Collective Dynamics of Self-Reinforcement: How Cross-Task Coupling Drives Policy Collapse in Unsupervised RLVR

Paper recorded by Signals 4 on 2026-10-27 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-27 on arXiv · recorded by Signals 4 on 2026-10-28

Category: cs.LG · 机器学习 · first seen 2026-10-28

Abstract

Label-free reinforcement learning with verifiable rewards (RLVR) rewards a language model for agreeing with its own majority vote. It improves reasoning at first but eventually collapses: the self-assessed reward goes to one while accuracy falls, often until the model gives the same answer to every problem. The collapse appears only when training uses many problems. We explain this dataset-size de

Read on arXiv →