RL for Generative Models

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

12 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 94

Jun 22, 2026cs.CV

READ More than What You See: Reinforcement Learning for Accurate and Coherent Audio Description Generations

Audio Description aims to generate concise narrations of essential visual content in audio-visual media for blind and low-vision audiences. Existing methods either rely on prompting off-the-shelf multimodal models, which often mismatch AD style, or partially optimize training-based systems with next-token prediction, which under-explores model capacity and biases generation toward generic expressions. We present READ, the first reinforcement-learning (RL) framework for training-based AD generation. READ formulates AD as sequence-level optimization with reference-matching, length, and format rewards, and further introduces a dedicated coherence reward under context-aware supervision to promote narratively coherent descriptions. Experiments on MAD-Eval, CMD-AD, and TV-AD show that READ substantially outperforms prior methods across diverse evaluation metrics. Our results highlight RL as a promising paradigm for accurate and coherent AD generation. Our codes, models, and benchmark results will be publicly available.

Bo Fang, Xinyao Zhang, Yuxin Song +3

City University of Hong Kong · Baidu Inc · Tsinghua University

RL for Generative Models

Jun 19, 2026cs.CL

Precision Recall Controllable Radiology Report Generation via Hybrid Natural Language and Clinical Reward Learning

Automated radiology report generation (RRG) has gained increasing attention because it can reduce the heavy workload of clinical report writing. However, most existing methods mainly optimize for natural language generation (NLG) metrics that focus on language fluency, while providing little control over clinically important factors such as precision and recall. As consequence, generated reports may be fluent but not well aligned with different clinical needs. To address this challenge, we propose a reinforcement learning framework for precision recall controllable RRG, where a control parameter explicitly adjusts the trade-off between clinical precision and recall during inference. This design allows the model to flexibly generate reports according to different clinical requirements. To ensure clinical correctness, we introduce a clinical reward into the training objective, which helps improve clinical efficacy (CE) beyond standard language-based optimization. In addition, we apply a group-relative training strategy that normalizes rewards within each training group, reducing reward variance and improving training stability. Extensive experiments on the MIMIC-CXR dataset show that our method consistently outperforms state-of-the-art approaches in both NLG and CE evaluation metrics, while providing reliable control over the CE precision recall trade-off.

Ling Chen, Ruinan Jin, Jun Luo +6

The Ohio State University, Columbus, OH 43221, USA · University Medical Center Regensburg, Regensburg, Germany

Radiology Report Generation Controllable Text Generation RL for Generative Models

Jun 19, 2026cs.RO

ReFPO: Reflow Regularization for Flow Matching Policy Gradients

We present Reflow-regularized Flow Matching Policy Gradients (ReFPO), a simple online RL method that adds explicit Reflow regularization to FPO for efficient flow-based control. We uncover a key structural property: the gradient updates in Flow Matching Policy Gradients (FPO) can be interpreted as an implicit advantage-weighted Reflow process, providing a new geometric perspective on flow-based policy gradients. Building on this insight, ReFPO introduces an explicit geometric regularizer that can be implemented with a single line of code change without incurring additional computational overhead or auxiliary distillation stages. By synergizing advantage-guided updates with path rectification, our method reduces CFM proxy-ratio spikes, stabilizes PPO-style training, and enables high-fidelity one-step inference that often matches or exceeds multi-step performance. We experimentally demonstrate that ReFPO improves average performance and discretization robustness across GridWorld, MuJoCo Playground, and high-dimensional Humanoid Control tasks, providing a scalable and stable approach for generative policies in complex physical simulations.

Ge Wang, Yibo Peng, Fan Feng +10

Ising AI · CUHK-Shenzhen · FNii-Shenzhen

Policy Gradient Reinforcement Learning RL for Generative Models

Jun 17, 2026cs.LG

The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL

Score- and flow-matching models often rely on preference-based reinforcement learning for two purposes: aligning with subjective preferences and, surprisingly, recovering properties such as visual realism and coherent object structure that matching-based training is intended to learn from the data itself. We argue that this reflects a structural mismatch. Matching losses measure

\ell_2

regression error on the velocity or score field under training-time marginals, a proxy poorly aligned with the visual and semantic properties that determine sample quality at inference. Given a reward aligned with these properties, RL sidesteps the mismatch by evaluating the model on its own samples and following the reward landscape directly. The challenge is to obtain such a reward without relying on human preferences, which are expensive and conflate data realism with annotator inclinations. We propose Discriminator-Guided RL (DRL). DRL trains a discriminator to separate data from base-model samples in a pretrained representation space and uses its logit as the reward in KL-regularized RL. The pretrained space restricts the discriminator to perceptually meaningful directions, and the logit estimates the log-likelihood ratio between data and model, which is the optimal reward for targeting the data distribution. Across SiT, JiT, REPA, and RAE, DRL reduces guidance-free FID (e.g.,

9.38 \to 2.62

on SiT) and semantic-space FD (e.g.,

88.2 \to 19.3

on DINOv3 for SiT), with consistent gains across all backbones, and improves human-preference rewards without training on them. It also yields a better Pareto frontier between preference reward and image fidelity under subsequent preference-based post-training, increasing alignment while reducing low-level artifacts such as oversaturation and excessive brightness.

