# The Model Knows Another Way: Strategy Switching for Effective RLVR Exploration

arXiv: https://arxiv.org/abs/2609.33085 · HTML: https://mlsanity.com/paper/2609.33085/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 24 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Builds on (most cited first, 22 of 22)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models](https://mlsanity.com/paper/2410.07985/) (2024)
- [Learning to Reason under Off-Policy Guidance](https://mlsanity.com/paper/2504.14945/) (2025)
- [The Invisible Leash: Why RLVR May or May Not Escape Its Origin](https://mlsanity.com/paper/2507.14843/) (2025)
- [BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning](https://mlsanity.com/paper/2506.17211/) (2025)
- [Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning](https://mlsanity.com/paper/2510.19807/) (2025)
- [Adaptive Guidance Accelerates Reinforcement Learning of Reasoning Models](https://mlsanity.com/paper/2506.13923/) (2025)
- [Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts](https://mlsanity.com/paper/2510.09388/) (2025)
- [Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs](https://mlsanity.com/paper/2601.08763/) (2026)
- [Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information](https://mlsanity.com/paper/2607.19313/) (2026)
- [Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR](https://mlsanity.com/paper/2605.15726/) (2026)
- [SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs](https://mlsanity.com/paper/2605.18864/) (2026)
- [How You Begin is How You Reason: Driving Exploration in RLVR via Prefix-Tuned Priors](https://mlsanity.com/paper/2605.08817/) (2026)
- [Select and Improve: Understanding the Mechanics of Post-Training for Reasoning](https://mlsanity.com/paper/2606.13125/) (2026)

## Built on by (most cited first, 1 of 1)

- [What Will Post-Training Fix? Per-Problem Gains Are Shared Across Independent RL Runs, and Existing Checkpoints Predict Them Better Than A Priori Signals](https://mlsanity.com/paper/2610.04978/) (2026)

## Abstract (arXiv)

Reinforcement learning with verifiable rewards (RLVR) is often limited by insufficient exploration: difficult problems can yield uniformly incorrect rollout groups and therefore little learning signal. We show that such failures need not reflect missing capability. Instead, finite sampling often concentrates on a problem-specific dominant reasoning strategy while leaving alternative strategies already supported by the model unexplored. Moreover, the accessibility of these strategies evolves during RL: some are internalized into autonomous behavior, while others become difficult to elicit before being absorbed. Motivated by these observations, we introduce Problem--Strategy Rollout Allocation (PSRA), which treats unguided and strategy-conditioned prompts as competing exploration arms and uses Bayesian sequential allocation to direct a fixed rollout budget toward arms most likely to yield informative, non-saturated groups. A preservation objective keeps useful strategy-conditioned routes accessible while successful guided behaviors are transferred to the unguided policy. Across Qwen2.5 models from 1.5B to 7B and two RL training corpora, PSRA consistently improves reasoning performance, reduces dead saturation, strengthens out-of-distribution transfer, and maintains larger gains under increased inference budgets.