Dongbin Zhao

Venues

Frequent coauthors

Papers

1. AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning
   ACL 2026 ·

   Jingbo Sun

   DBLP profile ↗ORCID search ↗
2. Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching
   ACL 2026 ·

   Bo Lv

   DBLP profile ↗ORCID search ↗
3. CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic
   ACL 2026 ·

   Yaocheng Zhang

   DBLP profile ↗ORCID search ↗
4. Spec-o3: A Tool-Augmented Vision-Language Agent for Rare Celestial Object Candidate Vetting via Automated Spectral Inspection
   ACL 2026 ·

   Minghui Jia

   DBLP profile ↗ORCID search ↗
5. Advancing Object-Goal Navigation through LLM-enhanced Object Affinities Transfer
   IROS 2025 ·

   Mengying Lin

   DBLP profile ↗ORCID search ↗
6. Consistency Policy with Categorical Critic for Autonomous Driving
   AAMAS 2025 ·

   Xing Fang

   DBLP profile ↗ORCID search ↗
7. Constrained Exploitability Descent: An Offline Reinforcement Learning Method for Finding Mixed-Strategy Nash Equilibrium
   ICML 2025 ·

   Runyu Lu

   DBLP profile ↗ORCID search ↗
8. DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy
   ICML 2025 ·

   Kaixuan Xu

   DBLP profile ↗ORCID search ↗
9. Divergence-Regularized Discounted Aggregation: Equilibrium Finding in Multiplayer Partially Observable Stochastic Games
   ICLR 2025 ·

   Runyu Lu

   DBLP profile ↗ORCID search ↗
10. Empowering LLM Agents with Zero-Shot Optimal Decision-Making through Q-learning
    ICLR 2025 ·

    Jiajun Chai

    DBLP profile ↗ORCID search ↗
11. Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games
    NeurIPS 2025 ·

    Runyu Lu

    DBLP profile ↗ORCID search ↗
12. INS: Interaction-aware Synthesis to Enhance Offline Multi-agent Reinforcement Learning
    ICLR 2025 ·

    Yuqian Fu

    DBLP profile ↗ORCID search ↗
13. In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning
    AAAI 2025 ·

    Songjun Tu

    DBLP profile ↗ORCID search ↗
14. Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL
    NeurIPS 2025 ·

    Songjun Tu

    DBLP profile ↗ORCID search ↗
15. Learning and Planning Multi-Agent Tasks via an MoE-based World Model
    NeurIPS 2025 ·

    Zijie Zhao

    DBLP profile ↗ORCID search ↗
16. Offline Goal-Conditioned Reinforcement Learning with Elastic-Subgoal Diffused Policy Learning
    AAMAS 2025 ·

    Yaocheng Zhang

    DBLP profile ↗ORCID search ↗
17. Online Preference-based Reinforcement Learning with Self-augmented Feedback from Large Language Model
    AAMAS 2025 ·

    Songjun Tu

    DBLP profile ↗ORCID search ↗
18. RLAE: Reinforcement Learning-Assisted Ensemble for LLMs
    EMNLP 2025 ·

    Yuqian Fu

    DBLP profile ↗ORCID search ↗
19. Salience-Invariant Consistent Policy Learning for Generalization in Visual Reinforcement Learning
    AAMAS 2025 ·

    Jingbo Sun

    DBLP profile ↗ORCID search ↗
20. UncAD: Towards Safe End-to-end Autonomous Driving via Online Map Uncertainty
    ICRA 2025 ·

    Pengxuan Yang

    DBLP profile ↗ORCID search ↗
21. Unsupervised Zero-Shot Reinforcement Learning via Dual-Value Forward-Backward Representation
    ICLR 2025 ·

    Jingbo Sun

    DBLP profile ↗ORCID search ↗
22. Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations
    NeurIPS 2025 ·

    Xin Liu

    DBLP profile ↗ORCID search ↗
23. World4Drive: End-to-End Autonomous Driving via Intention-Aware Physical Latent World Model
    ICCV 2025 ·

    Yupeng Zheng

    DBLP profile ↗ORCID search ↗
24. Aligning Credit for Multi-Agent Cooperation via Model-based Counterfactual Imagination
    AAMAS 2024 ·

    Jiajun Chai

    DBLP profile ↗ORCID search ↗
25. Boosting Continuous Control with Consistency Policy
    AAMAS 2024 ·

    Yuhui Chen

    DBLP profile ↗ORCID search ↗
26. Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization
    NeurIPS 2024 ·

    Haoran Li

    DBLP profile ↗ORCID search ↗
27. Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement
    NeurIPS 2024 ·

    Zhi Wang

    DBLP profile ↗ORCID search ↗
28. User Response Modeling in Reinforcement Learning for Ads Allocation
    WWW 2024 ·

    Zhiyuan Zhang

    DBLP profile ↗ORCID search ↗