Resume
Academic Achievements
- Complex Logical Instruction Generation (Preprint)
- Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty (EMNLP 2025, co-first author)
- LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries (Preprint)
- MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs (Preprint)
- IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction (ACL 2025)
- LMR-Bench: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research (EMNLP 2025)
- SafeConv: Explaining and Correcting Conversational Unsafe Behavior (ACL 2023, Oral Presentation)