Nicolas Beltran-Velez, Felix Friedrich, Zhang Xiaofeng +4

FAIR at Meta · Columbia University · Mila – Québec AI Institute +3

Flow Matching Reinforcement Learning RL for Image Generation RL for Generative Models

Jun 15, 2026cs.RO

Steering Generative Reinforcement Learning into Stable Robotic Controller

Diffusion and flow-based generative policies provide a powerful policy class for reinforcement learning by inducing rich stochastic exploration through iterative action generation. However, the stochasticity of diffusion policies is not suitable for stable and precise control in high-dimensional robotic systems, where small action variations can accumulate into inconsistent motion and reduced robustness. To address this issue, we propose SteerGenPO, a latent-space reinforcement learning framework that steers a trained generative policy into a robust deterministic robotic controller. The key idea is to replace stochastic latent sampling of the trained generative policy with a learned latent actor that predicts a state-dependent latent input for the generative policies. This separates exploration and control: stochastic generative sampling provides diverse action proposals during policy learning, while deterministic latent steering provides stable and adaptive control at deployment. We evaluate SteerGenPO on six Isaac Lab benchmarks and a Unitree G1 locomotion task. The results show SteerGenPO improves over both classical RL and generative RL baselines, while its deterministic latent steering produces more stable inference-time behaviors and more reliable command responses.

Yixuan Wang, Shutong Ding, Ke Hu +3

1ShanghaiTech University

Latent Action Learning Robotic RL RL for Generative Models Robust RL

Jun 14, 2026cs.CL

Interactor: Agentic RL oriented Iterative Creation for Ad Description Generation in Sponsored Search

This paper focuses on automatically generating informative ad descriptions in sponsored search. Unlike ad titles which are usually optimized to attract user click feedbacks, ad descriptions have a longer text span and possess the potential of incorporating world knowledge to address user search intents while presenting the fine-grained selling points of the ads. We propose Interactor, a multi-turn iterative creation framework optimized with agentic RL for ad description generation. The generation model acts as a policy that interacts with a customized environment consisting of multiple generative reward models. Given initial generations by the policy, the customized GenRMs evaluate multi-dimensional qualities including knowledge capacity and landing page consistency, providing both binary signals and reasoning feedbacks. The policy then iteratively refines the descriptions based on such feedbacks to ensure continuous improvement. Experiments on industrial datasets show that the Interactor framework significantly outperforms state-of-the-art approaches in generating knowledge-rich and faithful ad descriptions. Since May 2026, it has been deployed online in a leading search ads system, contributing to both ad revenue and user experience.

Penghui Wei, Jiayu Wu, Chao Ye +3

Search Ads, Baidu Inc.

Online Advertising RL for Generative Models Text Generation

Jun 11, 2026cs.CL

Can Post-Training Turn LLMs into Good Medical Coders? An Empirical Study of Generative ICD Coding

Automated International Classification of Diseases (ICD) coding is a core medical-coding task for billing, epidemiology, and clinical decision support. Generative large language models (LLMs) are often reported as weak medical coders, but this finding mainly comes from inference-time settings such as prompting, retrieval, reranking, or tool use, leaving the role of task-specific post-training underexplored. We present a controlled empirical study of post-training for generative ICD coding, comparing discriminative baselines with LLM coders across prompting, supervised fine-tuning, and reinforcement learning under a common protocol and metric set. To our knowledge, this is the first study to evaluate RL-based post-training for generative LLM coders in ICD coding. We further introduce PHI, a diagnostic curriculum that extends GRPO to refine missed-code cases. Our results show that prompting-only evaluation substantially underestimates the potential of LLMs for ICD coding. SFT provides the main capability jump, GRPO further improves code-set prediction beyond SFT, and PHI provides targeted gains on macro-level performance. These findings suggest that the main bottleneck is not the generative formulation alone, but how the model is adapted and optimized for full-taxonomy recall. We release our code, data splits, and checkpoints at https://github.com/AlexandreWANG915/LLM4ICD.

Ziqing Wang, Weihao Li, Shijie Chen +2

Northwestern University

Supervised Fine-Tuning Automated Medical Coding RL for Generative Models LLM Post-Training Medical LLMs

Jun 10, 2026cs.LG

Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier

The limiting resource for training agents via reinforcement learning (RL) is increasingly frontier task supply: valid, solvable tasks just difficult enough to train the current model. As reasoning and agentic models improve, fixed task distributions saturate, while naive synthetic generation yields tasks that are trivial, impossible, or ill-posed. Training a task generator with RL to optimize validity and learnability can address this bottleneck, but direct optimization requires repeated solver rollouts per candidate. For software-engineering (SWE) tasks, a single rollout can take tens of minutes; solver-in-the-loop generator training is intractable. We introduce PROPEL, a solver-amortized framework for training task generators at the targeted solve rate. PROPEL trains a lightweight activation probe on a one-time labeled corpus of generated tasks and solver outcomes. The probe predicts target-solver pass rate from a frozen generator reference model and serves as a proxy for solve rate during generator optimization, reducing generator evaluation to a single forward pass. Across math, code, and software-engineering at multiple model scales, PROPEL shifts generation toward the targeted solve rate: for coding, tasks generated at the learnable frontier increase from

10.1\% \rightarrow 20.0\%

for a Qwen2.5-3B-Instruct solver and from

5.3\% \rightarrow 12.6\%

for a Qwen2.5-7B-Instruct solver. For SWE, PROPEL increases the share of generations at the targeted solve rate from

9.8\% \rightarrow 19.6\%

for Qwen3.5-27B on repositories not seen during training of probe and generator.

