Policy Iteration with Human Feedback: Bringing Post-Training RL to In-context Learning

Minh-Ha Nguyen, Cathy Shyr|August 17, 2026arXiv

Key Takeaway

You can improve a frozen language model's performance on specialized tasks by treating policy refinement as a human-in-the-loop process: have an AI critic identify recurring failures, propose natural-language policy changes, and let domain experts decide what gets deployed.

Summary

This paper presents Policy Iteration with Human Feedback (PIHF), a method that improves a fixed language model's performance on rare-disease diagnosis by iteratively refining its decision-making policy through human expert review.

training alignment applications

Key Terms

policy-iteration in-context-learning human-in-the-loop critic-model