Pith. sign in

REVIEW 12 cited by

MarsCode Agent: AI-native Automated Bug Fixing

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.00899 v2 pith:E3ZCPLG2 submitted 2024-09-02 cs.SE cs.AI

Yizhou Liu , Pengfei Gao , Xinchen Wang , Jie Liu , Yexuan Shi , Zhao Zhang , Chao Peng This is my paper · ORCID
classification cs.SEcs.AI
keywords agentmarscodefixingllmssoftwareautomatedcodegeneration
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent advances in large language models (LLMs) have shown significant potential to automate various software development tasks, including code completion, test generation, and bug fixing. However, the application of LLMs for automated bug fixing remains challenging due to the complexity and diversity of real-world software systems. In this paper, we introduce MarsCode Agent, a novel framework that leverages LLMs to automatically identify and repair bugs in software code. MarsCode Agent combines the power of LLMs with advanced code analysis techniques to accurately localize faults and generate patches. Our approach follows a systematic process of planning, bug reproduction, fault localization, candidate patch generation, and validation to ensure high-quality bug fixes. We evaluated MarsCode Agent on SWE-bench, a comprehensive benchmark of real-world software projects, and our results show that MarsCode Agent achieves a high success rate in bug fixing compared to most of the existing automated approaches.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Evaluating LLM Agents on Automated Software Analysis Tasks

    cs.SE 2026-04 unverdicted novelty 7.0 of 10

    A purpose-built, staged LLM agent correctly sets up and executes software analysis tools on 33 of 35 benchmark tasks, outperforming general-purpose agent baselines by at least 17 percentage points.

  2. MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs

    cs.SE 2026-07 conditional novelty 6.0 of 10

    Coordinator-proposer multi-agent repair schedules hunks, proposes candidate patches in parallel, and selects/refines them, fixing 326/835 Defects4J bugs with GPT-3.5 and 420 with Claude-3.5-Sonnet.

  3. One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents

    cs.SE 2025-12 conditional novelty 6.0 of 10

    Repository-level issue localization can be done by a single jump-to-definition tool trained with reinforcement learning, achieving strong results on SWE-bench despite using only open-weights models.

  4. SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution

    cs.SE 2025-07 conditional novelty 6.0 of 10

    A competitive multi-agent debate over graph-derived fault propagation chains lifts automated issue resolution on SWE-bench Verified to 41.4% pass@1.

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

    cs.SE 2025-07 reject novelty 6.0 of 10

    GCC, a Git-inspired context management layer, is reported to lift a Claude-based agent to 48.00% on SWE-Bench-Lite and to enable a self-replicating CLI that resolves 40.7% of tasks versus 11.7% without it.

  6. Agentic Program Repair from Test Failures at Scale: A Neuro-symbolic approach with static analysis and test execution feedback

    cs.SE 2025-07 conditional novelty 6.0 of 10

    Meta's Engineering Agent solved 42.3% of curated internal test-failure tasks offline and landed 25.5% of generated fixes in production over three months.

  7. Aime: Towards Fully-Autonomous Multi-Agent Framework

    cs.AI 2025-07 reject novelty 6.0 of 10

    Aime, a dynamic multi-agent framework, reports outperforming specialized baselines on GAIA (77.6%), SWE-bench Verified (66.4%), and WebVoyager (92.3%), but without code, error bars, or a specified LLM.

  8. Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing

    cs.SE 2025-06 conditional novelty 6.0 of 10

    GUIRepair, a cross-modal LLM pipeline that converts issue screenshots into reproduction code and rendered patch screenshots into validation feedback, resolves 157/517 SWE-bench M instances with GPT-4o and 175 with o4-mini.

  9. The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks

    cs.AI 2025-02 conditional novelty 6.0 of 10

    AI coding agents that overthink, spending effort on internal reasoning instead of acting, perform worse, and selecting lower-overthinking attempts improves success by ~30% with 43% less compute.

  10. Beyond Accuracy: Behavioral Dynamics of Agentic Multi-Hunk Repair

    cs.SE 2025-11 conditional novelty 5.0 of 10

    On 372 multi-hunk bugs, coding agents repair between 26% and 93% of defects, accuracy falls as edits become more divergent and dispersed, and failed repairs consume up to 343% more tokens.

  11. Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling

    cs.SE 2025-07 conditional novelty 5.0 of 10

    Trae Agent combines parallel patch generation, hierarchical pruning, and agent-based majority-vote selection to reach 75.20% Pass@1 on SWE-bench Verified, the current leaderboard leader.

  12. SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code

    cs.CR 2025-06 conditional novelty 5.0 of 10

    A 558-task benchmark with SAST and LLM judging shows state-of-the-art LLMs generate vulnerability-free code only about 37% of the time in zero-shot settings.

Pith tools