Lorenz Wolf, Connor Watts, Roger Creus Castanyer +4

Vmax · Goodfire

Reinforcement Learning Synthetic Benchmark Generation RL for Generative Models

Jun 9, 2026cs.LG

Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning

Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control. While they are known to scale stably in the supervised imitation learning setting, incorporating them into reinforcement learning (RL) pipelines for policy improvement has proven more difficult. It often requires specialized training objectives or backpropagating through denoising processes, which cause well-known issues with stability and affect scalability. In this paper we study the question of whether simple policy improvement schemes at test time alone, leaving stable supervised policy training intact, can be a competitive alternative which sidesteps these issues. To this end, we propose QGF (Q-Guided Flow), an RL algorithm that performs policy optimization entirely at test time. QGF works by pre-training both a reference flow policy (via a standard behavioral cloning objective) and a value function critic and, at test time, using the value gradient to guide the reference policy to generate higher-value actions without any additional policy learning. Empirically, QGF outperforms prior test-time RL methods on single-task and goal-conditioned offline RL benchmarks with high-dimensional action spaces, and is competitive with state-of-the-art training-time algorithms while being much cheaper to run. Moreover, it exhibits favorable scaling with model size by avoiding the instability of actor-critic training, offering a practical and effective alternative RL algorithm with expressive policies.

Zhiyuan Zhou, Andy Peng, Charles Xu +4

UC Berkeley · Physical Intelligence

Policy Optimization Offline RL RL for Generative Models

Jun 9, 2026cs.LG

Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models

Recent work has demonstrated that online reinforcement learning (RL) can substantially improve the quality and alignment of flow matching models for image and video generation. Methods such as Flow-GRPO and CPS cast the denoising process as a Markov Decision Process and apply PPO-style ratio clipping to enforce a trust region. However, we argue that ratio clipping is structurally ill-suited for flow models: the probability ratio between new and old policies is a noisy, single-sample estimate of the true policy divergence, leading to over-constraining in some regions of the trajectory and under-constraining in others. We propose Flow-DPPO (Flow Divergence Proximal Policy Optimization), which replaces ratio clipping with a divergence proximal constraint. A key observation is that the per-step policy in flow models is Gaussian, enabling exact and cheap computation of the KL divergence between old and new policies. Flow-DPPO employs an asymmetric divergence mask that blocks gradient updates only when they simultaneously move away from the trusted region and violate the divergence threshold. Experiments show that Flow-DPPO achieves higher rewards with better KL-proximal efficiency, alleviates catastrophic forgetting, promotes balanced multi-objective optimization, and enables stable multi-epoch training where ratio clipping degrades. Code and models are available at https://github.com/Tencent-Hunyuan/UniRL/tree/main/FlowDPPO.

Bowen Ping, Xiangxin Zhou, Penghui Qi +3

Xi’an Jiaotong University · Tencent Hunyuan · National University of Singapore

RL for Video Generation RL for Image Generation Proximal Policy Optimization Flow-Based Generative Modeling RL for Generative Models

Jun 5, 2026cs.LG

Generative Modeling of Discrete Latent Structures via Dynamic Policy Gradients

Many scientific problems require inferring unobserved mechanistic latent states from indirect observations. While classical approaches, including expectation maximization, do not scale to combinatorially large spaces, deep learning approaches such as variational autoencoders typically form artificial latent states rather than reconstructing the mechanistic ground-truth states. Here, we introduce GReinSS, a policy learning framework that uses dynamically rescaled rewards to learn latent state distributions that maximize the observed data likelihood. We show that GReinSS accurately reconstructs simulated latent sets and latent graphs, outperforming alternative policy learning and generative modeling baselines. Additionally, GReinSS reconstructs isoforms from real short-read RNA sequencing data that better match isoforms detected by orthogonal long-read sequencing than the standard RSEM algorithm. Overall, GReinSS is a principled and practically effective approach for generative modeling and inference of combinatorial latent states from indirect observations.

Stefan Ivanovic, Ge Liu, Mohammed El-Kebir

Siebel School of Computing and Data Science, University of Illinois at Urbana-Champaign, IL 61801, USA · Cancer Center at Illinois, University of Illinois Urbana-Champaign, IL 61801, USA

Latent Variable Models Policy Gradient Methods RL for Generative Models

Jun 5, 2026cs.LG

GenPO++: Generative Policy Optimization with Jacobian-free Likelihood Ratios

Generative policies provide expressive and multimodal action distributions, making them attractive for reinforcement learning (RL) in complex continuous-control tasks. Among them, flow-based policies are especially appealing because they generate actions through deterministic transport maps. However, applying such generative policies to likelihood-based on-policy learning remains limited by the difficulty of evaluating the probability of executed actions. Existing flow RL methods either replace the true action-density ratio with approximate surrogates, which can introduce biased updates, or recover exact likelihoods through dummy-action augmentation, which enlarges the policy space and increases computation. In this work, we propose GenPO++, a reversible generative policy optimization framework that uses history states as auxiliary memory in a high-order reversible ODE solver, yielding exact inversion without changing the original action dimension. The resulting generative policy map has a log-determinant determined only by fixed solver coefficients, enabling exact and Jacobian-free likelihood-ratio computation. This design preserves the expressiveness of generative flow policies while avoiding both action ratio bias and dummy-action overhead. We evaluate GenPO++ on large-scale simulated control, fine-tuning, and real-world robotic manipulation tasks, where it achieves competitive or superior performance over state-of-the-art on-policy RL methods, while improving training stability and computational efficiency.

