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

• URL: http://arxiv.org/abs/2508.00031v1
• Date: Wed, 30 Jul 2025 08:01:45 GMT
• Title: Git Context Controller: Manage the Context of LLM-based Agents like Git
• Abstract summary: Large language model (LLM) based agents have shown impressive capabilities by interleaving internal reasoning with external tool use.<n>We introduce Git-Context-Controller (GCC), a structured context management framework inspired by software version control systems.<n>In a self-replication case study, a GCC-augmented agent builds a new CLI agent from scratch, achieving 40.7 task resolution, compared to only 11.7 without GCC.
• Score: 6.521644491529639
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model (LLM) based agents have shown impressive capabilities by interleaving internal reasoning with external tool use. However, as these agents are deployed in long-horizon workflows, such as coding for a big, long-term project, context management becomes a critical bottleneck. We introduce Git-Context-Controller (GCC), a structured context management framework inspired by software version control systems. GCC elevates context as versioned memory hierarchy like Git. It structures agent memory as a persistent file system with explicit operations: COMMIT, BRANCH, MERGE, and CONTEXT, enabling milestone-based checkpointing, exploration of alternative plans, and structured reflection. Our approach empowers agents to manage long-term goals, isolate architectural experiments, and recover or hand off memory across sessions and agents. Empirically, agents equipped with GCC achieve state-of-the-art performance on the SWE-Bench-Lite benchmark, resolving 48.00 of software bugs, outperforming 26 competitive systems. In a self-replication case study, a GCC-augmented agent builds a new CLI agent from scratch, achieving 40.7 task resolution, compared to only 11.7 without GCC. The code is released at: https://github.com/theworldofagents/GCC

Related papers

• CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation [12.333481527668326]
  Natural language to repository generation (NL2Repo) requires a system to construct an entire software repository from a natural-language requirements document.<n>We propose CodeTeam, a framework that separates planning, decision making, and implementation into distinct, coordinated stages.<n>Results show that project-specific developer allocation and retrieval-augmented planning each contribute substantially to the SketchBLEU improvement.
  arXiv  Detail & Related papers  (2026-06-20T14:57:33Z)
• Multi-Agent Computer Use [72.79887808312706]
  We argue that we should move towards evaluating and building multi-agent computer use (MACU) systems.<n>We propose a general multi-agent setup in which a manager model decomposes computer use tasks as a directed acyclic graph (DAG)<n>At each iteration, the manager dispatches parallel CUA subagents to carry out nodes on the ready frontier of the DAG.
  arXiv  Detail & Related papers  (2026-06-01T01:29:36Z)
• SCDBench: A Benchmark for LLM-Based Smart Contract Decompilers [55.39407031861402]
  We introduce SCDBench, a dataset and benchmark methodology for smart contract decompilation.<n>The dataset contains 600 real-world Solidity contracts with paired bytecode inputs, ground-truth source code, and replayable semantic checkpoints.<n>We evaluate Claude Opus 4.7, GPT-5.3-Codex, and GLM-5 in a zero-shot decompilation setting, including GLM-5 variants with and without extended reasoning.
  arXiv  Detail & Related papers  (2026-05-27T20:08:47Z)
• GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0) [56.81743709880371]
  Long-horizon large language model (LLM) agents are fundamentally limited by context.<n>We argue that long-horizon performance is determined not by context length, but by how much decision-relevant information is maintained within a finite context budget.<n>We present GenericAgent (GA), a general-purpose, self-evolving LLM agent system built around a single principle: information density and context.
  arXiv  Detail & Related papers  (2026-04-18T17:59:15Z)
• AgentForge: Execution-Grounded Multi-Agent LLM Framework for Autonomous Software Engineering [3.2126925586839623]
  We introduce execution-grounded verification as a first-class principle.<n>We instantiate this principle in AGENTFORGE, a multi-agent framework.<n>AGENTFORGEtoken achieves 40.0% resolution on SWE-BENCH Lite.
  arXiv  Detail & Related papers  (2026-04-13T13:51:13Z)
• ReCUBE: Evaluating Repository-Level Context Utilization in Code Generation [7.907933839674293]
  Large Language Models (LLMs) have emerged as capable coding assistants that operate over larges through either agentic exploration or full-context generation.<n>We introduce ReCUBE, a benchmark in which LLMs reconstruct a masked file within a real-world repository, using all remaining source files, dependency specifications, and documentation as their only source of context.<n>We propose the Caller-Centric Exploration (CCE) toolkit, a set of dependency graph-based tools that can be integrated into agentic frameworks.
  arXiv  Detail & Related papers  (2026-03-26T08:04:15Z)
• GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization [50.009407518866965]
  Repository-level bug localization is a critical software engineering challenge.<n>GNNs offer a promising alternative due to their ability to model complex, repository-wide dependencies.<n>We introduce GREPO, the first GNN benchmark for repository-scale bug localization tasks.
