arXiv Computation and Language

DTOC: Dynamic Tool Output Compression for Adaptive Context Management in AI Agents

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.

arXiv AI
Oct 27

CTXAgent - Self-Controlled Context Management of LLM Agents

The paper introduces CTXAgent, a self‑controlled context management system for large language model agents that compacts conversation history when a token threshold is reached. It evaluates seven frontier models, comparing their ability to manage context with and without dedicated tools, and benchmarks performance across coding, scientific, and software engineering tasks. Results show that well‑managed models keep live context below 100k tokens, maintain high benchmark scores, and achieve significant cost reductions, with Claude Opus 5.5 outperforming its explicit configuration by 34% lower cost.

By Matthias Busch, Marius Tacke, Roland C. Aydin, Christian Feiler, Christian J. Cyron
arXiv AI
Sep 28

Compress What You See, Not What You Say: Anchored Context Distillation for Latent-Observation Software Engineering Agents

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 Machine Learning
Nov 2

In-Model Context Compression with Agentic Soft Tokens for Long-Horizon LLM Agents

The paper introduces Agentic Soft-Token Compression (ASTC), a training‑free method that uses soft tokens within an LLM agent to compress long‑horizon context. ASTC leverages the model’s recurrent dynamics and Gated Delta Network attention to identify absorbed information, forwarding it as soft tokens while keeping hard‑token values intact. Experiments show ASTC matches or surpasses uncompressed agents, reducing attention pairs by up to 50.68% and outperforming trained compressors by 15.4 to 103.7 times in attention usage.

By Xuning He, Kai Fan, Runyu Zhang, Binghuan Wang, Yuxiang Zhang, Xue Jiang, Yihong Dong
arXiv Computation and Language
Aug 31

ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL

ContextPilot is a proactive context‑management framework designed to improve long‑horizon agentic reasoning with large language models. It expands the toolset to include planning, long‑term memory, and soft context offloading, and introduces a reinforcement‑learning strategy that focuses on critical editing decisions and assigns action‑level advantages. Experiments on long‑context QA and deep search tasks demonstrate that ContextPilot achieves stronger performance with a more compact working context, outperforming existing baselines across various base models and benchmarks.

By Zhuoshi Pan, Qizhi Pei, Junru Lu, Honglin Lin, H. Vicky Zhao, Di Yin, Xing Sun
arXiv AI
Sep 18

An Empirical Study of Harness Design for Coding Agents

The study investigates how individual components of a coding harness—planning, action space, and context management—affect autonomous coding agents’ performance. By fixing the execution loop and varying these components across 176 settings on SWE‑Bench Verified and Terminal‑Bench 2.1, the authors find that context management is most valuable when context windows are tight, staging rule‑based elision before LLM summarization yields the best efficiency, planning serves as an accuracy scaffold for weaker models and a cost saver for stronger ones, and predefined tools help models with limited bash skills while bash‑capable models benefit from a bash‑only interface. Trajectory‑level analysis shows that context management lengthens execution paths, planning alters where trajectories terminate, and the action space determines code granularity, offering a modular framework for future harness design.

By Run-Ze Fan, Zihao Zhang, Simin Ma, Yebowen Hu, Shouju Wang, Kaiqiang Song, Fei Liu, Hamed Zamani, Xiaoyang Wang
arXiv Machine Learning
Aug 27

Beyond Scaling: Self-Evolving LLM Agents for Hardware Kernel Optimization via an Experience-Driven Workflow and Experience Graph Memory

The paper introduces KOPE, an experience‑driven framework that records hardware kernel optimization trajectories in an Experience Graph Memory and uses Active Context Management and Injection to retrieve relevant past decisions under a fixed token budget. KOPE preserves decision order, outcomes, and alternative branches, enabling evidence from completed runs to inform future optimization steps. In experiments, KOPE achieves a 1.54× speedup over the strongest baseline, raises pass rates from 60.0% to 84.6%, and reduces token consumption dramatically, demonstrating the benefits of continual learning from external experience while keeping the foundation model unchanged.

By Siyuan Chen, Runlin Hou, Shenxiu Wu, Yansong Sun, Junming Cao, Yiyu Zhang, Shudi Shao, Junhao Qiu, Zhichao Lu, Qingfu Zhang