rubric-guided-supervision

Tag

Cards List
#rubric-guided-supervision

AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science

Hugging Face Daily Papers ↗ · 2026-10-23 Cached

AdaPRA introduces a persistent coding agent harness with adaptive rubric-guided process supervision that accumulates knowledge across attempts, boosting an 80B Qwen model's leaderboard percentile by 24.5 points on DSPredict-Easy and 14.8 on DSPredict-Hard while reducing process errors in data science agents.

0 favorites 0 likes
← Back to home

Submit Feedback