The paper introduces LOHA, a context layout that compresses older tool observations into soft tokens while keeping the agent’s own turns and the last K observations in plain text, and ACD, a training method that distills full‑text predictions into this latent representation while anchoring behavior on plain text. This approach reduces context per call by up to 57% without significant loss in resolve rates, and improves instance throughput in single‑GPU serving. Experiments on SWE‑bench Verified show that K=3 yields a 43–57% compression with only modest performance impact, while larger windows favor task performance over compression.
By Zhensheng Zou (Peking University), Guoqing Wang (Peking University), Dan Hao (Peking University)
arXiv:2608. 12847v1 Announce Type: new Abstract: Retrieval can identify a past trajectory that may matter, yet it does not specify how an acting agent should use that trajectory after users, entities, constraints, or environment state have changed.
By Yifei Li, Heng Wang, Lingling Zhang, Muye Huang, Xinyu Zhang, Jiashuai Liu, Hang Yan, Rongman Xu
arXiv:2606. 00408v1 Announce Type: cross Abstract: Long-horizon search agents accumulate large amounts of retrieved content across many tool calls, making context-budget efficiency increasingly important.
By Haoxiang Zhang, Qixin Xu, Zhuofeng Li, Lei Zhang, Pengcheng Jiang, Yu Zhang, Julian McAuley
arXiv:2609.22114v1 Announce Type: new
Abstract: Context compression is widely proposed as a way to cut the token bill of LLM coding agents, and public benchmarks report that aggressive compression pr...
By Luzhuo Chen, Jiayu Shi
The paper introduces Dynamic Tool Output Compression (DTOC), a framework that manages context in large‑language‑model agents by storing full tool outputs in external memory and inserting compact placeholders into the active context. DTOC treats context updates as explicit, reversible operations within the agent’s reasoning loop, allowing selective reconstruction of compressed outputs when needed. Experiments on the DeepSWE benchmark show that for responsive models such as Sonnet 4.6 and GPT‑5.4, DTOC reduces input tokens and agent steps while significantly improving solve rates and lowering cost per solved task, with ablation studies confirming the importance of reversibility for maintaining performance.
By Abhay Chaturvedi, Shreya Bhattacharya, Rashmika Gopalkrishnan, Peter van der Putten
arXiv:2609.36526v1 Announce Type: cross
Abstract: Long-horizon agents require context compression to manage growing interaction histories. Compression quality, however, is ultimately determined by do...
By Guanghui Min, Liang Wu, Mingjia Shi, Yinhan He, Mayank Darbari, Liangjie Hong, Chen 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
Paritok-4B is a 4‑billion‑parameter LoRA compressor designed for coding agents, which extracts and retains key spans of code rather than paraphrasing them. It is intent‑conditioned, selecting lines that are most relevant to the agent’s current task, and achieves high fidelity with 96% of identifiers, paths, and numbers preserved. Trained on 67,074 real OpenHands trajectories and fine‑tuned on Qwen3‑4B, it compresses agent context to about 25.7% of its original size while keeping 86.5% of the uncompressed solve quality across 300 SWE‑bench Lite instances.
By Jiayu Shi, Luzhuo Chen
arXiv:2606. 25449v1 Announce Type: cross Abstract: A language model's memory can be worse than having no memory at all.
By Alex Kwon
Tool-using language-model agents are governed not only by task prompts but also by persistent system-side instructions that specify tools, arguments, policies, execution protocols, and recovery. Compressing these agent control contexts (ACCs) can reduce input cost and context use, yet existing prompt-compression evaluations do not reveal whether the resulting control remains operationally reliable.
A language model's memory can be worse than having no memory at all. Give a model a memory that kept a wrong conclusion but dropped the work behind it, and it emits that stale value as a confident answer; give the same model an empty memory and it abstains.
Coding agents re-send large file reads and tool outputs to a frontier LLM every turn, and this context dominates their token bill. General-purpose prompt compressors are trained on prose and suit code...