# SuperRL: Reinforcement Learning with Supervision to Boost Language Model Reasoning

arXiv: https://arxiv.org/abs/2506.01096 · HTML: https://mlsanity.com/paper/2506.01096/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 5 of its 34 references that are in the map.
- First posted on arXiv 1 Jun 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)
- Knowledge distillation / [On-policy and self-distillation for LLMs](https://mlsanity.com/distill/on-policy-and-self-distillation-for-llms/)

## Builds on (most cited first, 5 of 5)

- [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)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters](https://mlsanity.com/paper/2212.10001/) (2022)
- [GraphReason: Enhancing Reasoning Capabilities of Large Language Models through A Graph-Based Verification Approach](https://mlsanity.com/paper/2308.09267/) (2023)

## Built on by (most cited first, 18 of 18)

- [RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization](https://mlsanity.com/paper/2508.00222/) (2025)
- [Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle](https://mlsanity.com/paper/2509.16679/) (2025)
- [Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners](https://mlsanity.com/paper/2510.04454/) (2025)
- [Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2509.21882/) (2025)
- [SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning](https://mlsanity.com/paper/2604.23747/) (2026)
- [EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning](https://mlsanity.com/paper/2508.07809/) (2025)
- [AgenticRed: Evolving Agentic Systems for Red-Teaming](https://mlsanity.com/paper/2601.13518/) (2026)
- [From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning](https://mlsanity.com/paper/2606.18089/) (2026)
- [When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff](https://mlsanity.com/paper/2606.09932/) (2026)
- [SD-E2: Semantic Exploration for Reasoning Under Token Budgets](https://mlsanity.com/paper/2601.17982/) (2026)
- [Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning](https://mlsanity.com/paper/2604.08926/) (2026)
- [BRIDGE: Bridging Reasoning In Distillation Gap Elimination via Structure-Aware Masking](https://mlsanity.com/paper/2602.17686/) (2026)
- [Improving LLM Code Reasoning via Semantic Equivalence Self-Play with Formal Verification](https://mlsanity.com/paper/2604.17010/) (2026)
- [Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance](https://mlsanity.com/paper/2605.15012/) (2026)
- [AIR: Adaptive Interleaved Reasoning with Code in MLLMs](https://mlsanity.com/paper/2606.23678/) (2026)
- [MedRouter: Demystifying Knowledge Differences Across Medical LLMs for Routing-Based Reasoning](https://mlsanity.com/paper/2609.33119/) (2026)
- [Balancing Reference Guidance and Free Generation in Trajectory Rollouts for Reasoning RL](https://mlsanity.com/paper/2610.11128/) (2026)
- [PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation](https://mlsanity.com/paper/2610.11167/) (2026)

## Abstract (arXiv)

Large language models are increasingly used for complex reasoning tasks where high-quality offline data such as expert-annotated solutions and distilled reasoning traces are often available. However, in environments with sparse rewards, reinforcement learning struggles to sample successful trajectories, leading to inefficient learning. At the same time, these offline trajectories that represent correct reasoning paths are not utilized by standard on-policy reinforcement learning methods. We introduce SuperRL, a unified training framework that adaptively alternates between RL and SFT. Whenever every rollout for a given instance receives zero reward, indicating the absence of a learning signal, SuperRL falls back to SFT on the curated offline data. Extensive experiments across diverse reasoning benchmarks show that SuperRL surpasses vanilla RL by delivering higher sample efficiency, stronger generalization, and improved robustness under sparse rewards.