The belief-action gap in language model agents
Language model (LM) agents can fail for different reasons, requiring different explanations and interventions. We study how state beliefs, action values, and action preferences interact as LM agents reason and commit to decisions in text-rendered grid worlds. We estimate task-relevant beliefs using report-based and rep...
A. S. Okcu, Wei-Sheng Wang, Tong-Meng Xie et al.
· 0 citations