The work connects internal organization, module-level hallucination mechanisms, and long-horizon metacognitive control into one coherent research program.
Biography
I am a Ph.D. candidate at the Gaoling School of Artificial Intelligence, Renmin University of China, advised by Prof. Jun Xu. My research focuses on trustworthy LLM agents, especially hallucination mechanisms, reasoning and planning, information retrieval, explainability, and legal AI. I use cognitive-neuroscience-inspired task design, behavior analysis, representation analysis, mechanism intervention, and process-level control to study these systems.
I expect to graduate in June 2027 and am seeking research positions. If you are interested in trustworthy LLMs and agents, their synergy with information retrieval, applied mechanistic interpretability, or cognitive-neuroscience-inspired AI, I would welcome the opportunity to discuss.
Impact Snapshot
Representative projects cover retrieval-augmented generation, large reasoning models, personalized LLMs, process rewarding, and deep-search agents.
Selected work received an ICLR Spotlight, won the SIGIR-AP Best Paper Award, and was selected by Paper Digest as Hot Papers at SIGIR and CIKM.
The site links project pages, source artifacts, and a compact full publication list for fast faculty-level evaluation of scope, continuity, and impact.
Research
My research studies large-model agents as complex artificial intelligent systems that perceive context, reason over goals, call tools, use memory, interact with humans and other agents, and act in changing environments. I build cognitive-neuroscience-inspired methods for explaining and controlling these systems: task paradigms reveal behavioral boundaries, representation analysis locates internal structure, mechanism intervention validates causal pathways, and process-level monitoring turns diagnosis into control.
Internal Cognitive Organization
I build NeuroCogMap-style internal cognitive maps that connect sparse features, functional parcels, capability hierarchy, and pathology localization.
Agent Module Mechanisms
I analyze tool evidence use, temporal reasoning dynamics, and personalized-memory drift through ReDeEP, RHD, and FPPS.
Metacognitive Control
I design process reward, hierarchical monitoring, reflection, corrective action, and experience updating through ReARTeR and DS-MCM.
Selected Publications
Representative work with project pages. The complete publication list is maintained separately as a compact text list.
NeuroCogMap Reveals Cognitive Organization of Large Language Models
arXiv 2026 | Lead project | Internal Cognitive Organization
A multi-level map connecting sparse model features, functional parcels, cognitive capabilities, capability hierarchy, and pathology localization.
ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
ICLR 2025 Spotlight | First author | Agent Module Mechanisms
A mechanism-level view of RAG hallucination as imbalance between external-evidence use and parametric-knowledge reliance.
Mechanistic Detection and Mitigation of Hallucination in Large Reasoning Models
ICLR 2026 | First author | Agent Module Mechanisms
A temporal neural-dynamics account of reasoning hallucination in large reasoning models.
When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs
ACL 2026 Findings | First author | Agent Module Mechanisms
A representation-level account of how personalized memory can bend factual behavior.
ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding
SIGIR 2025 | First author | Metacognitive Control
A process-rewarding framework for trustworthy multi-step retrieval-augmented reasoning.
Deep Search with Hierarchical Meta-Cognitive Monitoring Inspired by Cognitive Neuroscience
SIGIR 2026 | First author | Metacognitive Control
A deep-search framework that calibrates reasoning uncertainty against evidence uncertainty and triggers experience-driven correction.
Education
- 08.2022-present Ph.D. candidate, Gaoling School of Artificial Intelligence, Renmin University of China.
- 08.2018-06.2022 Bachelor of Computer Science and Technology, Beijing Jiaotong University (ranked 1st, top 0.4%).
Awards
- The National Scholarship 2024, selected as one of the 100 national representatives of Graduate National Scholarship recipients in China. News
- 2024 China Association for Science and Technology Youth Talent Support Program for Ph.D. Students.
- Renmin University of China Innovative Talent Program.
- SIGIR-AP 2024 Best Paper Award.
- First Prize in the inaugural Artificial Intelligence and Smart Governance Innovation and Entrepreneurship Competition for University Students.
Teaching
- Teaching Assistant, Introduction to Big Data Analytics, Renmin University of China, Fall 2022 and Fall 2023.
- Teaching Assistant, Python, Renmin University of China, Spring 2023.
Experience
- NTU, visiting student, Sep. 2025-Mar. 2026. Advisor: Yang Liu.
- Kuaishou, research intern, Feb. 2022-Jun. 2025. Advisors: Xiaoxue Zang, Kai Zheng, Yang Song.
- CAIL 2022, committee member.
- WWW 2024, 2025, reviewer.
- SIGIR 2024, 2025, program committee member.
- TOIS, reviewer.
- TASLP, reviewer.
- CIKM 2023, 2024, program committee member.
- NeurIPS 2025, reviewer.
- ICLR 2026, reviewer.