SOURCE-LINKED INTELLIGENCE

DCRL: Decoupling and Coupling Reinforcement Learning via Policy-Reward Manifold Alignment

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Reinforcement learning (RL) has emerged as a key paradigm for improving the reasoning capabilities of large language models (LLMs). However, existing reward systems, such as rule-based and reward-model-based, often exhibit issues such as unstable optimization and reward hacking. In this work, we revisit the general reasoning of LLMs from a geometric perspective, conceptualizing it as a coupled manifold composed of three interdependent sub-manifolds: logical deduction, evaluation, and representation. Based on this perspective, response generation in RL can be interpreted as a decoupling process

Read original source ↗ Open in workspace

recordType

paper

region

Global