Lune

FSE2026Top-tier venue

LinkAnchor: An Autonomous LLM-Based Agent for Issue-to-Commit Link Recovery

Arshia Akhavan, Alireza Hoseinpour, Abbas Heydarnoori, Hamid Bagheri, Mehdi Keshani

Abstract

Issue-to-commit link recovery in software repositories is fundamental to software traceability and project management, yet it remains a challenging task. Prior studies show that only about 42.2% of issues on GitHub are correctly linked to their commits, highlighting the need for more effective solutions. Existing work has explored a range of ML/DL approaches, and more recently, large language models (LLMs) have been applied to this problem. However, these methods face two major limitations. First, LLMs are restricted by limited context windows and cannot simultaneously process all available data sources, such as long commit histories, extensive issue discussions, and large code repositories. Second, most approaches operate on individual issue-commit pairs, where a model independently scores the relevance of a single commit to an issue. This pairwise formulation fails to account for the complex associativity of software fixes, where an issue is often resolved by an aggregate chain of commits rather than a single atomic change. By ignoring these temporal and parental dependencies, existing methods often fail to incorporate the complete resolution logic and might misidentify intermediate commits as final fixes. Furthermore, this strategy is computationally inefficient in large repositories, as it requires exhaustively evaluating an enormous number of candidate pairs. To address these challenges, we present LinkAnchor, the first autonomous LLM-based agent designed specifically for issue-to-commit link recovery. LinkAnchor introduces a lazy-access architecture that allows the underlying LLM to dynamically retrieve only the most relevant contextual data, such as commits, issue comments, and code files, without exceeding token limits. Instead of isolated scoring, LinkAnchor treats link recovery as a dynamic search process, navigating the commit graph to identify the final resolving commit and effectively aggregating the entire chain of contributing changes. LinkAnchor is first to formalize ILR as dynamic heuristic search over commit chains (vs. prior pairwise scoring), enabling aggregate reasoning that recovers distributed fixes (46% of cases). Our evaluations show that LinkAnchor outperforms state-of-the-art baselines by 41–714% in Hit@1 across six large-scale open-source projects, while costing only about 0.01 US dollars per issue. Finally, LinkAnchor is designed and tested for both GitHub and Jira, and its modular architecture makes it straightforward to extend to other platforms.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Traceability Transformed: Generating more Accurate Links with Pre-Trained BERT Models cites CodeBERT: A Pre-Trained Model for Programming and Natural Languages
  • AutoCodeRover: Autonomous Program Improvement cites SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
  • Finding A Needle in a Haystack: Automated Mining of Silent Vulnerability Fixes cites CodeBERT: A Pre-Trained Model for Programming and Natural Languages
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on21

  1. CodeBERT: A Pre-Trained Model for Programming and Natural LanguagesZhangyin Feng, Daya Guo, Duyu Tang, Nan Duan et al.EMNLP Findings 2020 · 2,828 citations
  2. SWE-agent: Agent-Computer Interfaces Enable Automated Software EngineeringJohn Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret et al.NeurIPS 2024 · 2,059 citations
  3. Traceability Transformed: Generating more Accurate Links with Pre-Trained BERT ModelsJinfeng Lin, Yalin Liu, Qingkai Zeng, Meng Jiang et al.ICSE 2021 · 124 citations
  4. AutoCodeRover: Autonomous Program ImprovementYuntong Zhang, Haifeng Ruan, Zhiyu Fan, Abhik RoychoudhuryISSTA 2024 · 96 citations
  5. Finding A Needle in a Haystack: Automated Mining of Silent Vulnerability FixesJiayuan Zhou, Michael Pacheco, Zhiyuan Wan, Xin Xia et al.ASE 2021 · 84 citations

Related papers

  1. EALink: An Efficient and Accurate Pre-Trained Framework for Issue-Commit Link RecoveryChenyuan Zhang, Yanlin Wang, Zhao Wei, Yong Xu et al.ASE 2023 · 10 citations
  2. MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue ResolutionWei Tao, Yucheng Zhou, Yanlin Wang, Wenqiang Zhang et al.NeurIPS 2024 · 210 citations
  3. SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue ResolutionChengxing Xie, Bowen Li, Chang Gao, He Du et al.ACL Findings 2025 · 10 citations
  4. Atomizer: An LLM-based Collaborative Multi-Agent Framework for Intent-Driven Commit UntanglingKangchen Zhu, Zhiliang Tian, Shangwen Wang, Mingyue Leng et al.ICSE 2026
  5. LiSSA: Toward Generic Traceability Link Recovery Through Retrieval- Augmented GenerationDominik Fuchß, Tobias Hey, Jan Keim, Haoyu Liu et al.ICSE 2025 · 8 citations
Dusk over the sea between two cliffs drawn in fine vertical lines