Ke Hu, Shutong Ding, Panxin Tao +2

ShanghaiTech University

RL Control Policy Gradient Methods Flow-Based Generative Modeling RL for Generative Models

Jun 5, 2026cs.CV

AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO

Group Relative Policy Optimization (GRPO) has demonstrated remarkable success in aligning text-to-image (T2I) flow models with human preferences. However, we have identified that the learning loop of current flow-based GRPO is fundamentally decoupled from the learner's current capability, suffering from critical blind spots at both prompt selection and advantage estimation: (i) Existing methods sample prompts randomly, overlooking the substantial impact of data selection on reinforcement learning (RL) efficacy--a factor proven crucial in GRPO for large language models; (ii) They evaluate sample quality solely relying on intra-group statistics, lacking a global perspective to accurately measure true policy improvement. To address these issues, we propose Adaptive GRPO (AdaGRPO), a novel capability-aware RL algorithm tailored for flow models. Specifically, AdaGRPO consists of two principal components: (i) Online Curriculum Filtering Strategy: Dynamically tracks the model's proficiency and adaptively selects prompts that best match its current learning boundary; (ii) Cross-Level Advantage Fusion: Synergistically integrates fine-grained intra-group advantages with macro-level global advantages, providing a comprehensive and unbiased policy evaluation. As a lightweight, plug-and-play module, AdaGRPO can be seamlessly integrated with existing frameworks such as Flow-GRPO, DanceGRPO, and Flow-CPS. Extensive experiments demonstrate that AdaGRPO consistently drives performance gains while significantly stabilizes GRPO training for flow models.

Jiazi Bu, Pengyang Ling, Yujie Zhou +8

1Shanghai Jiao Tong University · 2S-Lab, Nanyang Technological University · 3Shanghai AI Laboratory +7

T2I Generation Group Relative Policy Optimization RL for Image Generation Curriculum Learning RL for Generative Models

Jun 4, 2026cs.RO

Vault: One-Step Latent Generation with Positive-Anchored Rewards for Autonomous Driving

End-to-end autonomous driving must balance multimodal maneuver generation against real-time inference constraints. Diffusion planners capture diverse behaviors, but their iterative denoising incurs considerable inference cost in safety-critical deployment, while one-step alternatives still imitate only the single expert demonstration, so neither family certifies both the diversity and the quality of its outputs. To address this, we propose Vault, a framework that couples one-step latent generation with sample-based reinforcement learning guidance. Built on a V-JEPA 2.1 visual representation pretrained on the full NAVSIM training imagery, Vault generates trajectory candidates in a single forward pass by drifting in a VAE latent space. During training, a reward-gated positive pool collects the maximum-scoring trajectories that the model itself discovers under the official evaluator and anchors the drift targets to these certified samples. This closes a reinforcement-learning loop purely through sample-based target construction, without policy gradients, learned reward models, or extra interaction: the generator imitates the frontier of its own certified successes, so quality and multimodality improve together under a single fixed sampling configuration. A learned scorer that predicts the official score and its sub-metrics then selects the executed trajectory, and all training-only modules are discarded at inference. On the NAVSIM benchmarks, Vault achieves state-of-the-art performance at real-time inference cost, reaching 94.6 PDMS on v1 and 91.2 EPDMS on v2.

Yining Xing, Zehong Ke, Zhiyuan Liu +1

End-to-End Autonomous Driving One-Step Generative Modeling RL for Generative Models Autonomous Driving Planning

Jun 4, 2026cs.LG

OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation

Policy-gradient methods usually optimize expected return, but many real world applications care about distributional properties of returns: tail risk, outlier robustness, or best-of-K discovery. We introduce OrderGrad, a family of likelihood-ratio and reparameterization gradient estimators for order-statistic objectives. OrderGrad optimizes finite-sample L-statistics, i.e., weighted averages of sorted rewards or costs, recovering objectives such as VaR, CVaR, trimmed means, medians, and top-m/best-of-K criteria by changing only the rank weights. For any fixed sample size and rank-weight vector, OrderGrad provides an unbiased gradient estimator for the corresponding order-statistic objective. The method is implemented as a simple reward transformation that can then be used in an otherwise standard policy-gradient or reparameterized update. We study the resulting estimator's variance behavior and evaluate it on tasks where mean optimization is mismatched to the deployment objective, including LLM math post-training and other tasks. OrderGrad provides a unified, plug-and-play route to risk-averse, robust, and exploratory learning. Code: https://github.com/paavo5/ordergrad

Paavo Parmas, Yongmin Kim, Kohsei Matsutani +5

The University of Tokyo

Stochastic Optimization Risk-Sensitive RL Policy Gradient Methods RL for Generative Models Policy Learning

