ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning (2025 · 15 citations)
Large language models often fail at multi-step chemistry problems. They misuse domain formulas, choose wrong constants or units, and make arithmetic slips that carry through later steps. They also write faulty Python for calculations. Earlier fixes such as StructChem prompting or self-reflection rely on fixed…
ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning (2026 · 1 citation)
Code LLMs, especially small ones, are poor at tracing how a program actually runs. Earlier methods fine-tune on teacher-written explanations, either I/O reasoning chains or verbalized traces. Intermediate steps are never checked, so a model can learn to copy text without understanding execution, and the training data…

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

ChemAgent: Self-updating Library in Large Language Models Improves Chemical ReasoningarXiv:2501.06590Xiangru Tang, Tianyu Hu, Muyang Ye, et al.2025 · 15 citations
ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Lingxiao Tang, He Ye, Zhaoyang Chu, et al.2026 · 1 citation
ComfyFlow: Benchmarking LLMs for AIGC Workflow Generation ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetZhenran Xu et al.2026

Co-authors here

10 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 12 times (of the 149,439 papers whose bibliographies we read); 1 citing paper with a page here →.

Updated 1 November 2026