Skip to content

Author

Zhouxing Shi

University of California, Los Angeles

We have 3 of 36 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Evaluating the Robustness of Proof Autoformalization in Lean 4

It is argued that a robust proof autoformalizer must remain faithful even for informal proofs that diverge from these idealized ones, and the first study on the robustness of proof autoformalization models is presented.

Zheng-Tao Gui, Sheng-Yuan Yang, Zhouxing Shi · 2 citations
#artificial intelligence Preprint Oct 2026

Efficient Proof Generation for Lean Statements with Multiple Candidate Answers

This work proposes a joint proof framework that integrates candidate answer selection, answer supplementation, and formal proof generation into a unified reasoning process and achieves the same formal proof success rate as per-candidate proof generation with about one sixth of the token cost.

Peng-Zhen Lin, Ke Zhang, M. Raissi et al. · 0 citations

Recursive Self-Improvement via On-Policy Distillation for Reasoning

DCE+SRCL outperforms OPSD across multiple model scales and four competition-level mathematics benchmarks, and its comprehensive evaluations show that DCE+SRCL outperforms OPSD across multiple model scales and four competition-level mathematics benchmarks.

Shang-Jian Yin, Ze-Hao Zhao, Kavosh Asadi et al. · 6 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.