SiblingRepair uses LLMs with semantic sibling detection and simultaneous/iterative repair strategies to outperform prior multi-hunk APR tools like Hercules on Defects4J and GHRB benchmarks.
IEEE Transactions on Software Engineering38(1), 54–72 (2012)
8 Pith papers cite this work, alongside 1,064 external citations. Polarity classification is still indexing.
8
Pith papers citing it
1,064
external citations · OpenAlex
citation-role summary
background 2
citation-polarity summary
years
2026 8roles
background 2polarities
background 2representative citing papers
LLM-based Java program repair models lose over 50% of their bug-fixing success rate when presented with equivalent but syntactically varied buggy code.
Ablation experiment in Shplait finds that detailed type error messages improve AI agents' type-error repair rates over minimal messages or dynamic errors, with type systems adding further benefit.
SpecTune improves LLM-based automated program repair by validating localized postconditions and using their intermediate violations for more precise fault localization and patching.
PAFT improves LLM-based program repair pass rates by up to 65.6% while cutting average edit distance by up to 32.6% through explicit preservation signals and curriculum training.
ContractSkill converts draft web agent skills into explicit executable contracts that enable deterministic verification, fault localization, and minimal local repair, improving stability on benchmarks like VisualWebArena.
A framework repairs CPS requirements in Simulink by leveraging system execution data and is evaluated as effective on six real-world case studies covering 12 requirements.
SPEAR applies multi-agent systems with planning, execution, and repair agents using negotiation protocols to smart contract auditing and compares it empirically to centralized and pipeline approaches.
citing papers explorer
-
SiblingRepair: Sibling-Based Multi-Hunk Repair with Large Language Models
SiblingRepair uses LLMs with semantic sibling detection and simultaneous/iterative repair strategies to outperform prior multi-hunk APR tools like Hercules on Defects4J and GHRB benchmarks.
-
HEJ-Robust: A Robustness Benchmark for LLM-Based Automated Program Repair
LLM-based Java program repair models lose over 50% of their bug-fixing success rate when presented with equivalent but syntactically varied buggy code.
-
Type-Error Ablation and AI Coding Agents
Ablation experiment in Shplait finds that detailed type error messages improve AI agents' type-error repair rates over minimal messages or dynamic errors, with type systems adding further benefit.
-
Enhancing Program Repair with Specification Guidance and Intermediate Behavioral Signals
SpecTune improves LLM-based automated program repair by validating localized postconditions and using their intermediate violations for more precise fault localization and patching.
-
PAFT: Preservation Aware Fine-Tuning for Minimal-Edit Program Repair
PAFT improves LLM-based program repair pass rates by up to 65.6% while cutting average edit distance by up to 32.6% through explicit preservation signals and curriculum training.
-
ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents
ContractSkill converts draft web agent skills into explicit executable contracts that enable deterministic verification, fault localization, and minimal local repair, improving stability on benchmarks like VisualWebArena.
-
Automated Repair of Requirements for Cyber-Physical Systems in Simulink Requirements Tables
A framework repairs CPS requirements in Simulink by leveraging system execution data and is evaluated as effective on six real-world case studies covering 12 requirements.
-
SPEAR: An Engineering Case Study of Multi-Agent Coordination for Smart Contract Auditing
SPEAR applies multi-agent systems with planning, execution, and repair agents using negotiation protocols to smart contract auditing and compares it empirically to centralized and pipeline approaches.