2 papers
cs.CL2026
Not All Skills Help: Measuring and Repairing Agent Knowledge
Yixuan Wang, Yiyang Zhou, Yiming Liang +4
LLM agents can improve without weight updates by accumulating natural-language skills from experience, but current systems entrust every decision about which skills to keep and how…
cs.CL2025
Logical forms complement probability in understanding language model (and human) performance
Yixuan Wang, Freda Shi
With the increasing interest in using large language models (LLMs) for planning in natural language, understanding their behaviors becomes an important research question. This work…