RL Post-Training

RL: Reinforcement Learning

Overview

Reinforcement learning post-training studies how to adapt pretrained language, multimodal, and action models using rewards from people, verifiers, evaluators, or environments. Common approaches include reinforcement learning from human feedback and verifiable rewards, with policy-gradient methods such as PPO and GRPO, alongside preference optimization, self-distillation, offline replay, and adaptive curricula. Work also develops critics and step-level credit assignment for long-horizon agents, as well as systems that make rollout generation and training more efficient. A central tension is improving task performance while preserving exploration, concise outputs, prior capabilities, and reliable generalization when feedback is sparse or imperfect.

Latest papers

464 papers42 papers in the last four weeks, down 53% on the four weeks before. 0.3% of all new papers.

Oct 21, 2025

Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting

Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting. In this paper, toward identifying guidelines for mitigating this phenomenon, we systematically compare the forgetting patterns of two widely adopted post-training methods: supervised fine-tuning (SFT) and reinforcement learning (RL). Our experiments reveal a consistent trend across LM families (Llama, Qwen) and tasks (instruction following, general knowledge, and arithmetic reasoning): RL leads to less forgetting than SFT while achieving comparable or higher target task performance. To investigate the cause for this difference, we consider a simplified setting in which the LM is modeled as a mixture of two distributions, one corresponding to prior knowledge and the other to the target task. We identify that the mode-seeking nature of RL, which stems from its use of on-policy data, enables keeping prior knowledge intact when learning the target task. We then verify this insight by demonstrating that the use on-policy data underlies the robustness of RL to forgetting in practical settings, as opposed to other algorithmic choices such as the KL regularization or advantage estimation. Lastly, as a practical implication, our results highlight the potential of mitigating forgetting using approximately on-policy data, which can be substantially more efficient to obtain than fully on-policy data.
Oct 13, 2025

Representation-Based Exploration for Language Models: From Test-Time to Post-Training

Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model. In this paper, we investigate the value of deliberate exploration -- explicitly incentivizing the model to discover novel and diverse behaviors -- and aim to understand how the knowledge in pre-trained models can guide this search. Our main finding is that exploration with a simple, principled, representation-based bonus derived from the pre-trained language model's hidden states significantly improves diversity and pass@k rates -- both for post-training, and in a novel inference-time scaling setting we introduce. For inference-time, exploration with representation-based diversity improves efficiency, consistently improving pass@k rates across a variety of models and reasoning tasks. For example, for Qwen-2.5-14b-Instruct we obtain over 50% improvement in verifier efficiency on almost all tasks. For post-training, we show that integrating this exploration strategy into an RL pipeline improves reasoning performance over that of the initial model and over standard RL post-training. For example, on AIME 2024, our post-trained Qwen-2.5-7b-Instruct's pass@80 matches the pass@256 of GRPO on the same model, demonstrating a 3x improvement in test-time sample efficiency. Overall, our findings suggest that deliberate exploration -- with the right notion of diversity -- is a practical path toward discovery of new behaviors beyond sharpening.
Oct 13, 2025

Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers

Reinforcement learning (RL) has emerged as a crucial approach for enhancing the capabilities of large language models. However, in Mixture-of-Experts (MoE) models, the routing mechanism often introduces instability, even leading to catastrophic RL training collapse. We analyze the training-inference consistency of MoE models and identify a notable discrepancy in routing behaviors between the two phases. Moreover, even under identical conditions, the routing framework can yield divergent expert selections across repeated forward passes. To address this foundational inconsistency, we propose Rollout Routing Replay (R3), a method that records routing distributions from the inference engine and replays them during training. R3 significantly reduces training-inference policy KL divergence and mitigates extreme discrepancies without compromising training speed. Extensive experiments on various settings confirm that R3 succeeds in stabilizing RL training, preventing collapse and outperforming methods such as GSPO and TIS. We believe this work can offer a new solution for stabilizing RL in MoE models.
Oct 10, 2025

BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards

Today's generative models thrive with large amounts of supervised data and informative reward functions characterizing the quality of the generation. They work under the assumptions that the supervised data provides knowledge to pre-train the model, and the reward function provides dense information about how to further improve the generation quality and correctness. However, in the hardest instances of important problems, two problems arise: (1) the base generative model attains a near-zero reward signal, and (2) calls to the reward oracle are expensive. This setting poses a fundamentally different learning challenge than standard reward-based post-training. To address this, we propose BaNEL (Bayesian Negative Evidence Learning), an algorithm that post-trains the model using failed attempts only, while minimizing the number of reward evaluations (NREs). Our method is based on the idea that the problem of learning regularities underlying failures can be cast as another, in-loop generative modeling problem. We then leverage this model to assess whether new data resembles previously seen failures and steer the generation away from them. We show that BaNEL can improve model performance without observing a single successful sample on several sparse-reward tasks, outperforming existing novelty-bonus approaches by up to several orders of magnitude in success rate, while using fewer reward evaluations.
Oct 10, 2025

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

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.
Oct 10, 2025

TripScore: Aligning LLMs for Real-World Travel Planning via Expert-Calibrated Reward

In our deployed travel-planning service, most users give minimal inputs or free-form requests rather than the structured constraint checklists assumed by existing benchmarks. We therefore present TripScore, a behavior-grounded benchmark and evaluation framework built from real user logs and calibrated against 1,468 pairwise judgments by 203 travel experts. TripScore couples a hierarchical feasibility gate (format and commonsense) with a unified, point-wise reward that aggregates soft quality and preference fulfillment. Using TripScore as both evaluator and reward signal, we benchmark direct prompting, test-time compute, neuro-symbolic solvers, code agents, and fine-tuning. We find that reinforcement learning fine-tuning (e.g., GRPO) provides consistent gains over other approaches under the same base model and practical latency.
Oct 9, 2025

SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training

Reinforcement learning (RL) is a key paradigm for post-training large language models (LLMs), but the widely used Group Relative Policy Optimization (GRPO) often suffers from entropy collapse: exploration quickly disappears, policies converge prematurely, and sample diversity declines, ultimately harming training effectiveness. Existing remedies, including entropy bonuses and clip-based methods, rarely keep entropy within a stable exploration regime and often introduce oscillatory entropy or reward degradation. In this work, we identify a previously overlooked asymmetry in entropy dynamics: under high-temperature sampling, positive and negative samples have opposite effects on policy entropy. Specifically, high-temperature positive samples promote entropy growth, whereas negative samples suppress it. We provide a qualitative theoretical explanation for this phenomenon: when entropy decreases during policy updates, its derivative with respect to temperature is strictly positive under positive sample updates, indicating that high-temperature positive samples can counteract entropy decay, thereby slowing entropy collapse and potentially reversing it. Motivated by this insight, we propose SCOPE-RL, a stable entropy control framework through a regularization term constructed from temperature-adaptive positive samples. Extensive experiments show that SCOPE-RL consistently outperforms strong RL baselines on both Pass@1 and Pass@k. Our results provide evidence that escaping entropy collapse can improve reasoning performance, while our quantitative empirical analysis further reveals a non-monotonic entropy-performance relationship, with an optimal level of exploration for RL post-training in reasoning LLMs. Our code is available at https://github.com/597358816/SCOPE-RL.
Oct 2, 2025

Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression

Recent thinking models are capable of solving complex reasoning tasks by scaling test-time compute, but this scaling should be allocated in line with task difficulty. On one hand, short reasoning (underthinking) leads to errors on harder problems that require extended reasoning steps; but, excessively long reasoning (overthinking) can be token-inefficient by generating unnecessary steps even after reaching a correct intermediate solution. We refer to this as under-adaptivity, where the model fails to modulate its response length appropriately given problems of varying difficulty. To address under-adaptivity and strike a balance between under- and overthinking, we propose TRAAC (Think Right with Adaptive, Attentive Compression), an online post-training RL method that leverages the model's self-attention to identify key steps and prune redundant ones. TRAAC also estimates difficulty and incorporates it into training rewards, thereby learning to allocate a reasoning budget commensurate with example difficulty. Across a variety of tasks (AIME, AMC, GPQA-D, BBEH), TRAAC (Qwen3-4B) achieves an average absolute accuracy gain of 8.4% with a relative reduction in reasoning length of 36.8% compared to the base model, and a 7.9% accuracy gain paired with a 29.4% length drop compared to the best RL baseline. TRAAC generalizes well, with accuracy and efficiency gains on out-of-distribution non-math datasets like GPQA-D, BBEH, and OptimalThinkingBench. Our analysis shows that TRAAC learns to adjust its thinking budget based on difficulty and that a combination of task-difficulty calibration and attention-based compression yields gains across diverse tasks.
Oct 1, 2025

Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers

Reinforcement Learning with Verifiable Rewards (RLVR) replaces costly human labeling with automated verifiers. To reduce verifier hacking, many RLVR systems binarize rewards to {0,1}\{0,1\}, but imperfect verifiers inevitably introduce false negatives (rejecting correct answers) and false positives (accepting incorrect ones). We formalize verifier unreliability as a stochastic reward channel with asymmetric noise rates ρ0ρ_0 and ρ1ρ_1 -- the FP rate and the FN rate, respectively. From this abstraction we derive two lightweight corrections: (i) a backward correction that yields an unbiased surrogate reward and thus an unbiased policy-gradient estimator in expectation, and (ii) a forward correction that reweights score-function terms so the expected update aligns with the clean gradient direction and requires only the FN rate. We implement both as lightweight hooks in a group relative policy optimization pipeline, both corrections improve RLVR for math reasoning under synthetic and real verifier noise, with the forward variant being more stable under heavier noise. Finally, an appeals mechanism with a lightweight LLM verifier estimates the FN rate online and further improves performance.
Aug 27, 2025

ReST-RL: Reinforcing LLM Reasoning through Unified Self-Training and Value-Guided Search

With respect to improving the reasoning accuracy of LLMs, the representative reinforcement learning (RL) method - Group Relative Policy Optimization (GRPO) - has achieved critical success, yet it still suffers from the issue of insignificant reward signals. This paper introduces ReST-RL, a unified Reinforced Self-Training (ReST) policy-value framework that reconnects policy optimization and value-guided search to improve LLM reasoning ability. Firstly, ReST-GRPO adopts an optimized ReST-style algorithm to reshape the policy-induced trajectory distribution by increasing the reward variance of GRPO sampling and exposing the policy to more informative partial states, thereby improving training efficiency and effectiveness. Then, we further introduce a decoding optimization method, VM-MCTS, which trains a Value Model (VM) from self-collected Monte-Carlo Tree Search (MCTS) targets and deploys it through an adapted MCTS algorithm to provide precise process signals and verification scores, further enhancing reasoning accuracy. These two stages are internally dependent - ReST-GRPO yields higher quality trajectories for value learning with VM-MCTS, which in turn enables more effective inference-time search. We validate our framework on multiple coding benchmarks (e.g., APPS, BigCodeBench, and HumanEval), where it significantly outperforms other reinforcement training baselines (naive GRPO, DAPO, and ReST-DPO), as well as decoding and verification baselines (e.g., PRM-BoN and ORM-MCTS), indicating its power to strengthen LLM reasoning capability. Moreover, we further evaluate ReST-RL on out-of-domain math and science reasoning tasks, where it achieves improved performance without target-domain tuning and favorable end-to-end efficiency trade-offs, providing preliminary transfer evidence beyond our primary coding domain.
Jul 29, 2025

Post-Training Large Language Models via Reinforcement Learning from Self-Feedback

Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. Recent research suggests that Chain-of-Thought (CoT) reasoning paths are inherent in pre-trained LLMs and can be elicited by simply altering the decoding process, where the presence of a CoT path correlates with higher answer confidence. Building on these insights, we present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that utilises the model's intrinsic confidence as a self-generated reward. By generating multiple CoT decoding beams from a frozen LLM, we compute the confidence of each final answer span and rank the resulting traces accordingly to create synthetic preferences. These preferences are subsequently utilised to fine-tune the policy through standard preference optimisation, requiring no human labels, gold answers, or externally curated rewards. RLSF simultaneously (i) refines the model's probability estimates--restoring well-behaved calibration--and (ii) strengthens step-by-step reasoning, yielding improved performance on arithmetic reasoning and multiple-choice question answering. By converting a model's own uncertainty into structured self-feedback, RLSF affirms reinforcement learning on intrinsic model behaviour as a principled and data-efficient component of the LLM post-training pipeline. Our results demonstrate that leveraging these inherent reasoning capabilities provides a robust path for enhancing model reliability without manual prompt engineering or external supervision.
Jul 2, 2025

AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training

Reinforcement learning (RL) has become a pivotal technology in the post-training phase of large language models (LLMs). Traditional task-collocated RL frameworks suffer from significant scalability bottlenecks, while task-separated RL frameworks face challenges in managing complex dataflows and resolving resource idling. Furthermore, most existing frameworks are tightly coupled with LLM training or inference engines, making them difficult to support custom-designed engines. To address these challenges, we propose AsyncFlow, an asynchronous streaming RL framework tailored for efficient post-training. Specifically, we introduce a distributed data storage and transfer module that provides panoramic data management and fine-grained scheduling capabilities in a fully streamed manner. This architecture inherently enables automated pipeline overlapping among RL tasks and dynamic load-balancing. Moreover, we propose an asynchronous producer-consumer workflow, which is engineered to minimize computational idleness by strategically deferring the parameter update process within staleness thresholds. Finally, the core capabilities of AsyncFlow are architecturally decoupled from underlying training and inference engines and encapsulated by service-oriented user interfaces, offering a modular and customizable user experience. Extensive experiments demonstrate an average throughput of 1.59x compared to the state-of-the-art baseline. The architecture presented in this work provides actionable insights for designing next-generation RL training systems.
Apr 28, 2025

GVPO: Group Variance Policy Optimization for Large Language Model Post-Training

Post-training plays a crucial role in refining and aligning large language models to meet specific tasks and human preferences. While recent advancements in post-training techniques, such as Group Relative Policy Optimization (GRPO), leverage increased sampling with relative reward scoring to achieve superior performance, these methods often suffer from training instability that limits their practical adoption. As a next step, we present Group Variance Policy Optimization (GVPO). GVPO incorporates the analytical solution to KL-constrained reward maximization directly into its gradient weights, ensuring alignment with the optimal policy. The method provides intuitive physical interpretations: its gradient mirrors the mean squared error between the central distance of implicit rewards and that of actual rewards. GVPO offers two key advantages: (1) it guarantees a unique optimal solution, exactly the KL-constrained reward maximization objective, (2) it supports flexible sampling distributions that avoids on-policy and importance sampling limitations. By unifying theoretical guarantees with practical adaptability, GVPO establishes a new paradigm for reliable and versatile LLM post-training.
Apr 16, 2025

Reinforcement Learning from Human Feedback

Reinforcement learning from human feedback (RLHF) has become a crucial tool to build the latest machine learning systems at scale. The field grew around the core methods of RLHF into today's broader suite of post-training techniques. In this book, we give a comprehensive introduction to the core methods for post-training models for people with some level of quantitative background, organized around the canonical RLHF recipe. The book starts with what RLHF does and why it was created, with seminal technical milestones in its young history and a primer on reinforcement learning context needed to understand the book. The core of the book details every optimization stage in using RLHF, from starting with instruction tuning to training a reward model and finally all of rejection sampling, reinforcement learning, on-policy distillation, and direct alignment algorithms. The book also discusses broader topics, such as the origins of RLHF -- both in recent literature and in a convergence of disparate fields of science in economics, philosophy, and optimal control. The book concludes with advanced topics -- understudied or emerging research questions in synthetic data, tool-use, character training, and evaluation -- and open questions for the field. The book is released with a variety of companion resources, including a codebase, a library to compare model completions from within post-training stages, and an educational course, to be a one-stop shop for learning all foundational concepts for post-training language models.