publications

The symbol * means equal contribution and † means corresponding author.

2025

  1. MATH-AI@NeurIPS 2025
    RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?
    Yiyou Sun, Yuhan Cao, Pohao Huang, and 4 more authors
    2025
  2. Manuscript
    Pay for The Second-Best Service: A Game-Theoretic Approach Against Dishonest LLM Providers
    Yuhan Cao*, Yu Wang*, Sitong Liu, and 3 more authors
    2025
  3. Manuscript
    AICrypto: A Comprehensive Benchmark for Evaluating Cryptography Capabilities of Large Language Models
    Yu Wang*, Yijian Liu*, Liheng Ji*, and 11 more authors
    2025
  4. Manuscript
    Can LLMs Generate Reliable Test Case Generators? A Study on Competition-Level Programming Problems
    Yuhan Cao*†, Zian Chen*, Kun Quan, and 18 more authors
    2025
  5. Manuscript
    Demonstrations of Integrity Attacks in Multi-Agent Systems
    Can Zheng, Yuhan Cao, Xiaoning Dong, and 1 more author
    2025
  6. Manuscript
    Convince me with More Paragraphs: Generate and Evaluate Persuasive Writing with Multi-Agent LLMs
    Zijian Ling*, Yazhuo Zhou*, Yuhan Cao*†, and 4 more authors
    2025
  7. Manuscript
    Prediction of Persistent Drug Seeking Behavior by Brain-Wide Network
    Yuhan Cao*, Wenlei Zhang*, Xiaocheng Zhang, and 6 more authors
    2025

2024

  1. Manuscript
    Combinatorial Auctions Framework on Network
    Xuanyu Li, Miao Li, Yuhan Cao, and 1 more author
    2024
  2. AAAI 2024
    Double Auction on Diffusion Network (Oral Presentation Received, Oral Presenter)
    Miao Li, Yuhan Cao, and Dengji Zhao†
    The 38th Annual AAAI Conference on Artificial Intelligence, 2024
    PDF