SOURCE-LINKED INTELLIGENCE

DE-Venus: A Data-Efficient RLVR Framework for Large Language Models

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Reinforcement learning with verifiable rewards (RLVR) improves large language model reasoning, but its practical scaling is constrained by expensive on-policy rollouts and the cost of obtaining reliable targets at scale. Existing methods address sample selection, incomplete supervision, or noisy labels separately, often entangling supervision logic with distributed training and hindering controlled comparison and reuse. We present DE-Venus, a unified framework for data-efficient RLVR that treats supervision as evolving state across data preparation and policy optimization. It organizes this li

Read original source ↗ Open in workspace

recordType

paper

region

Global