformly to retain as many facts as possible. In production, however, inference cost and fi…
WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
Large language models (LLMs) need knowledge updates to meet the ever-growing world facts and correct the hallucinated responses, facilitating the methods of lifelong model editing. Where the updated knowledge resides in …
HallucinationModel EditingQuestion AnsweringRetrieval