AI RESEARCH
Convergence and Emergence of In-Context Reinforcement Learning with Chain of Thought
arXiv CS.LG
•
ArXi:2605.07123v1 Announce Type: new In-context reinforcement learning (ICRL) refers to the ability of RL agents to adapt to new tasks at inference time without parameter updates by conditioning on additional context. Recent empirical studies further nstrate that Chain-of-Thought (CoT) generation can amplify this ICRL capability. This paper is the first to provide a theoretical understanding on how CoT interacts with ICRL. We conduct our analysis in a policy evaluation setup with linear Transformer.