Bowen Li

Robots can now autonomously learn to avoid failures by transforming recovery experiences into abstract planning skills, achieving over 50% better performance on unseen tasks.

Removing gold answer strings from rewritten contexts can cause F1 scores to plummet by up to 64 points, underscoring their critical role in retrieval-augmented QA performance.

LLM agents struggle to consistently reflect human-like psychology, even when provided with extensive personality profiles and autobiographical memories, suggesting current models lack a deeper understanding of human behavior.