collaborators

7 papers

cs.AI2026

EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning

Yufei He, Juncheng Liu, Zhiyuan Hu +9

Prevailing medical AI operates on an unrealistic ''one-shot'' model, diagnosing from a complete patient file. However, real-world diagnosis is an iterative inquiry where Clinicians…

cs.AI2025

Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning

Zifeng Ding, Shenyang Huang, Zeyu Cao +11

Forecasting future links is a central task in temporal graph (TG) reasoning, requiring models to leverage historical interactions to predict upcoming ones. Traditional neural appro…

cs.CR2025

Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods

Yulin Chen, Haoran Li, Yuan Sui +2

With the development of technology, large language models (LLMs) have dominated the downstream natural language processing (NLP) tasks. However, because of the LLMs' instruction-fo…

cs.LG2025

Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance

Yufei He, Ruoyu Li, Alex Chen +8

Large language model (LLM) agents often struggle in environments where rules and required domain knowledge frequently change, such as regulatory compliance and user risk screening.…

cs.AI2025

Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?

Yufei He, Yuexin Li, Jiaying Wu +3

As large language models (LLMs) continue to evolve, ensuring their alignment with human goals and values remains a pressing challenge. A key concern is \textit{instrumental converg…

cs.CR2025

Can Indirect Prompt Injection Attacks Be Detected and Removed?

Yulin Chen, Haoran Li, Yuan Sui +4

Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions, b…