Publications (7)
Abstain and Validate: A Dual-LLM Policy for Reducing Noise in Agentic Program Repair
José Cambronero, Michele Tufano, Sherry Shi +7
Agentic Automated Program Repair (APR) is increasingly tackling complex, repository-level bugs in industry, but ultimately these patches still need to be reviewed by a human before…
Agentic Bug Reproduction for Effective Automated Program Repair at Google
Runxiang Cheng, Michele Tufano, Jürgen Cito +5
Bug reports often lack sufficient detail for developers to reproduce and fix the underlying defects. Bug Reproduction Tests (BRTs), tests that fail when the bug is present and pass…
A Visual Attention Grounding Neural Model for Multimodal Machine Translation
Mingyang Zhou, Runxiang Cheng, Yong Jae Lee +1
We introduce a novel multimodal machine translation model that utilizes parallel visual and textual information. Our model jointly optimizes the learning of a shared visual-languag…
Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair
Runxiang Cheng, Michele Tufano, José Cambronero +5
Bug Reproduction Tests (BRTs) have been used in many Automated Program Repair (APR) systems, primarily for validating promising fixes and aiding fix generation. In practice, when d…
Towards a Human-in-the-Loop Framework for Reliable Patch Evaluation Using an LLM-as-a-Judge
Sherry Shi, Renyao Wei, Michele Tufano +4
Reliable evaluation is crucial for advancing Automated Program Repair (APR), but prevailing benchmarks rely on execution-based evaluation methods (unit test pass@k), which fail to…
Configuration Validation with Large Language Models
Xinyu Lian, Yinfang Chen, Runxiang Cheng +4
Misconfigurations are major causes of software failures. Existing practices rely on developer-written rules or test cases to validate configurations, which are expensive. Machine l…