ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (2024 · 200 citations)
LLM self-training usually keeps only the generated solutions whose final answer is correct. Many of those solutions still contain flawed or useless intermediate steps, so the fine-tuning data ends up noisy. Process reward models (PRMs) can check each step, but they normally need costly step-level human labels.…
DataSciBench: An LLM Agent Benchmark for Data Science (2026 · 13 citations)
Most benchmarks for LLMs in data science test isolated tasks with simple metrics such as accuracy and with ground truth that is easy to obtain.

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.

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree SearchConference on Neural Information Processing Systems (NeurIPS)Dan Zhang, Sining Zhoubian, Ziniu Hu, et al.2024 · 200 citations
SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models ↗arXiv:2401.07950 · no summary yetDan Zhang et al.2024 · 37 citations
DataSciBench: An LLM Agent Benchmark for Data ScienceFindings of the Association for Computational LinguisticsDan Zhang, Sining Zhoubian, Min Cai, et al.2026 · 13 citations

Co-authors here

6 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 209 times (of the 149,439 papers whose bibliographies we read); 46 citing papers with a page here →.

Updated 30 October 2026