Xingchen Wan

Xingchen Wan

Senior Research Scientist

Google

About me

I am a Senior Research Scientist at Google based in the San Francisco Bay Area.

Previously, I did my DPhil (the Oxford way of saying PhD) in the Machine Learning Research Group, Department of Engineering Science, University of Oxford.

Academic Services

Area chair/senior program committee member at NeurIPS (2024-25), ICML (2025), ACL ARR (2025-); Action editor at TMLR.

Reviewer/program committee member at ACL (2023-24), AutoML-Conf (2023-24), COLM (2024), CVPR (2024), ECCV (2024), EMNLP (2023-24), ICLR (2024-25), ICML (2023-24), JMLR, Machine Learning, NeurIPS (2022-23), WACV (2022-24), etc.

Interests
  • Large language models
  • Bayesian optimization
  • Automated machine learning (AutoML)
  • Machine learning on graphs
Education
  • DPhil (PhD), Machine Learning, 2019 - 2023

    University of Oxford

  • BA, MEng, Engineering Science. First-class Honours, 2015 - 2019

    University of Oxford

Recent News

💡 Preprint: VPRL
We propose Visual Planning via Reinforcement Learning (VPRL), which significantly boosted planning capabilities in pure vision-based models with reinforcement learning post-training.
📄 Astute RAG accepted at ACL 2025
Astute RAG was accepted at ACL 2025 as a main paper!
💡 Preprint: Reasoning-SQL
We applied DeepSeek R1-style GRPO post-training to obtain Reasoning-SQL 14B, achieving SoTA results on par or better than much larger models on the BIRD benchmark. Check the preprint here.
💡 Preprint: Automating multi-agent designs
Our new work on automating prompt and topology design in multi-agent LLM systems is now available as an arXiv preprint!
📄 ICLR acceptance: Self-improving long-context reasoners

Publications

View all listed publications or view by tags. For a complete list including preprints & working papers, refer to my Google Scholar.
(2025). Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models. Proceedings of the 63rd Annual Conference of the Association for Computational Linguistics (ACL) (to appear).

PDF Cite Abstract

(2025). Visual Planning: Let's Think Only with Images. arXiv preprint arXiv:2505.11409.

PDF Cite Abstract

(2025). Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL. arXiv preprint arXiv:2503.23157.

PDF Cite Abstract

(2025). From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation. International Conference on Learning Representations (ICLR).

PDF Cite Abstract

(2025). Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies. arXiv preprint arXiv:2502.02533.

PDF Cite Abstract

(2024). Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization. Advances in Neural Information Processing Systems (NeurIPS).

PDF Cite Abstract OpenReview

(2024). UQE: A Query Engine for Unstructured Databases. Advances in Neural Information Processing Systems (NeurIPS).

PDF Cite Abstract OpenReview

(2024). Bayesian Optimization of Functions over Node Subsets in Graphs. Advances in Neural Information Processing Systems (NeurIPS).

PDF Cite Code Abstract OpenReview

Experience

 
 
 
 
 
Google
Senior Research Scientist
February 2024 – Present San Francisco Bay Area, CA, US
May 2025 - Present: Senior Research Scientist
Feb 2024 - Apr 2025: Research Scientist
 
 
 
 
 
Google
Research Intern
October 2022 – June 2023 San Francisco Bay Area, CA, US & London, UK
 
 
 
 
 
Meta
Research Intern
May 2022 – September 2022 London, UK

Contact