# RLPR: Extrapolating RLVR to General Domains without Verifiers

arXiv: https://arxiv.org/abs/2506.18254 · HTML: https://mlsanity.com/paper/2506.18254/

## Key facts

- Cited by 85 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 23 Jun 2025.

## Placed in

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

## Builds on (most cited first, 20 of 20)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [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)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild](https://mlsanity.com/paper/2503.18892/) (2025)
- [Process Reinforcement through Implicit Rewards](https://mlsanity.com/paper/2502.01456/) (2025)
- [The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models](https://mlsanity.com/paper/2505.22617/) (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 without External Rewards](https://mlsanity.com/paper/2505.19590/) (2025)
- [The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning](https://mlsanity.com/paper/2505.15134/) (2025)
- [RM-R1: Reward Modeling as Reasoning](https://mlsanity.com/paper/2505.02387/) (2025)
- [Generative Reward Models](https://mlsanity.com/paper/2410.12832/) (2024)
- [General-Reasoner: Advancing LLM Reasoning Across All Domains](https://mlsanity.com/paper/2505.14652/) (2025)
- [A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility](https://mlsanity.com/paper/2504.07086/) (2025)
- [Reinforcing General Reasoning without Verifiers](https://mlsanity.com/paper/2505.21493/) (2025)
- [X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains](https://mlsanity.com/paper/2505.03981/) (2025)

## Built on by (most cited first, 30 of 85)

- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback](https://mlsanity.com/paper/2510.16888/) (2025)
- [Self-Questioning Language Models](https://mlsanity.com/paper/2508.03682/) (2025)
- [CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning](https://mlsanity.com/paper/2509.22647/) (2025)
- [RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents](https://mlsanity.com/paper/2507.03112/) (2025)
- [Learning to Orchestrate Agents in Natural Language with the Conductor](https://mlsanity.com/paper/2512.04388/) (2025)
- [Learning to Self-Verify Makes Language Models Better Reasoners](https://mlsanity.com/paper/2602.07594/) (2026)
- [Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning](https://mlsanity.com/paper/2601.07408/) (2026)
- [Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision](https://mlsanity.com/paper/2509.14234/) (2025)
- [Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2507.17512/) (2025)
- [Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain](https://mlsanity.com/paper/2603.02218/) (2026)
- [G-Zero: Self-Play for Open-Ended Generation from Zero Data](https://mlsanity.com/paper/2605.09959/) (2026)
- [Environment Scaling for Interactive Agentic Experience Collection: A Survey](https://mlsanity.com/paper/2511.09586/) (2025)
- [Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning](https://mlsanity.com/paper/2512.15146/) (2025)
- [Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting](https://mlsanity.com/paper/2510.08696/) (2025)
- [PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization](https://mlsanity.com/paper/2603.26535/) (2026)
- [LaSeR: Reinforcement Learning with Last-Token Self-Rewarding](https://mlsanity.com/paper/2510.14943/) (2025)
- [Bridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMs](https://mlsanity.com/paper/2603.25077/) (2026)
- [Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning](https://mlsanity.com/paper/2605.02913/) (2026)
- [Variational Reasoning for Language Models](https://mlsanity.com/paper/2509.22637/) (2025)
- [RAVR: Reference-Answer-guided Variational Reasoning for Large Language Models](https://mlsanity.com/paper/2510.25206/) (2025)
- [Learning Robust Reasoning through Guided Adversarial Self-Play](https://mlsanity.com/paper/2602.00173/) (2026)
- [CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning](https://mlsanity.com/paper/2606.09393/) (2026)
- [Reinforcement Learning for Tool-Integrated Interleaved Thinking towards Cross-Domain Generalization](https://mlsanity.com/paper/2510.11184/) (2025)
- [Likelihood-Based Reward Designs for General LLM Reasoning](https://mlsanity.com/paper/2602.03979/) (2026)
- [StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models](https://mlsanity.com/paper/2508.05383/) (2025)
- [From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation](https://mlsanity.com/paper/2601.18533/) (2026)
- [SERL: Self-Examining Reinforcement Learning on Open-Domain](https://mlsanity.com/paper/2511.07922/) (2025)
- [Masked-and-Reordered Self-Supervision for Reinforcement Learning from Verifiable Rewards](https://mlsanity.com/paper/2511.17473/) (2025)
- [TRINITY: An Evolved LLM Coordinator](https://mlsanity.com/paper/2512.04695/) (2025)

## Abstract (arXiv)

Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates promising potential in advancing the reasoning capabilities of LLMs. However, its success remains largely confined to mathematical and code domains. This primary limitation stems from the heavy reliance on domain-specific verifiers, which results in prohibitive complexity and limited scalability. To address the challenge, our key observation is that LLM's intrinsic probability of generating a correct free-form answer directly indicates its own evaluation of the reasoning reward (i.e., how well the reasoning process leads to the correct answer). Building on this insight, we propose RLPR, a simple verifier-free framework that extrapolates RLVR to broader general domains. RLPR uses the LLM's own token probability scores for reference answers as the reward signal and maximizes the expected reward during training. We find that addressing the high variance of this noisy probability reward is crucial to make it work, and propose prob-to-reward and stabilizing methods to ensure a precise and stable reward from LLM intrinsic probabilities. Comprehensive experiments in four general-domain benchmarks and three mathematical benchmarks show that RLPR consistently improves reasoning capabilities in both areas for Gemma, Llama, and Qwen based models. Notably, RLPR outperforms concurrent VeriFree by 7.6 points on TheoremQA and 7.5 points on Minerva, and even surpasses strong verifier-model-dependent approaches General-Reasoner by 1.6 average points across seven benchmarks.