Jun 1, 2026cs.CV

MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching

Recent breakthroughs in instruction-based image editing have captured significant attention, as models are now capable of handling real-world editing demands with the practicality required by everyday users. However, editing models trained primarily for single-turn edits often break down in multi-turn editing--the natural interactive setting where a user iteratively refines an image based on the model's own previous outputs. This failure stems from the all-or-nothing requirement, where a single failed turn compromises the entire sequence, and error propagation, where exposure bias leads to compounding editing errors. To address these challenges, we introduce MT-EditFlow, a flow-matching reinforcement learning framework designed to optimize reward signals for sequential image editing. MT-EditFlow integrates a multi-turn perspective with a multi-reward formulation to provide a unified structure applicable to both GRPO and NFT-based reinforcement learning methods. We systematically analyze and optimize the reward signal by investigating effective scoring strategies for turn-level aggregation, VLM reasoning modes to trade off reward bias and variance, and advantage fusion levels to prevent reward hacking. Our findings reveal that broadcasting the aggregated advantage across the entire editing trajectory effectively bridges the gap between local planning and global multi-turn task success. Extensive experiments demonstrate that MT-EditFlow significantly improves performance across diverse base models. Notably, it boosts FLUX.1-Kontext-dev by 6.85 points in turn-3 overall performance, surpassing state-of-the-art open-source models such as Qwen-Image-Edit. By maintaining high marginal success rates and reducing exposure bias, MT-EditFlow provides a foundation for more reliable and natural human-AI collaboration in visual content creation.

Jiahui Huang, Yasi Zhang, Tianyu Chen +6

Apple · University of California, Los Angeles · University of Texas at Austin +1

Multimodal Reward Modeling RL for Generative Models Diffusion-Based Image Editing Image Editing RL for Image Editing

Jun 1, 2026cs.CV

Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity Decomposition

Post-training via Group Relative Policy Optimization (GRPO) has emerged as a powerful paradigm for aligning flow-based generative models with human preferences. However, the iterative denoising nature of flow models incurs substantial costs when generating group rollouts for policy-gradient updates, compelling existing methods to train with extremely few denoising steps. This temporal sparsity severely restricts preference optimization: reward feedback can only reach a handful of stages per trajectory, leaving the vast majority of intermediate denoising steps without direct supervision and thus compromising alignment granularity. To address this, we propose Pave-GRPO, which reformulates the GRPO objective through Principled average velocity decomposition. Rather than generating expensive high-step rollouts, we maintain efficient few-step group sampling but decompose each coarse transition into an equivalent ensemble of finer sub-trajectories spanning multiple intermediate timesteps. This propagates reward feedback to a denser set of temporal stages for more comprehensive preference alignment without additional generation cost. This design offers two benefits: (i) zero-cost horizon expansion: through the direct reuse of piece-wise group samples and their associated rewards, Pave-GRPO significantly broadens the effective optimization scope under fixed sampling budgets; and (ii) comprehensive temporal supervision: by equivalently decomposing an instantaneous velocity target into a multi-timestep ensemble, it distributes reward signals across more intermediate stages of the denoising process, enabling finer-grained and more thorough preference optimization. Extensive experiments validate that Pave-GRPO effectively advances preference alignment across different reward settings, offering comprehensive performance enhancement.

Pengyang Ling, Jiazi Bu, Yujie Zhou +6

University of Science and Technology of China, China · Shanghai Jiao Tong University, China · Fudan University, China +3

Diffusion Model Alignment Group Relative Policy Optimization Temporal Credit Assignment RL for Generative Models Preference-Based RL

May 27, 2026cs.LG

AtomComposer: Discovering Chemical Space from First Principles with Reinforcement Learning

Discovering novel stable molecules without training data remains a grand scientific challenge. Current molecular generative models are trained on large, pre-curated datasets, which introduce biases and limit exploration of novel chemistry. In contrast, we propose a new paradigm: autonomous, generalized agents capable of mapping vast, unknown chemical spaces without any pretraining. For the first time, we present AtomComposer, a self-guided agent that autonomously constructs valid 3D isomers under stoichiometric constraints and is trained exclusively online using reinforcement learning. Unlike existing approaches that generally overfit to a specific chemical formula, we establish a multi-composition training scheme that enables a broad generalization across diverse chemistry, guided by energy- and validity-based rewards. Our agent can discover up to an order of magnitude more valid isomers on unseen test formulas than existing single-composition reinforcement-learning baselines trained with per-step energy rewards. These results fulfill the promise of online reinforcement learning as a powerful paradigm for scalable, from-scratch exploration of chemical configuration space.

Bjarke Hastrup, Francois Cornet, Tejs Vegge +1

Dept. of Energy Conversion and Storage, Technical University of Denmark, Denmark · Dept. of Applied Mathematics and Computer Science, Technical University of Denmark, Denmark · Pioneer Center for Accelerating P2X Materials Discovery (CAPeX), Kgs. Lyngby, Denmark

AI Agents for Scientific Discovery 3D Molecular Generation Molecular Generation RL for Generative Models

May 26, 2026cs.CL

Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation

Reinforcement learning in open-ended long-form generation is challenging because reliable reference answers and automatic metrics are often unavailable. Existing rubric-based methods typically rely on pointwise LLM-as-a-judge scoring, but absolute scores are difficult to calibrate across complex responses, may provide weak discrimination among same-query rollouts, and can become saturated during optimization. We propose Tournament-GRPO, a group-wise reward framework that converts rubric-guided LLM judgments into relative rewards through repeated multi-round tournaments among same-query rollouts. Tournament-GRPO compares candidates within groups, accumulates tournament outcomes, and normalizes them into group-wise rewards for GRPO training. Experiments on Deep Research Bench show that Tournament-GRPO consistently outperforms existing reward-design baselines, achieving a 4.52-point overall-score improvement over the strongest baseline. Further analyses show that tournament rewards provide a favorable effectiveness--efficiency trade-off and that tournament design affects training dynamics. These results suggest that rubric-guided tournament comparison provides an effective reward signal for reinforcement learning in open-ended long-form generation.

