Pith. sign in

REVIEW 8 cited by

How Far Can We Go with Practical Function-Level Program Repair?

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 2404.12833 v2 pith:IUTAWWFK submitted 2024-04-19 cs.SE

Jiahong Xiang , Xiaoyang Xu , Fanchu Kong , Mingyuan Wu , Zizheng Zhang , Haotian Zhang , Yuqun Zhang This is my paper
classification cs.SE
keywords repairfunction-levelinformationllmsperformancetechniquesauxiliarydefects4j
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recently, multiple Automated Program Repair (APR) techniques based on Large Language Models (LLMs) have been proposed to enhance the repair performance. While these techniques mainly focus on the single-line or hunk-level repair, they face significant challenges in real-world application due to the limited repair task scope and costly statement-level fault localization. However, the more practical function-level APR, which broadens the scope of APR task to fix entire buggy functions and requires only cost-efficient function-level fault localization, remains underexplored. In this paper, we conduct the first comprehensive study of LLM-based function-level APR including investigating the effect of the few-shot learning mechanism and the auxiliary repair-relevant information. Specifically, we adopt six widely-studied LLMs and construct a benchmark in both the Defects4J 1.2 and 2.0 datasets. Our study demonstrates that LLMs with zero-shot learning are already powerful function-level APR techniques, while applying the few-shot learning mechanism leads to disparate repair performance. Moreover, we find that directly applying the auxiliary repair-relevant information to LLMs significantly increases function-level repair performance. Inspired by our findings, we propose an LLM-based function-level APR technique, namely SRepair, which adopts a dual-LLM framework to leverage the power of the auxiliary repair-relevant information for advancing the repair performance. The evaluation results demonstrate that SRepair can correctly fix 300 single-function bugs in the Defects4J dataset, largely surpassing all previous APR techniques by at least 85%, without the need for the costly statement-level fault location information. Furthermore, SRepair successfully fixes 32 multi-function bugs in the Defects4J dataset, which is the first time achieved by any APR technique ever to our best knowledge.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Tracing Errors, Constructing Fixes: Repository-Level Memory Error Repair via Typestate-Guided Context Retrieval

    cs.SE 2025-06 conditional novelty 7.0 of 10

    LTFix uses typestate-guided context retrieval to repair 37 of 49 real-world C memory errors with an LLM, outperforming SAVER, ProveNFix, and SWE-agent.

  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. Smaller Models, Unexpected Costs: Trade-offs in LLM Quantization for Automated Program Repair

    cs.SE 2026-06 unverdicted novelty 6.0 of 10

    Empirical evaluation of 13 quantization configurations on 6 LLMs for APR shows reduced memory (up to 85%) but increased inference time/energy, different repaired problem sets with little overlap, and 48% of configs st...

  4. Repair Ingredients Are All You Need: Improving Large Language Model-Based Program Repair via Repair Ingredients Search

    cs.SE 2025-06 conditional novelty 6.0 of 10

    An agent that retrieves internal code context and external historical fix patterns repairs more Defects4J bugs than prior LLM-based repair tools.

  5. 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.

  6. From Empirical Evaluation to Context-Aware Enhancement: Repairing Regression Errors with LLMs

    cs.SE 2025-06 conditional novelty 6.0 of 10

    Adding bug-inducing commit context to LLM prompts raises correct regression repairs from 9 to 16 of 99 Java bugs (1.8x).

  7. Empirical Evaluation of Large Language Models in Automated Program Repair

    cs.SE 2025-06 conditional novelty 5.0 of 10

    An empirical study of four open-source LLMs across six benchmarks shows code-specialized models often outperform larger general models, and most correct repairs appear early in generation.

  8. SoK: Automated Vulnerability Repair: Methods, Tools, and Assessments

    cs.SE 2025-06 conditional novelty 5.0 of 10

    Vul4C, a 144-vulnerability C/C++ repair benchmark with exploits and patches, is introduced and used to compare seven C/C++ and two Java automated vulnerability repair tools.

Pith tools