  arXiv  Detail & Related papers  (2026-02-14T23:22:15Z)
• Learning to Share: Selective Memory for Efficient Parallel Agentic Systems [49.78267008828593]
  Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results.<n>Recent approaches deploy multiple agent teams running in parallel to explore diverse reasoning trajectories.<n>We propose Learning to Share (LTS), a learned shared-memory mechanism for parallel agentic frameworks.
  arXiv  Detail & Related papers  (2026-02-05T18:20:21Z)
• FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents [53.03492387564392]
  We introduce FS-Researcher, a file-system-based framework that scales deep research beyond the context window via a persistent workspace.<n>A Context Builder agent browses the internet, writes structured notes, and archives raw sources into a hierarchical knowledge base that can grow far beyond context length.<n>A Report Writer agent then composes the final report section by section, treating the knowledge base as the source of facts.
  arXiv  Detail & Related papers  (2026-02-02T03:00:19Z)
• ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development [72.4729759618632]
  We introduce ABC-Bench, a benchmark to evaluate agentic backend coding within a realistic, executable workflow.<n>We curated 224 practical tasks spanning 8 languages and 19 frameworks from open-source repositories.<n>Our evaluation reveals that even state-of-the-art models struggle to deliver reliable performance on these holistic tasks.
  arXiv  Detail & Related papers  (2026-01-16T08:23:52Z)
• Repository Intelligence Graph: Deterministic Architectural Map for LLM Code Assistants [0.0]
  Repository aware coding agents often struggle to recover build and test structure.<n>We introduce the Repository Intelligence Graph (RIG), a deterministic, evidence backed architectural map that represents buildable components, aggregators, runners, tests, external packages, and package managers.<n>We evaluate three commercial agents (Claude Code, Cursor, Codex) on eight repositories spanning low to high build complexity, including the real world MetaFFI project.
  arXiv  Detail & Related papers  (2026-01-15T06:42:45Z)
• InfiAgent: An Infinite-Horizon Framework for General-Purpose Autonomous Agents [36.740230738304525]
  InfiAgent keeps the agent's reasoning context strictly bounded regardless of task duration.<n>InfiAgent with a 20B open-source model is competitive with larger proprietary systems.
  arXiv  Detail & Related papers  (2026-01-06T17:35:57Z)
• SCOPE: Prompt Evolution for Enhancing Agent Effectiveness [53.75986399936395]
  Large Language Model (LLM) agents are increasingly deployed in environments that generate massive, dynamic contexts.<n>While agents have access to this context, their static prompts lack the mechanisms to manage it effectively.<n>We introduce textbfSCOPE (Self-evolving Context Optimization via Prompt Evolution)<n>We propose a Dual-Stream mechanism that balances tactical specificity (resolving immediate errors) with strategic generality (evolving long-term principles)
  arXiv  Detail & Related papers  (2025-12-17T12:25:05Z)
• AgentGit: A Version Control Framework for Reliable and Scalable LLM-Powered Multi-Agent Systems [7.408263799616532]
  We present AgentGit, a framework that brings Git-like rollback and branching to multi-agent systems (MAS)<n>We show that AgentGit significantly reduces redundant, runtime and token usage, and supports parallel exploration across multiple branches.<n>This work offers a practical path to more robust MAS design and enables error recovery, safe exploration, computation, and A/B testing in collaborative AI systems.
  arXiv  Detail & Related papers  (2025-11-01T17:11:31Z)
• DeepAgent: A General Reasoning Agent with Scalable Toolsets [111.6384541877723]
  DeepAgent is an end-to-end deep reasoning agent that performs autonomous thinking, tool discovery, and action execution.<n>To address the challenges of long-horizon interactions, we introduce an autonomous memory folding mechanism that compresses past interactions into structured episodic, working, and tool memories.<n>We develop an end-to-end reinforcement learning strategy, namely ToolPO, that leverages LLM-simulated APIs and applies tool-call advantage attribution to assign fine-grained credit to the tool invocation tokens.
  arXiv  Detail & Related papers  (2025-10-24T16:24:01Z)
• Improving Code Localization with Repository Memory [33.423769985220005]
  We introduce tools that allow the agent to retrieve from a non-parametric memory encompassing recent historical commits and linked issues.<n>We demonstrate that augmenting such a memory can significantly improve LocAgent, a state-of-the-art localization framework.
  arXiv  Detail & Related papers  (2025-10-01T15:10:15Z)
• Meta-RAG on Large Codebases Using Code Summarization [11.415083231118142]
  Large Language Model (LLM) systems have been at the forefront of applied Artificial Intelligence (AI) research in a multitude of domains.<n>We propose a multi-agent system to localize bugs in large pre-existings using information retrieval and LLMs.<n>Our system introduces a novel Retrieval Augmented Generation (RAG) approach, Meta-RAG, where we utilize summaries to condenses by an average of 79.8%, into a compact, structured, natural language representation.
