Shichen Fan

LLM agents fabricate product attributes in over half of their listings, but a novel reputation-penalty mechanism can significantly curb this behavior without needing access to the truth.

Forget slow, expensive neural verifiers: this work shows a simple corpus lookup can provide faster, better rewards for RL fine-tuning of QA models.

LLM agents can now autonomously generate complex skills with multi-file dependencies, rivaling human-authored skills, thanks to a co-evolutionary verification process that doesn't need ground truth labels.