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.
How far can we go with practical function-level program repair?
5 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
5
Pith papers citing it
2
external citations · external index
citation-role summary
background 2
citation-polarity summary
fields
cs.SE 5roles
background 2polarities
background 2representative citing papers
ADI equips AI debugging agents with function-level interaction via a new execution trace structure, raising SWE-bench Verified resolution to 63.8% at $1.28 per task and delivering 6-18% gains when added to existing agents.
Across 13 quantization setups on six LLMs and two APR benchmarks, memory falls sharply while time and energy rise, nearly half of configs are Pareto-dominated, and repaired bug sets drift despite similar counts.
LLMs perform well on basic syntactic and semantic bugs in small code but struggle with complex security vulnerabilities and large production codebases.
A literature survey that collects and categorizes 124 papers on LLM-based agents for software engineering from SE and agent perspectives.
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.
-
Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis
ADI equips AI debugging agents with function-level interaction via a new execution trace structure, raising SWE-bench Verified resolution to 63.8% at $1.28 per task and delivering 6-18% gains when added to existing agents.
-
Smaller Models, Unexpected Costs: Trade-offs in LLM Quantization for Automated Program Repair
Across 13 quantization setups on six LLMs and two APR benchmarks, memory falls sharply while time and energy rise, nearly half of configs are Pareto-dominated, and repaired bug sets drift despite similar counts.
-
Can LLMs Find Bugs in Code? An Evaluation from Beginner Errors to Security Vulnerabilities in Python and C++
LLMs perform well on basic syntactic and semantic bugs in small code but struggle with complex security vulnerabilities and large production codebases.
-
Large Language Model-Based Agents for Software Engineering: A Survey
A literature survey that collects and categorizes 124 papers on LLM-based agents for software engineering from SE and agent perspectives.