DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training

Paper recorded by Signals 4 on 2026-09-03 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-03 on arXiv · recorded by Signals 4 on 2026-09-04

Category: cs.LG · 机器学习 · first seen 2026-09-04

Abstract

Reinforcement Learning from Verifiable Rewards works well when a task has a programmatic checker, but most long-horizon agent domains have none. We work in the outcome-blind setting, where ground-truth success signals are not available. Multi-criteria rubrics are a popular way to supply such a reward; they are scored once per trajectory, but a single scalar is a poor signal across tens of steps. W

Read on arXiv →