Haitao Mi

Venues

Frequent coauthors

Papers

1. Crossing the Reward Bridge: Expanding Reinforcement Learning with Verifiable Rewards Across Diverse Domains
   ACL 2026 ·

   Yi Su

   DBLP profile ↗ORCID search ↗
2. EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving
   ACL 2026 ·

   Mukai Li

   DBLP profile ↗ORCID search ↗
3. Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification
   ACL 2026 ·

   Yuxuan Wan

   DBLP profile ↗ORCID search ↗
4. Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding
   ACL 2026 ·

   Wenkai Wang

   DBLP profile ↗ORCID search ↗
5. Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning
   ACL 2026 ·

   Haolin Liu

   DBLP profile ↗ORCID search ↗
6. Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
   ACL 2026 ·

   Zhenwen Liang

   DBLP profile ↗ORCID search ↗
7. Verified Critical Step Optimization for LLM Agents
   ACL 2026 ·

   Mukai Li

   DBLP profile ↗ORCID search ↗
8. WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models
   ACL 2026 ·

   Rui Wang

   DBLP profile ↗ORCID search ↗
9. WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms
   EACL 2026 ·

   Zhisong Zhang

   DBLP profile ↗ORCID search ↗
10. Your Reasoning Model is Secretly a Reward Model - Optimization-Free Verification from Experience
    ACL 2026 ·

    Zhenwen Liang

    DBLP profile ↗ORCID search ↗
11. DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
    ICLR 2025 ·

    Murong Yue

    DBLP profile ↗ORCID search ↗
12. Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning Models
    ICML 2025 ·

    Xingyu Chen

    DBLP profile ↗ORCID search ↗
13. Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls
    ACL 2025 ·

    Ante Wang

    DBLP profile ↗ORCID search ↗
14. Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
    NeurIPS 2025 ·

    Yuheng Zhang

    DBLP profile ↗ORCID search ↗
15. Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
    ICLR 2025 ·

    Yuheng Zhang

    DBLP profile ↗ORCID search ↗
16. LiteSearch: Efficient Tree Search with Dynamic Exploration Budget for Math Reasoning
    AAAI 2025 ·

    Ante Wang

    DBLP profile ↗ORCID search ↗
17. Low-Bit Quantization Favors Undertrained LLMs
    ACL 2025 ·

    Xu Ouyang

    DBLP profile ↗ORCID search ↗
18. MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation
    NeurIPS 2025 ·

    Zhenwen Liang

    DBLP profile ↗ORCID search ↗
19. Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation
    EMNLP 2025 ·

    Jun-Yu Ma

    DBLP profile ↗ORCID search ↗
20. Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching
    ACL 2025 ·

    Xiaoying Zhang

    DBLP profile ↗ORCID search ↗
21. The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
    NeurIPS 2025 ·

    Ke Ji

    DBLP profile ↗ORCID search ↗
22. Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models
    NeurIPS 2025 ·

    Yue Wang

    DBLP profile ↗ORCID search ↗
23. Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
    NeurIPS 2025 ·

    Xiaoyuan Liu

    DBLP profile ↗ORCID search ↗
24. Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
    NeurIPS 2025 ·

    Mengru Wang

    DBLP profile ↗ORCID search ↗
25. UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
    NeurIPS 2025 ·

    Chenlong Deng

    DBLP profile ↗ORCID search ↗
26. WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback
    EMNLP 2025 ·

    Minda Hu

    DBLP profile ↗ORCID search ↗
27. WebEvolver: Enhancing Web Agent Self-Improvement with Co-evolving World Model
    EMNLP 2025 ·

    Tianqing Fang

    DBLP profile ↗ORCID search ↗
28. Improving LLM Generations via Fine-Grained Self-Endorsement
    ACL 2024 ·

    Ante Wang

    DBLP profile ↗ORCID search ↗
29. Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation
    ACL 2024 ·

    Xiaoying Zhang

    DBLP profile ↗ORCID search ↗
30. Self-Consistency Boosts Calibration for Math Reasoning
    EMNLP 2024 ·

    Ante Wang

    DBLP profile ↗ORCID search ↗
31. The Trickle-down Impact of Reward Inconsistency on RLHF
    ICLR 2024 ·

    Lingfeng Shen

    DBLP profile ↗ORCID search ↗
32. Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
    NeurIPS 2024 ·

    Ye Tian

    DBLP profile ↗ORCID search ↗