Guided-RLVR: Guided Exploration in Reinforcement Learning with Verifiable Rewards

arXiv:2610.37041v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has shown strong empirical gains in improving the reasoning ability of large language models (LLMs) on tasks such as mathematics and programming. However, recent studies have shown that RLVR rollouts often collapse onto a narrow set of reasoning trajectories, limiting the explored reasoning space. Motivated by findings that thinking tokens at critical steps serve as critical structural elements in LLM reasoning pathways, we propose Guided-RLVR, a novel approach that augments RLVR with a lightweight controller. The controller strategically injects semantically meaningful steering tokens into the sampling distribution, encouraging the model to approach problems from multiple reasoning perspectives and thereby expanding the exploration space. Experiments on mathematical reasoning and code generation benchmarks show that Guided-RLVR consistently outperforms existing RLVR methods while producing more diverse reasoning trajectories.

Related

• How You Begin is How You Reason: Driving Exploration in RLVR via Prefix-Tuned Priors
• Efficient RLVR Scheduling via Graph-Structured Online Difficulty Estimation
• Diverse Reasoning Paths Matter: Symbolic Equivalence Augmentation for Enhancing RL Exploration
• Quantifying Empirical Compute-Supervision Tradeoffs in RLVR

Source: arXiv cs.AI | 2026-10-28