Critical-State RL: Diagnosing Trainable States for Multi-Turn Tool Use

Paper recorded by Signals 4 on 2026-09-21 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-21 on arXiv · recorded by Signals 4 on 2026-09-22

Category: cs.LG · 机器学习 · first seen 2026-09-22

Abstract

Multi-turn tool-use failures can hinge on a single model call, yet reward variation alone does not reveal which call would benefit from training. When rewards depend on later interactions, their variation can reflect downstream randomness rather than differences between the current actions. We introduce Critical-State RL to identify trainable states in multi-turn interactions. Given task-defined c

Read on arXiv →