Zixuan Yang, Yiqun Chen, Wei Yang +7

Renmin University of China · University of Southern California · Zhejiang University +1

Open-Ended Generation Reward Modeling LLM-as-a-Judge Long-Form Document Generation Rubric-Based RL RL for Generative Models+4

May 25, 2026cs.LG

AdvantageFlow: Regularized Advantage-Weighted RL in Flow Models

We present AdvantageFlow, a forward-process reinforcement learning (RL) algorithm for rectified flow models. The algorithm minimizes an advantage-weighted prediction loss, which maximizes reward, regularized by the rollout policy, which convexifies the objective and makes its optimization stable. Our objective can be viewed as fitting a local reward-improving target distribution. The rollout regularization arises as a variance reduction step. We evaluate AdvantageFlow empirically on text-to-image generation with Stable Diffusion 3.5 Medium and FLUX.1, and compare it to both forward- and reverse-process RL algorithms.

Branislav Kveton, Anup Rao, Subhojyoti Mukherjee +2

Adobe Research

Rectified Flow RL for Image Generation Flow-Based Generative Modeling RL for Generative Models

May 25, 2026cs.CL

GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generation

Generating structured, editable diagrams remains a significant challenge for contemporary large language models, despite their proficiency in general-purpose vector code generation. The primary difficulty lies in the structural fragility of the output; minor errors such as misaligned connector endpoints, text labels overlapping borders, or complex layouts drifting beyond the canvas boundaries render the resulting SVG files functionally unusable for professional applications. To address these issues, we introduce GeoSVG-RL, a specialized reinforcement learning framework designed for layout-constrained text-to-SVG generation. Unlike standard training objectives that rely solely on maximizing token-level likelihood, our approach optimizes the policy against explicit, executable geometric feedback. The model first produces a structured layout plan that serves as a geometric contract for the subsequent generation of the SVG code. This code is then rendered through a browser-backed verifier, enabling the calculation of fine-grained rewards across six critical dimensions: rendering validity, canvas fitting, precise anchor placement, text containment, graph consistency, and code cleanliness. We utilize Group Relative Policy Optimization (GRPO) to refine the model, sampling multiple candidates per prompt to facilitate updates based on relative quality. Starting from a supervised warm-start phase on synthetic data, GeoSVG-RL achieves substantial gains in structural reliability, particularly in arrow-anchor accuracy and text-in-box rates. Quantitative evaluations demonstrate that our method consistently outperforms current state-of-the-art systems in local geometric precision and the preservation of graph connectivity, providing a robust pathway toward automated yet reliable technical illustration.

Sifan Li, Yujun Cai, Hongkai Chen +1

University of California, Merced · The University of Queensland · vivo Mobile Communication Co., Ltd.

RL for Generative Models Conditional Generation

May 22, 2026cs.CV

Geo-Align: Video Generation Alignment via Metric Geometry Reward

Camera-controlled video generation has achieved remarkable progress in recent years. However, existing video-to-video re-rendering methods primarily rely on Supervised Fine-Tuning using synthetic datasets. At present, there is an extreme scarcity of synchronized, multi-view real-world video data. Consequently, the prevailing paradigm often exhibits limited generalization when processing out-of-distribution real-world videos, with models struggling to accurately adhere to physical scales and camera trajectories. To bridge this gap, we propose Geo-Align, the first Reinforcement Learning framework specifically designed for camera-controlled video re-rendering. Built upon a pretrained model, we optimize the model through a scale-aware perceptual reward mechanism. Specifically, we introduce a metric 3D estimator to extract precise camera trajectories from generated videos, explicitly penalizing deviations in rotation and translation. Furthermore, we meticulously designed a data pipeline strategy based on real-world conditioning videos and target camera trajectories derived from synthetic data, eliminating the reliance on paired data. Extensive experiments demonstrate that Geo-Align consistently outperforms existing supervised learning baselines in both precise camera controllability and visual fidelity, indicating the effectiveness of our method.

Zizun Li, Haoyu Guo, Runzhe Teng +2

1USTC · 2Shanghai AI Lab · 3ZJU

Camera-Controlled Video Generation Reinforcement Learning RL for Video Generation RL for Generative Models

May 22, 2026cs.LG

Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models

Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying online RL to flow matching is turning the deterministic sampling trajectory into a stochastic policy, typically by replacing the reverse-time Ordinary Differential Equation (ODE) with a Stochastic Differential Equation (SDE). The stochastic sampler, controlling the exploration behavior and denoising dynamics, is thus part of the policy, and its design can significantly affect the reward optimization performance. We break down the sampler design into two interdependent components: choosing the right amount of stochastic exploration, and discretizing the resulting SDE faithfully at the small step counts used in RL. To address the first component, we analyze the inherent tension between exploration and stability in denoising and derive an SDE schedule that balances the two. Turning to the discretization challenge, we use a toy example to show that existing samplers can deviate from the flow-matching process, either by introducing excessive discretization noise or by relying on heuristic rules that do not guarantee convergence to the data distribution. To address these issues, we propose Precise, a new stochastic sampler that balances effective exploration with stability. Crucially, Precise keeps the denoising trajectory SDE-consistent through a novel approximation that freezes the clean-latent posterior mean, resolving the excess noise issue in standard samplers. Extensive experiments demonstrate that this formulation leads to significantly faster and more stable reward optimization via reinforcement learning, achieving state-of-the-art alignment scores (e.g., PickScore, HPSv2.1) while requiring 13.1-53.2% less wall-clock training time to match the best in-domain performance of prior samplers.