  arXiv  Detail & Related papers  (2025-08-04T17:01:10Z)
• LLM-Driven Collaborative Model for Untangling Commits via Explicit and Implicit Dependency Reasoning [20.147009997147798]
  We propose ColaUntangle, a new collaborative consultation framework for commit untangling.<n>ColaUntangle integrates Large Language Model (LLM)-driven agents in a multi-agent architecture.<n>We construct multi-version Program Dependency Graphs (delta-PDG), enabling agents to reason over code relationships with both symbolic and semantic depth.
  arXiv  Detail & Related papers  (2025-07-22T09:42:13Z)
• SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving [90.32201622392137]
  We present SwingArena, a competitive evaluation framework for Large Language Models (LLMs)<n>Unlike traditional static benchmarks, SwingArena models the collaborative process of software by pairing LLMs as iterations, who generate patches, and reviewers, who create test cases and verify the patches through continuous integration (CI) pipelines.
  arXiv  Detail & Related papers  (2025-05-29T18:28:02Z)
• RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving [9.477917878478188]
  RepoMaster is an autonomous agent framework designed to explore and reuse GitHub repositories for solving complex tasks.<n>RepoMaster constructs function-call graphs, module-dependency graphs, and hierarchical code trees to identify essential components.<n>On our newly released GitTaskBench, RepoMaster lifts the task-pass rate from 24.1% to 62.9% while reducing token usage by 95%.
  arXiv  Detail & Related papers  (2025-05-27T08:35:05Z)
• LocAgent: Graph-Guided LLM Agents for Code Localization [25.395102705800916]
  LocAgent is a framework that addresses code localization through graph-based representation.<n>Our method with the fine-tuned Qwen-2.5-Coder-Instruct-32B model achieves comparable results to SOTA proprietary models at greatly reduced cost.
  arXiv  Detail & Related papers  (2025-03-12T05:55:01Z)
• CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models [106.11371409170818]
  Large language models (LLMs) can act as agents with capabilities to self-refine and improve generated code autonomously. We propose CodeTree, a framework for LLM agents to efficiently explore the search space in different stages of the code generation process. Specifically, we adopted a unified tree structure to explicitly explore different coding strategies, generate corresponding coding solutions, and subsequently refine the solutions.
  arXiv  Detail & Related papers  (2024-11-07T00:09:54Z)
• Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement [112.04307762405669]
  G"odel Agent is a self-evolving framework inspired by the G"odel machine.<n>G"odel Agent can achieve continuous self-improvement, surpassing manually crafted agents in performance, efficiency, and generalizability.
  arXiv  Detail & Related papers  (2024-10-06T10:49:40Z)
• MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation [60.04380907045708]
  Retrieval-Augmented Generation (RAG) is considered a promising strategy to address this problem.<n>We propose MemoRAG, a novel RAG framework empowered by global memory-augmented retrieval.<n>MemoRAG achieves superior performances across a variety of long-context evaluation tasks.
  arXiv  Detail & Related papers  (2024-09-09T13:20:31Z)
• Long Code Arena: a Set of Benchmarks for Long-Context Code Models [75.70507534322336]
  Long Code Arena is a suite of six benchmarks for code processing tasks that require project-wide context. These tasks cover different aspects of code processing: library-based code generation, CI builds repair, project-level code completion, commit message generation, bug localization, and module summarization. For each task, we provide a manually verified dataset for testing, an evaluation suite, and open-source baseline solutions.
  arXiv  Detail & Related papers  (2024-06-17T14:58:29Z)
• On the Impacts of Contexts on Repository-Level Code Generation [5.641402231731082]
  We present RepoExec, a novel benchmark designed to evaluate repository-level code generation.<n>We focus on three key aspects: executability, functional correctness through comprehensive test case generation, and accurate utilization of cross-file contexts.
  arXiv  Detail & Related papers  (2024-06-17T10:45:22Z)
• Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration [64.19431011897515]
  This paper presents Alibaba LingmaAgent, a novel Automated Software Engineering method designed to comprehensively understand and utilize whole software repositories for issue resolution.<n>Our approach introduces a top-down method to condense critical repository information into a knowledge graph, reducing complexity, and employs a Monte Carlo tree search based strategy.<n>In production deployment and evaluation at Alibaba Cloud, LingmaAgent automatically resolved 16.9% of in-house issues faced by development engineers, and solved 43.3% of problems after manual intervention.
  arXiv  Detail & Related papers  (2024-06-03T15:20:06Z)
• Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub [79.31134731122462]
  We introduce OpenAct benchmark to evaluate the open-domain task-solving capability, built on human expert consultation and repositories in GitHub.<n>We present OpenAgent, a novel LLM-based agent system that can tackle evolving queries in open domains through autonomously integrating specialized tools from GitHub.
  arXiv  Detail & Related papers  (2023-12-28T15:47:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.