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
arXiv:2608. 10676v1 Announce Type: new Abstract: Large language model (LLM)-based search agents answer questions through multi-step interactions with external environments.
By Aijun Yang, Qianxue Guo, Ziyi Huang, Yuxuan Chen, Shiyou Qian, Jian Cao
StateComp introduces a method for long‑horizon agents to decide when to compress historical interactions based on the current agent state, rather than relying on fixed windows or periodic schedules. The framework uses a two‑stage annotation process to create KEEP and READY labels, trains an imbalance‑aware router on frozen language model representations, and groups adjacent READY interactions into compact summaries. Experiments on WorkBuddyBench show that StateComp cuts agent and summarization tokens by 52.27% and speeds up representation extraction 12.67‑fold while preserving task performance.
By Mingxuan Wang, Hongyue Chen, Yinglong Guo, Fei Luo, Chao Ning, Bo Wang, Guorun Yao, Yanbiao Ma, Jungong Han
SUMONE is a lightweight summarizer designed to compress long interaction histories of language‑model agents. It is trained via masked reconstruction, where a frozen reconstructor predicts randomly masked parts of the original trajectory; reconstruction quality plus a length penalty yields a task‑agnostic reward for optimizing the summarizer with GRPO. At inference, only the summarizer remains, enabling plug‑and‑play context compression that reduces inference cost by roughly 78 % on DeepSearchQA and 75 % on SWE‑bench without affecting the underlying agent.
By Jizhe Zhang, Ang Li, Chenheng Zhang, Yisen Wang
Large language model (LLM)-based search agents answer questions through multi-step interactions with external environments. However, providing complete execution trajectories to the LLM causes unbounded context growth and introduces noise.
arXiv:2607. 25066v1 Announce Type: new Abstract: Long-horizon LLM agents accumulate reasoning traces, actions, and tool observations that can eventually exceed a model's fixed context window.
By Thang Dang, Yuma Ichikawa, Sakina Fatima, Koichi Shirahata
arXiv:2606. 31650v1 Announce Type: cross Abstract: Long-horizon language agents must repeatedly interact with tools, accumulate evidence, and make decisions under bounded context windows.
By Zijun Xie, Binbin Zheng, Enlei Gong, Jihua Liu, Yuyang You, Lingfeng Liu, Jiayao Tang, Guanqun Zhao, Aoqi Hu, Zeyu Chen
arXiv:2608.29363v1 Announce Type: new
Abstract: Enterprise data agents answer business queries by chaining many tool calls over multiple reasoning steps, routinely accumulating hundreds of thousands...
By Ziqi Lin, Ye Wu, Mengying Yang, Xu Liu, Yizhou Liu, Qiang Ke, Qin Guo
CoEM introduces a Commit-on-Evidence Memory system that learns when to compress source evidence into compact memory facts while preserving potentially useful excerpts verbatim in a pending set. The system uses a learned policy to decide whether to promote, retain, or discard each pending excerpt as new context arrives, and a frozen verifier ensures only supported facts are committed. Reinforcement learning trains this policy with step-level evidence rewards and final answer rewards, leading to consistent improvements in long-context reasoning, achieving 10.4–11.4 F1 points over the strongest baseline on 6,400-document inputs.
By Jingguang Li, Yebo Wu, Zuyi Guo, Kailang Ma, Xianjie Dai, Han Zheng, Benwang Chen, Li Li, Can Rong, Heye Huang
The paper introduces MERIT, a benchmark that evaluates the marginal benefit of long‑term memory for tool‑using large language model agents while explicitly accounting for cost. MERIT provides episodic tool‑use tasks across three domains, verifies dependence on earlier‑episode facts, and measures memory operations in tokens and dollars. Experiments on GPT‑4.1‑mini, Claude Haiku 4.5, and Claude Sonnet 5 show that memory can significantly improve task success, but its utility varies widely across models and memory implementations, and full replay is rarely cost‑effective.
By Shweta Mishra, Shashank Mishra
arXiv:2606. 22737v2 Announce Type: replace Abstract: Before letting an agent operate over real context, can you prove it used the right evidence?
By Jeffrey Flynt
arXiv:2607. 20064v1 Announce Type: new Abstract: Long-horizon tasks require sustained perception, reasoning, and exploration, and are a persistent challenge for large language model (LLM) agents.
By Alexis Fox, Junlin Wang, Paul Rosu, Bhuwan Dhingra