Noisy Issues, Noisy Results: Mislabeling in Information Retrieval-based Bug Localization
cs.SE
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/mou23/Mislabeling-in-IRB
Terminology
Sources
- Large Language Models in Fault Localisation
- A Multi-Agent Approach to Fault Localization via Graph-Based Retrieval and Reflexion
- Enhancing LLM-based Fault Localization with a Functionality-Aware Retrieval-Augmented Generation Framework
- OrcaLoca: An LLM Agent Framework for Software Issue Localization
- Tool-integrated Reinforcement Learning for Repo Deep Search
- D&C: A Divide-and-Conquer Approach to IR-based Bug Localization
Related papers
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
- TestPrism: Rethinking Test Evaluation Beyond a Single Reference
- Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- For Coding Agents, the Repository Matters