Pengrui Han

The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs

FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data

Where LLM Agents Fail And How They can Learn From Failures

AcademicEval: Live Long-Context LLM Benchmark

Thought-Retriever: Don’t Just Retrieve Raw Data, Retrieve Thoughts