← Back to all news
arXiv Computation and Language By Jinkyeong Choi, Chaebin Jeong, Junsung Jeon, Donghyeon Park

KEEPER: Learning Control-Sufficient Textual Memory for Long-Horizon LLM Agents

Read the original on arXiv Computation and Language →

The paper introduces KEEPER, a framework for learning control‑sufficient textual memory in long‑horizon large language model agents. It examines four auxiliary objectives that balance information content and update sensitivity, finding that reward‑related prediction yields the best task performance before and after offline reinforcement learning. A claim‑level analysis shows that incorrect claims can persist in memory even when corrective observations are made, highlighting the need to assess error persistence and valid‑information retention alongside task outcomes.

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.

Related stories

arXiv AI
Oct 15

TextualRL: Textual Reinforcement Learning for Context Management

TextualRL is a gradient‑free reinforcement learning framework that updates the textual context guiding large language model agents without altering their parameters. It treats groups of rollouts from the same task as units of critique, contrasting successful and failed runs to generate context patches, and validates these patches using held‑out rewards. Experiments on six benchmarks show that TextualRL boosts test accuracy by 24.4 and 15.3 percentage points for GPT‑5.5 and Qwen3.8‑27B, respectively.

By Tianyu Huai, Jie Zhou, Bo Mao, Qin Chen, Liang He, Xipeng Qiu
llmsagentsreinforcement-learningbenchmarks
More like this →
Hugging Face Trending Papers
Oct 13

TextualRL: Textual Reinforcement Learning for Context Management

TextualRL is a gradient‑free reinforcement learning framework that updates the textual context guiding large language model agents without altering their parameters. It critiques groups of rollouts from the same task, contrasts successful and failed runs, and uses cross‑group evidence to propose and validate context edits. Across six benchmarks, TextualRL boosts test accuracy by 24.4 and 15.3 percentage points for GPT‑5.5 and Qwen3.8‑27B, respectively.

llmsagentsreinforcement-learningbenchmarks
More like this →
arXiv AI
Oct 7

AMBER: Training Long-Horizon Web Agents through Append-Only Memory

The paper introduces AMBER, an append‑only memory framework for language‑model agents that interact over long horizons. AMBER lets agents jointly learn to reason, act, and write free‑form memory, guaranteeing retention by construction and enabling end‑to‑end reinforcement learning without extensive curated data. Experiments on WebArena Lite show AMBER outperforms overwrite‑based memory by 4.09 percentage points in average success and improves task completion rates in repeated runs.

By Chinmay Savadikar, Zhaoyu Zhang, Mingyu Zhao, Shuang Xie, Han Li, Tianfu Wu, Lingyun Wang
agentsnlpreinforcement-learningfine-tuning
More like this →
arXiv Machine Learning
Jun 16

HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents

arXiv:2606. 16285v1 Announce Type: cross Abstract: Long-horizon agents rely on memory mechanisms to compress interaction history, but optimizing memory writing faces a distinct credit assignment challenge: a memory update may be rewarded or penalized due to downstream tool failures, noisy observations, or reasoning errors rather than its own contribution.

By Jiangze Yan, Yi Shen, Wenjing Zhang, Jieyun Huang, Zhaoxiang Liu, Ning Wang, Kai Wang, Shiguo Lian
agentsreinforcement-learning
More like this →