arXiv (All)
open access
Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR
Reinforcement learning with verifiable rewards (RLVR) is a scalable paradigm for improving the mathematical reasoning of large language models, but it is fundamentally limited by exploration: the policy can only improve on trajectories it has already sampled. Sampling more rollouts alleviates this a
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Enhancing Multimodal RLVR with Pairwise Token Contrast and Adaptive Trajectory Confidence#1357326
- Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning#984141
- Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners#1357045
- DE-Venus: A Data-Efficient RLVR Framework for Large Language Models#925667
- Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models#1357104
Record · ID 1199839
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive