About Me
My research interests and work directions focus on RL algorithms and LLM post-training techniques, with a specific emphasis on Search Agent, Tool-Use, Reasoning, and Instruction Following. My expertise spans the full LLM pipeline—from training and inference to evaluation—covering key areas such as RLVR, reward modeling, data synthesis, and multi-domain training. Prior to this, I completed my Ph.D. with a focus on applying deep reinforcement learning (DRL) to cloud environment scheduling challenges, supervised by Prof. Lin Zhang. My doctoral work aimed at utilizing neural network generalization for decision-making to optimize solution flexibility and reduce latency, drawing extensively on MDP modeling, uplift modeling, and online/offline DRL.
Experience
Recent Publications
NIPS 2026
- TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs Co-First Corresponding
- On the Bias of Group-Based Advantage Estimation (Link)
EMNLP 2026
- ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay (Link) Co-First Corresponding
- HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning (Link) Co-First
- MoE Sparsity Begets Monosemanticity: Insights into Understanding and Fine-Tuning Co-First
- When Not to Imitate: Boundary-Aware Skill Memory for Reliable Tool-Use LLM Agents (Link) Corresponding
- Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration
- ToolForge: A Data Synthesis Pipeline for Multi-Hop, Multi-Turn, and Self-Reflective Tool-Use Data
- UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams
ACM MM 2026
- Training Multi-Image Vision Agents via End2End Reinforcement Learning (Link)
KDD 2026
ICML 2026
- ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning (Link) Co-First Corresponding
- Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards (Link)
- SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning (Link)
- GRASP: Graph Reasoning via Agentic Solving and Probing of LLMs
ACL 2026
- AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning (Link)
ICLR 2026
- ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models (Link) Co-First
- LogiConBench: Benchmarking Logical Consistencies of LLMs
- MAD-Logic: Multi-Agent Debate Enhances Symbolic Translation and Reasoning
- SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training (Link)
ICLR 2026 Workshop
- MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL (Link)
→ Full list on Google Scholar