Master (incoming) · Beihang University
Undergraduate · Xidian University
Trustworthy LLM Reasoning · Reliable AI Agents · AI for Research · Recursive Self-Improvement
I am an undergraduate student at Xidian University and an incoming master's student at Beihang University, focusing on LLM Agents and Post-training.
My research focuses on understanding when and why LLMs and agents fail, how such failures can be diagnosed from internal representations or execution trajectories, and how these signals can eventually support more reliable and self-improving AI systems.
I am particularly interested in AI for Research, including scientific agents that can understand literature, formulate hypotheses, conduct experiments, interpret evidence, and iteratively refine their research strategies.
-
Trustworthy LLM Reasoning
- Chain-of-Thought faithfulness
- Internal representation dynamics
- Reasoning reliability and failure diagnosis
-
Reliable & Self-Improving Agents
- Agent evaluation and capability boundaries
- Execution trajectory analysis
- Failure attribution and continual adaptation
- Recursive Self-Improvement (RSI)
-
AI for Research
- Scientific agents and AutoResearch
- Research judgment and research taste
- Hypothesis–experiment co-evolution
- Scientific information retrieval
-
SPD-Faith Bench (ACL Findings 2026) Diagnosing and improving Chain-of-Thought faithfulness in multimodal large language models; introduces the training-free SAGE framework. W. Lv, Y. Feng, X. Xia, et al.
-
GeoFaith (arXiv) Learning Faithful Reasoning Processes with Spatio-Temporal Latent Dynamics for Large Language Models. W. Lv, W. Zhao, J. Wang, X. Xia, et al.
-
Act As a Real Researcher (AARRI-Bench) (arXiv) Evaluating frontier LLMs and agentic harnesses on realistic research-intern tasks, with an emphasis on research judgment beyond task execution. J. Wang, W. Lv, et al.*
-
DPDiff-AD (IJCV) Dual prototype-conditioned diffusion for multi-class unsupervised anomaly detection. Y. Feng, Y. Li, W. Lv, et al.
Research Intern · University of Science and Technology of China Advisor: Prof. Xiaobo Xia Sep. 2025 – May 2026 · Hefei, China
Research Intern · Xidian University Advisor: Prof. Bo Chen Dec. 2024 – Jul. 2025 · Xi’an, China
TypeScript · React · Electron · SQLite · LLM Agents
A local-first research-agent workspace for building customizable research tools and making scientific workflows traceable.
- Designed Research Apps to combine Skills, MCP tools, models, and agent backends into customizable research workflows.
- Built an integrated workspace for literature discovery, paper reading, reproduction, data analysis, and writing.
- Developing experiment lineage and evidence provenance to connect research questions, code, data, results, and conclusions.
- Exploring long-term research memory and team collaboration to preserve experience and support shared research projects.
- Finalist (Top 1%) · International Contest in Mathematical Modeling · Feb. 2026
- Excellent Award · HarmonyOS Agent Competition, Huawei × Nanjing University · May 2025
- First Prize · National College Student Mathematics Competition · Dec. 2024
Languages: Python, C/C++, Java, SQL, JavaScript / TypeScript
AI / ML: PyTorch, scikit-learn, Hugging Face Transformers, LLM APIs, RAG, embeddings, multi-agent workflows
Engineering: FastAPI, Flask, React, Git, Docker, Linux, SQLite, PostgreSQL, pandas, NumPy, REST APIs
Open to research collaboration and RA opportunities.



