arXiv Computation and Language October 21, 2026 By Jingwei Sun, Jianing Zhu, Jiangchao Yao, Tongliang Liu, Bo Han

Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory

Read the original on arXiv Computation and Language →

The paper introduces TriMem, a memory system for lifelong LLM agents that stores raw dialogue segments, extracted atomic facts, and synthesized profiles to preserve detail, enable efficient retrieval, and support deep reasoning. It uses TextGrad-based prompt optimization to iteratively refine extraction and profiling prompts without updating model parameters. Experiments on LoCoMo and PerLTQA show TriMem outperforms strong memory baselines across multiple LLM backbones.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Jun 9

Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systems

arXiv:2605. 12213v2 Announce Type: replace Abstract: LLM-based conversational AI agents struggle to maintain coherent behavior over long horizons due to limited context.

By Jiazhou Liang, Armin Toroghi, Yifan Simon Liu, Faeze Moradi Kalarde, Liam Gallagher, Scott Sanner

llms rag agents

arXiv Computation and Language

Sep 1

Learning to Reason and Use Tools through Unsupervised Fine-Tuning in Task-Oriented Dialog Systems

arXiv:2608.30426v1 Announce Type: new Abstract: Current dialogue systems struggle with dynamic information retrieval, often leading to hallucinations and lower response accuracy. We address this by a...

By Markel Ferro, Oier Lopez de Lacalle

llms agents fine-tuning safety

Hugging Face Trending Papers

Aug 2

TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents

Large language model agents have shown strong capabilities in generating coherent and contextually appropriate responses, yet robust long-horizon dialogue remains limited by the lack of external memory that is traceable, updatable, and diagnostically transparent. Existing memory-augmented agents often store memories as isolated records or overwritable states, making it difficult to preserve how information originates, evolves, conflicts, or becomes obsolete over time.

llms agents safety

arXiv AI

Aug 25

HERO: Human-profile Enhanced Retrieval Optimization Framework for Long-term Agent Memory

arXiv:2608.22310v1 Announce Type: new Abstract: Long-term memory is crucial for personalized responses and long-horizon agent interactions. Existing methods often rely on LLMs to compress or rewrite...

By Yuanhua Lin, Yile Li, Zhiyuan Zhao, Jing Shang, Jian Sun

llms agents benchmarks

arXiv Computation and Language

3d ago

DiaLong: Benchmarking Reminiscence in Long-Context Dialogues

arXiv:2610.25463v2 Announce Type: replace Abstract: How well can transformer-based Large Language Models (LLMs) retain and recall memories in long contexts of dialogue? LLMs are known to forget long-...

By Owen Bianchi, Samer Aslan, Ryunosuke Saito

llms benchmarks

arXiv AI

Oct 1

StateTree: Enhancing Long-Term Dialogue Reasoning via Reinforcement Learning

StateTree is a reinforcement learning approach that improves long‑term dialogue reasoning by building a tree‑structured auxiliary task from limited dialogue data. The method embeds key‑value records across multiple sessions into a binary tree, requiring the model to traverse from root to leaf, retrieve records, compare timestamps, and identify a target question among distractors. Curriculum RL training increases tree depth, and a compositional variant trains the model to combine partial reasoning fragments, enabling cross‑session retrieval, temporal reasoning, knowledge updates, and multi‑hop reasoning while generalizing from 10K‑token to 128K‑token contexts.

By Naen Xu, Wanqing Cui, Yibo Hu, Shixin Hong, Hengyu An, Meiguang Jin, Junfeng Ma, Tianyu Du

llms reinforcement-learning fine-tuning

One email a morning, machine-written

Related stories

Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systems

Learning to Reason and Use Tools through Unsupervised Fine-Tuning in Task-Oriented Dialog Systems

TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents

HERO: Human-profile Enhanced Retrieval Optimization Framework for Long-term Agent Memory

DiaLong: Benchmarking Reminiscence in Long-Context Dialogues

StateTree: Enhancing Long-Term Dialogue Reasoning via Reinforcement Learning