🧑‍🔬 Weiwen Xu

🏛️ Affiliations

🏢Alibaba DAMO AcademyHangzhou · China2024–2025 · 3 paperscurrent🏢Alibaba GroupGeorge Town · Cayman Islands2024–2025 · 3 paperscurrent🏢Alibaba GroupHangzhou · China2024–2025 · 3 paperscurrent🎓Southern Medical UniversityGuangzhou · China2009–2020 · 29 papers🎓Chinese University of Hong KongHong Kong · China2022 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 6 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions (2025 · 16 citations)
   Keeping up with rapidly released LLMs requires evaluation that is both fast and trustworthy. Static benchmarks such as MMLU or MT-Bench risk contamination and handle open-ended output poorly. Crowdsourced platforms like Chatbot Arena are trusted but need many human votes, which makes them slow for new models and weak…
2. Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks (2025 · 13 citations)
   LLMs that combine chain-of-thought with retrieval-augmented generation often fail on hard, knowledge-heavy problems such as competitive programming.
3. ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning (2025 · 11 citations)
   Reasoning-oriented LLMs do well in math and code, but medical QA depends on broad, accurate domain knowledge and lacks large, carefully checked reasoning data.
4. FineReason: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving (2025 · 6 citations)
   Most reasoning benchmarks for LLMs score only the final answer. They do not show whether a model can examine its intermediate steps, notice a dead end, and recover from it. FineReason fills this gap with logic puzzles that break down into small verifiable steps. It covers four puzzle types: Sudoku, Graph Coloring…
5. Revealing Procedural Reasoning Structures in Chain-of-Thought Training via Span-Level Gradient Organization (2026 · 1 citation)
   The paper asks how step-by-step reasoning patterns in Chain-of-Thought (CoT) training data appear in the training signal itself, rather than in generated outputs or hidden representations.

All works

7 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

1. Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents ↗arXiv:2410.13185 · no summary yetLong Li et al.2024 · 47 citations
2. Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee DiscussionsAnnual Meeting of the Association for Computational Linguistics (ACL)Ruochen Zhao, Wenxuan Zhang, Yew Ken Chia, et al.2025 · 16 citations
3. Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging TasksAnnual Meeting of the Association for Computational Linguistics (ACL)Xingxuan Li, Weiwen Xu, Ruochen Zhao, et al.2025 · 13 citations
4. ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical ReasoningConference on Empirical Methods in Natural Language Processing (EMNLP)Yu Sun, Xingyu Qian, Weiwen Xu, et al.2025 · 11 citations
5. ConReader: Exploring Implicit Relations in Contracts for Contract Clause Extraction ↗Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · no summary yetWeiwen Xu et al.2022 · 10 citations
6. FineReason: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle SolvingAnnual Meeting of the Association for Computational Linguistics (ACL)Guizhen Chen, Weiwen Xu, Hao Zhang, et al.2025 · 6 citations
7. Revealing Procedural Reasoning Structures in Chain-of-Thought Training via Span-Level Gradient OrganizationAnnual Meeting of the Association for Computational Linguistics (ACL)Jia Liu, Jiaxin Luo, Weiwen Xu, et al.2026 · 1 citation

🤝 Co-authors here

12 of 19 co-authors with a page, the most papers together first.

• Deli Zhao ×3
• Lidong Bing ×3
• Hao Zhang ×2
• Ruochen Zhao ×2
• Yu Rong ×2
• Anh Tuan Luu
• Chaoqun Liu
• Chenghao Xiao
• Fangkai Jiao
• Guizhen Chen
• Hou Pong Chan
• Jia Liu

Venues

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

• Annual Meeting of the Association for Computational Linguistics (ACL) ×4: ACL 2026, ACL 2025 ×3
• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×2: EMNLP 2025

🔗 Cited by

Papers of our library cite their works 84 times (of the 149,439 papers whose bibliographies we read); 20 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/weiwen-xu/