# Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts

arXiv: https://arxiv.org/abs/2510.09388 · HTML: https://mlsanity.com/paper/2510.09388/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 28 of its 37 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 28 of 28)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems](https://mlsanity.com/paper/2402.14008/) (2024)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Process Reinforcement through Implicit Rewards](https://mlsanity.com/paper/2502.01456/) (2025)
- [Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model](https://mlsanity.com/paper/2503.24290/) (2025)
- [Learning to Reason under Off-Policy Guidance](https://mlsanity.com/paper/2504.14945/) (2025)
- [REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization](https://mlsanity.com/paper/2501.03262/) (2025)
- [Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining](https://mlsanity.com/paper/2504.07912/) (2025)
- [Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs](https://mlsanity.com/paper/2402.14740/) (2024)
- [CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models](https://mlsanity.com/paper/2503.22342/) (2025)
- [On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting](https://mlsanity.com/paper/2508.11408/) (2025)
- [Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning](https://mlsanity.com/paper/2504.13818/) (2025)
- [SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning](https://mlsanity.com/paper/2506.19767/) (2025)
- [BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning](https://mlsanity.com/paper/2506.17211/) (2025)
- [DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training](https://mlsanity.com/paper/2504.09710/) (2025)
- [QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation](https://mlsanity.com/paper/2507.13266/) (2025)
- [GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning](https://mlsanity.com/paper/2507.10628/) (2025)

## Built on by (most cited first, 14 of 14)

- [HDPO: Hybrid Distillation Policy Optimization via Privileged Self-Distillation](https://mlsanity.com/paper/2603.23871/) (2026)
- [R3L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification](https://mlsanity.com/paper/2601.03715/) (2026)
- [No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning](https://mlsanity.com/paper/2601.06794/) (2026)
- [KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance](https://mlsanity.com/paper/2604.12627/) (2026)
- [Hindsight Hint Distillation: Scaffolded Reasoning for SWE Agents from CoT-free Answers](https://mlsanity.com/paper/2605.11556/) (2026)
- [LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance](https://mlsanity.com/paper/2605.22567/) (2026)
- [The Model Knows Another Way: Strategy Switching for Effective RLVR Exploration](https://mlsanity.com/paper/2609.33085/) (2026)
- [Context Bootstrapped Reinforcement Learning](https://mlsanity.com/paper/2603.18953/) (2026)
- [Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing](https://mlsanity.com/paper/2604.07747/) (2026)
- [N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization](https://mlsanity.com/paper/2606.10768/) (2026)
- [To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation](https://mlsanity.com/paper/2606.29481/) (2026)
- [AdaKP: Online Adaptive Knowledge-Point Selection for Reasoning-Oriented Reinforcement Learning](https://mlsanity.com/paper/2607.24833/) (2026)
- [Teach to Learn: Hint Annealing for Self-improving LLM Reasoning](https://mlsanity.com/paper/2609.34975/) (2026)
- [Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding](https://mlsanity.com/paper/2610.07342/) (2026)

## Abstract (arXiv)

Reinforcement Learning (RL) has become a key driver for enhancing the long chain-of-thought (CoT) reasoning capabilities of Large Language Models (LLMs). However, prevalent methods like GRPO often fail when task difficulty exceeds model capacity, leading to reward sparsity and inefficient training. Prior work attempts to mitigate this with off-policy data, but such methods often induce severe distributional mismatches that destabilize policy updates. In this work, we identify a core issue underlying these failures, which we term low training affinity, and introduce Affinity, the first quantitative metric for monitoring the compatibility between external guidance and the model's intrinsic policy. To address this, we propose HINT, an adaptive framework designed to enhance reasoning capabilities while explicitly preserving high Affinity. First, instead of revealing partial answers, HINT supplies Meta-Hints, which act as abstract cognitive scaffolding to guide the model in articulating solutions independently. Second, to ensure stability, we integrate Affinity-Aware Policy Optimization (AAPO), which dynamically modulates the learning objective based on the Affinity. Extensive experiments across diverse benchmarks demonstrate that HINT consistently outperforms strong baselines, while exhibiting superior stability and robust generalization to out-of-distribution tasks. Code is available at https://github.com/ViviqwerAsd/HINT.