Publications

Peer-Reviewed Papers

From Automated Program Repair to Automated Agent Repair: Why Failed Trajectories Matter

Xiangxin Zhao
ASE 2026 Student Research Competition (SRC), Munich, Germany · Accepted

An execution-grounded audit of failed coding-agent trajectories, laying the empirical foundation for Trajectory-Centric Automated Agent Repair (TC-AAR).

Recommended citation: Xiangxin Zhao. 2026. "From Automated Program Repair to Automated Agent Repair: Why Failed Trajectories Matter." In Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE '26), Student Research Competition. ACM. doi:10.1145/3832783.3844579
Download Paper | Download Bibtex

Preprints & Under Review

CRJudgeBench: Can AI Detect Plausible but Invalid Code Reviews?

Yue Pan, Jiawei Li, Ziyuan Zhang, Xiangxin Zhao, He Ye
Manuscript · Under review

A benchmark of 1,199 instances for judging the technical trustworthiness of code-review comments, plus Sentinel, a repository-grounded agentic judge.

Recommended citation: Yue Pan, Jiawei Li, Ziyuan Zhang, Xiangxin Zhao, He Ye. (2026). "CRJudgeBench: Can AI Detect Plausible but Invalid Code Reviews?" Under review.

Failure as a Process: An Anatomy of CLI Coding Agent Trajectories

Xiangxin Zhao, Han Li, Shuaiting Li, Tianyi Zhao, Earl T. Barr, Federica Sarro, He Ye
arXiv preprint arXiv:2607.09510 · Under review

The first large-scale empirical study of CLI coding-agent failure trajectories: 3,843 trajectories from seven frontier models across three scaffolds on Terminal-Bench, 1,794 of them manually annotated (63,000+ steps).

Recommended citation: Xiangxin Zhao, Han Li, Shuaiting Li, Tianyi Zhao, Earl T. Barr, Federica Sarro, He Ye. (2026). "Failure as a Process: An Anatomy of CLI Coding Agent Trajectories." arXiv preprint arXiv:2607.09510.
Download Paper