{"ID":2888691,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.00031","arxiv_id":"2508.00031","title":"Git Context Controller: Manage the Context of LLM-based Agents like Git","abstract":"Large language model (LLM) agents have demonstrated strong capabilities in long-horizon tasks by interleaving reasoning with tool use. However, as these agents scale to complex workflows such as software engineering and open-ended research, context management becomes a fundamental bottleneck: interaction histories grow unbounded, become costly to maintain, and are difficult to reuse across sessions and agents. We introduce \\textbf{Git-Context-Controller (GCC)}, a structured context management framework inspired by software version control systems. GCC elevates agent context from a transient token stream to a persistent, navigable memory workspace with explicit operations -- \\texttt{COMMIT}, \\texttt{BRANCH}, \\texttt{MERGE}, and \\texttt{CONTEXT}, that enable milestone-based checkpointing, isolated exploration of alternative reasoning paths, and hierarchical retrieval of historical context. By organizing agent memory as a versioned file system, GCC allows agents to manage long-term goals, recover and transfer reasoning across sessions, and coordinate multi-trajectory problem solving in a principled manner. Empirically, agents equipped with GCC achieve state-of-the-art performance on both SWE-Bench and BrowseComp benchmarks. On SWE-Bench Verified, GCC improves task resolution by over 13\\% relative to strong long-context baselines and outperforms 26 existing open and commercial systems, reaching over 80\\% success rate. The project will be open-sourced for the research community. The algorithm has been incorporated to the project: https://one-context.com","short_abstract":"Large language model (LLM) agents have demonstrated strong capabilities in long-horizon tasks by interleaving reasoning with tool use. However, as these agents scale to complex workflows such as software engineering and open-ended research, context management becomes a fundamental bottleneck: interaction histories grow...","url_abs":"https://arxiv.org/abs/2508.00031","url_pdf":"https://arxiv.org/pdf/2508.00031v2","authors":"[\"Junde Wu\",\"Minhao Hu\",\"Jiayuan Zhu\",\"Jiazhen Pan\",\"Yuyuan Liu\",\"Min Xu\",\"Yueming Jin\"]","published":"2025-07-30T08:01:45Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[\"Large Language Model\",\"Language Model\",\"LoRA\",\"Generative Adversarial Network\"]","project_urls":"[\"https://one-context.com\"]","has_code":false,"code_links":[{"ID":611566,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2888691,"paper_url":"https://arxiv.org/abs/2508.00031","paper_title":"Git Context Controller: Manage the Context of LLM-based Agents like Git","repo_url":"https://github.com/LastPieceAI/OneContext","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}