Preprints

• A Causal Approach for Interpretable Reward Redistribution in Visual Reinforcement Learning Causal RL Under Review
  Yudi Zhang, Yali Du, Biwei Huang, Ziyan Wang, Jun Wang, Meng Fang, Mykola Pechenizkiy. Under Review
• Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones? LLM Agents Preprint
  Yudi Zhang, Lu Wang, Meng Fang, Yali Du, et al. Preprint Link

Conferences

• CAST: A Causality-inspired Spatial-temporal Return Decomposition Approach for Multi-agent RL. Causal RL RLC 2026
  Yudi Zhang, Yali Du, Biwei Huang, Meng Fang, Mykola Pechenizkiy. RLC 2026 Link
• Self-Evolving LLM Agents with In-distribution Optimization. LLM Agents ICML 2026
  Yudi Zhang, Meng Fang, Zhenfang Chen, Mykola Pechenizkiy. ICML 2026 Link
• Causality Meets Locality: Provably Generalizable and Scalable Policy Learning for Networked Systems. Causal RL NeurIPS 25 Spotlight
  Hao Liang^*, Shuqing Shi^*, Yudi Zhang, Biwei Huang, Yali Du. NeurIPS 2025 Link
• Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-level Physics Problem Solving. LLM RAG EMNLP Findings 25
  Shunfeng Zheng^*, Yudi Zhang^*, Meng Fang, Zihan Zhang, Zhitan Wu, Mykola Pechenizkiy, Ling Chen. EMNLP Findings 2025 Link
• RuAG: Learned-rule-augmented Generation for Large Language Models. LLM Agents ICLR 25
  Yudi Zhang^*, Pei Xiao^*, Lu Wang, Chaoyun Zhang, Meng Fang, Yali Du, et al. ICLR 2025 Link
• Pillagerbench: Benchmarking LLM-based Agents in Competitive Minecraft Team Environments. LLM Agents IEEE CoG 25 Oral
  Olivier Schipper, Yudi Zhang, Yali Du, Mykola Pechenizkiy, Meng Fang. IEEE Conference on Games (CoG), 2025 Link
• Large Language Models are Neurosymbolic Reasoners. LLM Agents AAAI 24
  Meng Fang^*, Shilong Deng^*, Yudi Zhang^*, Zijing Shi, Ling Chen, Mykola Pechenizkiy, Jun Wang. AAAI 2024 Link
• Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach. Causal RL NeurIPS 23
  Yudi Zhang, Yali Du, Biwei Huang, Ziyan Wang, Jun Wang, Meng Fang, Mykola Pechenizkiy. NeurIPS 2023 Link
• COOM: A Game Benchmark for Continual Reinforcement Learning. Continual RL NeurIPS D&B 23
  Tristan Tomilin, Meng Fang, Yudi Zhang, Mykola Pechenizkiy. NeurIPS 2023 D&B Track Link
• RSPT: Reconstruct Surroundings and Predict Trajectories for Generalizable Active Object Tracking. Embodied AI AAAI 23 Oral
  Fangwei Zhong^*, Xiao Bi^*, Yudi Zhang, Wei Zhang, Yizhou Wang. AAAI 2023 Link

Journals

• Large action models: From inception to implementation. LLM Agents TMLR
  TMLR 2025 Link
• MACCA: Offline Multi-agent Reinforcement Learning with Causal Credit Assignment. Causal RL TMLR
  Ziyan Wang, Yali Du, Yudi Zhang, Meng Fang, Biwei Huang. TMLR 2025 Link