Training Advisors for LLM Agents from Task Outcomes
Large language model agents tackle multi-step tasks by interleaving reasoning and tool calls with observations from the environment. Prior work has shown that natural-language feedback can help these agents revise their decisions during task execution. We introduce Caddie, a method for training critics to provide natur...
Sergei Polezhaev, Barys Liskavets, O. Press et al.
· 0 citations