# Reinforce-Ada: An Adaptive Sampling Framework under Non-linear RL Objectives

arXiv: https://arxiv.org/abs/2510.04996 · HTML: https://mlsanity.com/paper/2510.04996/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 35 of its 40 references that are in the map.
- First posted on arXiv 6 Oct 2025.

## Placed in

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

## Builds on (most cited first, 30 of 35)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [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)
- [OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems](https://mlsanity.com/paper/2402.14008/) (2024)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment](https://mlsanity.com/paper/2304.06767/) (2023)
- [The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models](https://mlsanity.com/paper/2505.22617/) (2025)
- [Introduction to Multi-Armed Bandits](https://mlsanity.com/paper/1904.07272/) (2019)
- [Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint](https://mlsanity.com/paper/2312.11456/) (2023)
- [Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models](https://mlsanity.com/paper/2312.06585/) (2023)
- [MathArena: Evaluating LLMs on Uncontaminated Math Competitions](https://mlsanity.com/paper/2505.23281/) (2025)
- [RLHF Workflow: From Reward Modeling to Online RLHF](https://mlsanity.com/paper/2405.07863/) (2024)
- [The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning](https://mlsanity.com/paper/2506.01347/) (2025)
- [GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning](https://mlsanity.com/paper/2504.02546/) (2025)
- [SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning](https://mlsanity.com/paper/2509.02479/) (2025)
- [A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce](https://mlsanity.com/paper/2504.11343/) (2025)
- [Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts](https://mlsanity.com/paper/2506.02177/) (2025)
- [Efficient Reinforcement Finetuning via Adaptive Curriculum Learning](https://mlsanity.com/paper/2504.05520/) (2025)
- [Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning](https://mlsanity.com/paper/2504.13818/) (2025)
- [TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling](https://mlsanity.com/paper/2508.17445/) (2025)
- [Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?](https://mlsanity.com/paper/2507.04632/) (2025)
- [No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping](https://mlsanity.com/paper/2509.21880/) (2025)
- [NGRPO: Negative-enhanced Group Relative Policy Optimization](https://mlsanity.com/paper/2509.18851/) (2025)
- [SPEED-RL: Faster Training of Reasoning Models via Online Curriculum Learning](https://mlsanity.com/paper/2506.09016/) (2025)
- [Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training](https://mlsanity.com/paper/2509.03403/) (2025)
- [The Crucial Role of Samplers in Online Direct Preference Optimization](https://mlsanity.com/paper/2409.19605/) (2024)

## Built on by (most cited first, 25 of 25)

- [Maximum Likelihood Reinforcement Learning](https://mlsanity.com/paper/2602.02710/) (2026)
- [Self-Hinting Language Models Enhance Reinforcement Learning](https://mlsanity.com/paper/2602.03143/) (2026)
- [WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks](https://mlsanity.com/paper/2601.02439/) (2026)
- [Future-KL Regularized GRPO: Process-Level Credit Assignment from f-Divergence Regularization](https://mlsanity.com/paper/2601.10201/) (2026)
- [Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition](https://mlsanity.com/paper/2602.04486/) (2026)
- [Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning](https://mlsanity.com/paper/2602.14868/) (2026)
- [DyJR: Preserving Diversity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay](https://mlsanity.com/paper/2603.16157/) (2026)
- [Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum](https://mlsanity.com/paper/2603.18325/) (2026)
- [EchoRL: Reinforcement Learning via Rollout Echoing](https://mlsanity.com/paper/2605.31228/) (2026)
- [Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning](https://mlsanity.com/paper/2608.05080/) (2026)
- [Tail-Likelihood Reinforcement Learning](https://mlsanity.com/paper/2609.02987/) (2026)
- [Rollout-Level Advantage-Prioritized Experience Replay for GRPO](https://mlsanity.com/paper/2606.04560/) (2026)
- [Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration](https://mlsanity.com/paper/2605.05566/) (2026)
- [It Takes 8 Tokens: Weak-to-Strong Off-Policy RL via Auxiliary Branches](https://mlsanity.com/paper/2607.16205/) (2026)
- [Learning to Solve Hard Problems in RL for LLMs by Never Giving Up](https://mlsanity.com/paper/2609.13443/) (2026)
- [Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification](https://mlsanity.com/paper/2601.21244/) (2026)
- [CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning](https://mlsanity.com/paper/2605.24331/) (2026)
- [AdaKP: Online Adaptive Knowledge-Point Selection for Reasoning-Oriented Reinforcement Learning](https://mlsanity.com/paper/2607.24833/) (2026)
- [Ignorance or Incompetence? Constructing Knowledge-Gated, Verifiable Tasks for LLM Agents](https://mlsanity.com/paper/2608.30322/) (2026)
- [Spurious Advantage Hidden in GRPO](https://mlsanity.com/paper/2609.04063/) (2026)
- [Video-HopChain: Multi-Hop Questions and Confidence-Gated Exploration for Video Reasoning Models](https://mlsanity.com/paper/2609.25773/) (2026)
- [Frontier Learning: Training LLM Reasoners at the Edge of Capability](https://mlsanity.com/paper/2609.35426/) (2026)
- [SERA: Scale-Equalized Rollout Allocation for Maximum Likelihood Reinforcement Learning](https://mlsanity.com/paper/2609.36552/) (2026)
- [Towards Better Training Signal: Advantage Clipped Policy Optimization](https://mlsanity.com/paper/2609.36816/) (2026)
- [Variance-Optimal State Resampling for Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2610.15888/) (2026)

## Abstract (arXiv)

Reinforcement learning (RL) for large language model reasoning is frequently hindered by signal loss, a phenomenon where standard uniform sampling with small group sizes fails to uncover informative learning signals for difficult prompts. We demonstrate that this collapse is a statistical artifact of undersampling rather than an inherent model limitation. To address this systematically, we introduce a theoretical framework based on optimizing a non-linear RL objective (e.g., log-likelihood). We show that this objective naturally induces a weighted gradient estimator that prioritizes difficult prompts, which can be robustly realized through adaptive sampling. Guided by this framework, we propose Reinforce-Ada, a family of algorithms that dynamically allocates inference budgets based on prompt difficulty, effectively scaling up RL compute to where it is needed most. Unlike passive filtering methods that discard low-signal prompts, Reinforce-Ada actively invests compute to recover them. We introduce two efficient realizations: an estimation-based approach and a model-free sequential sampling approach. Extensive experiments across multiple benchmarks show that Reinforce-Ada significantly outperforms uniform baselines like GRPO, recovering lost signals and accelerating convergence by up to 2× while maintaining the same total inference budget. Code is available at https://github.com/RLHFlow/Reinforce-Ada.