Jade Zou, Tao Huang, Weijie Kong +7

Peking University · Tencent Hunyuan

Diffusion Model Alignment Flow Matching Stochastic Differential Equations Diffusion Sampling RL for Generative Models

May 22, 2026cs.LG

Reinforcement Learning for Graph Generation under a Hard Assortativity Constraint

Generating graph ensembles with precisely controlled structural properties is central to investigating how network structure shapes function. Canonical ensembles impose constraints only in expectation (soft constraints), letting individual realizations fluctuate around the target, whereas enforcing hard constraints with prescribed precision in every realization remains challenging beyond fixing the degree sequence. Here we show that a reinforcement learning framework can drive a graph through degree-preserving rewirings to satisfy a prescribed assortativity, which characterizes the degree--degree correlation of adjacent nodes. By replacing the entropically dominated Metropolis--Hastings random walk with directed transport, the learned policy reduces generation cost by at least an order of magnitude while retaining over 98% of configurational diversity. Trained on small graphs, the framework generalizes across sizes and topologies without retraining, enabling quantitative isolation of secondary observables such as the clustering coefficient. These results establish reinforcement learning as a practical paradigm for hard-constrained graph generation.

Hoyun Choi, Junghyo Jo, Deok-Sun Lee

School of Computational Sciences, Korea Institute for Advanced Study, 85, Hoegi-ro, 02455, Seoul, Korea. · Department of Physics Education, Seoul National University, 1, Gwanak-ro, 08826, Seoul, Korea. · Center for Theoretical Physics and Artificial Intelligence Institute, Seoul National University, 1, Gwanak-ro, 08826, Seoul, Korea. +1

Graph Rewiring Graph Generation Generative Modeling RL for Generative Models

May 20, 2026cs.LG

Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent

Online off-policy reinforcement learning (RL) is shaped by two coupled choices: the policy class and the update rule. Gaussian policies are fast and have tractable entropy, but struggle with multimodal action distributions. Generative policies are more expressive, but often require iterative sampling or lack tractable entropy estimates. On the optimisation side, SAC-style soft policy improvement and mirror descent (MD) can be viewed as minimising different KL divergences: the former moves the policy towards a value-induced Boltzmann distribution, while the latter regularises each update against the previous policy. Combining entropy regularisation with an MD constraint is therefore attractive, as it supports exploration while stabilising policy improvement; however, the resulting target can be multimodal and is poorly matched by unimodal Gaussian policies. We propose Stochastic MeanFlow Policies (SMFP), a one-step generative policy class that maps Gaussian noise to actions through a MeanFlow transformation. This stochastic reparameterisation yields a tractable entropy surrogate and allows MeanFlow policies to be trained within off-policy mirror descent under a unified objective for exploratory yet stable improvement. Across seven MuJoCo benchmarks, SMFP improves over Gaussian and generative baselines while retaining single-step inference efficiency.

Zeyuan Wang, Da Li, Yulin Chen +6

Laboratory for Big Data and Decision, National University of Defense Technology, China · Samsung AI Center Cambridge, UK · Queen Mary University of London, UK +3

Reinforcement Learning Maximum Entropy RL Mean Flow RL for Generative Models Off-Policy RL

May 19, 2026cs.AI

Memory-Augmented Reinforcement Learning Agent for CAD Generation

Automatic generation of computer-aided design (CAD) models is a core technology for enabling intelligence in advanced manufacturing. Existing generation methods based on large language models (LLMs) often fall short when handling complex CAD models characterized by long operation sequences, diverse operation types, and strong geometric constraints, primarily because reasoning chains break and effective error-correction mechanisms are lacking. To address this problem, this paper proposes a memory-augmented reinforcement learning framework for CAD generation agents. The framework encapsulates the underlying geometric kernel into a structured toolchain callable by the agent and builds a closed-loop mechanism of design intent understanding, global planning, execution, and multi-dimensional verification. It also designs a dual-track memory module consisting of a case library and a skill library, and proposes a dynamic utility retrieval algorithm. By introducing reinforcement learning into retrieval and policy optimization, the agent can effectively avoid retrieval traps in which examples are semantically similar but geometrically infeasible, enabling online self-correction and continual evolution without additional large-scale annotated data. Experiments show that the proposed method significantly improves both the success rate and geometric consistency on complex CAD model generation tasks.

Yin Xiaolong, Liu Yu, Shen Jiahang +4

Zhejiang University · Ocean University of China

Text-to-CAD Generation RL for Generative Models Memory-Augmented Agents RL for LLM Agents

May 19, 2026cs.CV

FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models

Recent advances in flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks due to the generation of harmful or undesirable content. Existing concept erasure methods are either inference-time interventions with limited effectiveness or rely on supervised fine-tuning (SFT), which requires precisely aligned data and struggles with scalability and multi-concept settings. In this paper, we propose \emph{FlowErase-RL}, the first GRPO-based framework for concept erasure in flow matching models. We reformulate concept erasure as a reward optimization problem and introduce a \textbf{dynamic dual-path reward mechanism} that jointly optimizes (i) a Concept Erasure (CE) reward to suppress target concepts and (ii) a Non-target Space (NS) reward to preserve generative fidelity. The two reward paths are adaptively balanced during training via a performance-driven switching strategy, enabling stable optimization without explicit supervision. Extensive experiments on nudity, object, and artistic style erasure demonstrate that our method achieves state-of-the-art erasure performance while maintaining strong image quality and semantic alignment. Moreover, it exhibits robust resistance to adversarial attacks and scales effectively to multi-concept scenarios. Our results establish a new paradigm for safe and controllable generation in flow matching models.

