DebugRepair improves LLM-based automated program repair by adding test semantic purification, simulated instrumentation, and debugging-driven conversational repair, fixing 224 Defects4J bugs with GPT-3.5 (26.2% above prior SOTA) and 295 with DeepSeek-V3.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
MemHint combines LLM classification of custom memory functions with Z3 path validation to augment CodeQL and Infer, detecting 52 memory leaks (49 confirmed) across 3.4M LOC versus 19 and 3 by vanilla tools.
GALA uses hierarchical graph alignment between UI screenshots and code structures to achieve state-of-the-art bug localization in multimodal automated program repair on SWE-bench.
CDDRefactorER constrains AI-driven refactoring using Cognitive-Driven Development rules to cut failures by 54-71% and raise novice comprehension scores by 22-31%.
U-Define improves user control in LLM planning by letting people define hard rules and soft preferences in natural language with matching verification methods, raising usefulness and satisfaction scores.
citing papers explorer
-
DebugRepair: Enhancing LLM-Based Automated Program Repair via Self-Directed Debugging
DebugRepair improves LLM-based automated program repair by adding test semantic purification, simulated instrumentation, and debugging-driven conversational repair, fixing 224 Defects4J bugs with GPT-3.5 (26.2% above prior SOTA) and 295 with DeepSeek-V3.
-
Finding Memory Leaks in C/C++ Programs via Neuro-Symbolic Augmented Static Analysis
MemHint combines LLM classification of custom memory functions with Z3 path validation to augment CodeQL and Infer, detecting 52 memory leaks (49 confirmed) across 3.4M LOC versus 19 and 3 by vanilla tools.
-
GALA: Multimodal Graph Alignment for Bug Localization in Automated Program Repair
GALA uses hierarchical graph alignment between UI screenshots and code structures to achieve state-of-the-art bug localization in multimodal automated program repair on SWE-bench.
-
Improving Code Comprehension through Cognitive-Load Aware Automated Refactoring for Novice Programmers
CDDRefactorER constrains AI-driven refactoring using Cognitive-Driven Development rules to cut failures by 54-71% and raise novice comprehension scores by 22-31%.
-
U-Define: Designing User Workflows for Hard and Soft Constraints in LLM-Based Planning
U-Define improves user control in LLM planning by letting people define hard rules and soft preferences in natural language with matching verification methods, raising usefulness and satisfaction scores.