Ph.D. Student, University of Science and Technology of China
Advised by Prof. Lan Zhang
I am a Ph.D. student in Computer Science at the University of Science and Technology of China (USTC), advised by Prof. Lan Zhang. I received my B.Sc. in Computer Science from Lanzhou University in 2024.
My research centers on reliable intent realization for agents in the physical world — grounding large language models so they can turn high-level human intent into dependable, verifiable actions in real, physical environments.
IoT-Brain: Grounding LLMs for Semantic-Spatial Sensor Scheduling
ACM MobiCom 2026CCF-Aalso ACM ANAI Workshop @ MobiCom 2025
A verify-before-commit spatial trajectory graph that grounds LLMs in the what-to-sense / when-to-sense decision for large-scale sensor networks.
VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit
Annual Meeting of the Association for Computational Linguistics (ACL) 2026, Main ConferenceCCF-A
A verify-before-commit protocol that defends LLM agents against tool-stream injection while preserving reasoning flexibility.
Re³: Relevance & Recency Retrieval for Mitigating Temporal Hallucination
Annual Meeting of the Association for Computational Linguistics (ACL) 2026, Main ConferenceCCF-A
Balancing relevance and recency for temporal information retrieval to curb temporal hallucination.
Nice Fold or Hero Call: Learning Budget-Efficient Thinking for Adaptive Reasoning
Preprint, arXiv 2026UNDER REVIEW
† Equal contribution.