Yi Sun, Zhiqi Zhang, Xinhao Zhong +5

Harbin Institute of Technology, Shenzhen · Jilin University · Tsinghua Shenzhen International Graduate School, Tsinghua University +2

Flow Matching T2I Generation Safe T2I Generation Flow-Based Generative Modeling RL for Generative Models Concept Erasure

May 19, 2026cs.AI

Generative Auto-Bidding with Unified Modeling and Exploration

Automated bidding is central to modern digital advertising. Early rule-based methods lacked adaptability, while subsequent Reinforcement Learning approaches modeled bidding as a Markov Decision Process but struggled with long-term dependencies. Recent generative models show promise, yet they lack explicit mechanisms to balance exploration and safety, relying solely on action perturbations or trajectory guidance without a safety fallback. This results in inefficient exploration and elevated financial risk for advertising platforms. To address this gap, we propose GUIDE (Generative Auto-Bidding with Unified Modeling and Exploration), a framework that synergistically integrates directed exploration with a safe fallback mechanism. GUIDE employs a Decision Transformer (DT) to jointly model historical bidding actions and environmental state transitions. A Q-value module guides the DT's exploration via regularization constraints, while an Inverse Dynamics Module (IDM) leverages DT-predicted future states to infer robust, behaviorally consistent actions as a safe policy fallback. The Q-value module then adaptively selects the final action between these two options, balancing exploration and safety. Together, these components form an integrated "explore-safeguard-select" pipeline that unifies efficiency and safety. We conduct extensive experiments on public datasets, in simulated auction environments, and through large-scale online deployment on Taobao, a leading Chinese advertising platform. Results show GUIDE consistently outperforms state-of-the-art baselines across all scenarios. In real-world deployment, GUIDE achieves notable gains: +4.10% ad GMV, +1.40% ad clicks, +1.66% ad cost, and +3.52% ad ROI, demonstrating its effectiveness and strong industrial applicability.

Mingming Zhang, Feiqing Zhuang, Na Li +7

Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University · Taobao & Tmall Group of Alibaba

Automated Bidding Online Advertising Decision Transformer RL Exploration RL for Generative Models Safe RL

May 16, 2026cs.CV

Latent Action Control for Reasoning-Guided Unified Image Generation

Unified multimodal models can encode visual understanding and image generation within a shared backbone, yet understanding does not automatically translate into control: models may infer objects, relations, or knowledge cues but fail to instantiate them in the generated image. We propose Latent Action Control (LAC), which makes reasoning actionable by representing it as hidden continuous actions inside a unified generator. Given a prompt, LAC rolls out a role-structured latent trajectory for planning, internal visual drafting, diagnosis, and refinement, and injects these actions into the hidden stream that conditions flow-based generation, without producing reasoning tokens or intermediate images. Since such action trajectories are unobserved, LAC learns them through prior-guided variational latent action alignment from training-only rendered semantic priors, draft image features, and supervised halting signals, followed by Latent-Flow GRPO to align the latent-to-image rollout with terminal visual feedback. This provides a control path from inferred relations, bindings, and knowledge cues to the generation process. Instantiated on BAGEL-7B-MoT, LAC consistently improves compositional and knowledge-grounded generation across GenEval, WISE, and T2I-CompBench, with the largest gains on spatial relations, attribute binding, and world-knowledge-sensitive prompts. Ablations and latent interventions show that the learned action trajectory is consumed by the generator, suggesting that unified generation benefits when understanding is not only encoded, but made actionable during generation.

Fuxiang Zhai, Sixiang Chen, Yingjin Li +4

The Hong Kong University of Science and Technology (Guangzhou)

Unified Multimodal Models Compositional T2I Generation RL for Generative Models Controllable Image Generation

May 15, 2026cs.CV

Embedding-perturbed Exploration Preference Optimization for Flow Models

Recent advancements have established Reinforcement Learning (RL) as a pivotal paradigm for aligning generative models with human intent. However, group-based optimization frameworks (e.g., GRPO) face a critical limitation: the rapid decay of intra-group variance. As the distinctiveness among samples within a group diminishes, the variance approaches zero. This eliminates the very learning signal required for optimization, rendering the process unstable and forcing the policy into premature stagnation or reward hacking. Existing strategies, such as varying the initial noise or increasing group sizes, often fail to address this fundamental issue, resulting in training instability or diminishing returns. To overcome these challenges, we propose

\textbf{Embedding-perturbed Exploration Preference Optimization (}E^2\textbf{PO)}

, a novel framework that sustains optimization through embedding-level perturbation. Our method introduces structured, embedding-level perturbations within sample groups, guaranteeing a robust variance that preserves the discriminative signal throughout the training process. Extensive experiments demonstrate that our approach significantly outperforms state-of-the-art baselines, achieving a more faithful alignment with human preference.

Sujie Hu, Chubin Chen, Jiashu Zhu +3

1Tsinghua University · ⋆Work done during the internship at AMAP · 2AMAP, Alibaba Group

AI Alignment Group Relative Policy Optimization RL for Generative Models RL Fine-Tuning Preference-Based RL