Prism Process Reward Guided Inference

Optimize multi-step reasoning by treating candidate solutions as particles in a process-reward energy landscape. Use PRM step-level scores to guide stochastic refinement and population resampling, achieving directional error correction without hallucination amplification.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit f9d0c12354

Frequently asked questions

npx get-skill add adu2021/prism-process-reward-guided-inference