Git Context Controller: Manage the Context of LLM-based Agents like Git

TL;DR

The paper introduces Git-Context-Controller, a structured framework for managing long-term context in LLM agents, enabling better memory, reuse, and multi-trajectory reasoning, leading to state-of-the-art performance.

Contribution

It proposes a versioned, file system-inspired context management system for LLM agents, improving long-term memory and multi-path exploration capabilities.

Findings

Achieves over 13% improvement on SWE-Bench

Outperforms 26 existing systems in success rate

Enables hierarchical and milestone-based context management

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