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 natural-language analysis and advice as agents work through a task. Unlike…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.