Yuyang Wu's Homepage

Carnegie Mellon University

prof_pic.jpg

5000 Forbes Ave

Pittsburgh, PA 15213

I am Yuyang (Younger) Wu, a Ph.D. student in AI for Science at Carnegie Mellon University, where I also earned my M.S. from the School of Computer Science. My research focuses on agent self-evolution and recursive self-improvement of large language models.

My work aims to build AI agents that can continuously evolve — refining their own capabilities, strategies, and knowledge through self-directed improvement. I am passionate about developing autonomous systems that learn from their own experience and iteratively become more capable, reliable, and general.

My recent research explores how agents can bootstrap their own growth through recursive self-improvement, enabling AI to accelerate scientific discovery while continuously raising its own standards of accuracy and generalization.

news

Aug 20, 2025 Our paper on MolErr2Fix has been accepted to EMNLP 2025 as an oral presentation!

selected publications

  1. MolErr2Fix: Benchmarking LLM Trustworthiness in Chemistry via Modular Error Detection, Localization, Explanation, and Revision
    Yuyang Wu, Jinhui Ye, Shuhao Zhang, and 3 more authors
    In EMNLP 2025 (Oral Presentation), 2025
  2. BIB
    Multiview representation learning for identification of novel cancer genes and their causative biological mechanisms
    Jianye Yang, Haitao Fu, Feiyang Xue, and 7 more authors
    Briefings in Bioinformatics, 2024
  3. ECCV
    Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective
    Qiyao Xue, Weichen Liu, Shiqi Wang, and 3 more authors
    In ECCV 2026, 2026
  4. arXiv
    Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning
    Yuyang Wu, Yue Huang, Shuaike Shen, and 8 more authors
    arXiv preprint arXiv:2605.07251, 2026
  5. BioNLP
    KGRxn-LLM: Knowledge Graph Enhanced Large Language Models for Molecular Reaction Reasoning
    Weichen Liu, Qiyao Xue, Yuyang Wu, and 2 more authors
    In BioNLP 2026, 2026
  6. arXiv
    CLORE: Content-Level Optimization for Reasoning Efficiency
    Yuyang Wu, Qiyao Xue, Guanxing Lu, and 4 more authors
    arXiv preprint arXiv:2605.22211, 2026
  7. arXiv
    KARA: Efficient Reasoning LLM Serving via Sliding-Window KV Cache Compression
    Shen Han, Yuyang Wu, Junpu Yu, and 1 more author
    arXiv preprint arXiv:2607.01237, 2026
  8. VIS
    VeriLLMed: Interactive Visual Debugging of Medical Large Language Models with Knowledge Graphs
    Yurui Xiang, Xingyi Mao, Rui Sheng, and 7 more authors
    In VIS 2026, 2026
  9. BIB
    HimGNN: a novel hierarchical molecular graph representation learning framework for property prediction
    Shen Han, Haitao Fu, Yuyang Wu, and 6 more authors
    Briefings in Bioinformatics, 2023