Group Relative Policy Optimization

An LLM judge deployed inside a reasoning pipeline does not merely measure quality, it decides which answer ships. We show that the cost of that decision depends less on judge accuracy than on the decision rule the judge is embedded in. On frozen candidate pools from four GRPO policies, an unconstrained scalar DeepSeek-R1-7B judge buys almost nothing over answer-level majority vote (+1.0 pp on 500 GSM8K questions, +0.34 EM on 300 HotpotQA questions), and on a frozen-rule 30-question confirmation split it is 10 points worse than majority, a judge that destroys accuracy while scoring candidates confidently. We then subordinate the same judge to Evidence-Locked Derive-Gate-Repair (EL-DGR), a task-adaptive non-compensatory rule under which a judge preference may override evidence-supported consensus only with an extractive evidence certificate, and a repair only when neither alternative is certified and the repair is. With no change to the judge, the candidates, or the budget, EL-DGR reaches 58.2% on GSM8K (vs. 56.8% judge, 55.8% majority, 55.4% first candidate) and 17.33 EM / 25.46 F1 on HotpotQA (vs. 15.67/23.49, 15.33/23.19, 15.33/22.97), improving on first-candidate GRPO by +2.8 pp (exact McNemar p=0.0026) and +2.00 EM (p=0.070, borderline). A decision audit shows why: EL-DGR overturns consensus on only 8 of 30 pilot questions and never converts a correct consensus into an incorrect answer. We also report what did not work: the same seven-channel decomposition used as a step-level gated training reward is null, and corrected channel-drop ablations show no channel is individually necessary (p=1.0 throughout). The practitioner-facing finding is negative about judges and positive about admissibility, bound the judge's blast radius rather than trying to make it accurate.

Wasserstein policy gradient (WPG) updates state-conditional action laws by transport in the action space. We study entropy-regularized discounted linear-quadratic (LQ) control. A Bellman verification argument shows that the unrestricted problem has a linear-Gaussian optimal policy, and the discounted-occupancy-weighted statewise Wasserstein gradient is tangent to this policy class. WPG therefore reduces exactly to a finite-dimensional ODE for the feedback gain and action covariance. We prove that this ODE is globally well posed and converges exponentially from every admissible initialization. For each fixed LQ problem, the exponent has a positive limit as the entropy temperature tends to zero and contains no perturbative factor of the form $\exp(-c/τ)$, while retaining the usual dependence on the conditioning of the control problem.

Reinforcement learning with Verifiable Reward (RLVR) has emerged as a powerful paradigm for training coding agents, where the execution feedback from compilation and tests provides objective verification. However, unlike agent tasks, coding agents face a unique and finer-grained credit assignment challenge: at each step, coding actions simultaneously pack varying changes into different regions of a code version, which makes the contribution of independent change indistinguishable. Existing RLVR methods mostly leverage the outcome reward or step-level reward, which fails to dive into a code diff and makes unique properties of coding actions invisible to training. In this paper, we propose Diff-in-Diff Policy Optimization (DiDPO), a critic-free RL method that constructs fine-grained credit units directly from the structure of code diffs. DiDPO organizes multi-turn coding interactions into multiple thought--action steps and discovers code diffs across sampled trajectories. It then selects anchors by aggregating highly similar sub-diffs split from each whole diff by our ``groupability score'', which provides the splitting schema that optimally balances the semantic scope of anchors and the group mass they may form. Finally these anchors form advantage groups and project the diff-level advantage back to individual response tokens. Experiments on long-horizon coding and reasoning benchmarks show that DiDPO significantly outperforms strong agentic RL baselines. On Qwen2.5-7B-Coder, DiDPO exceeds comparable methods by over 10% and narrows the gap with far larger models, offering a principled framework for fine-grained credit assignment in coding agent training. We also open-source verl-code, an agentic rl codebase that supports various RL methods and coding benchmarks.

Detailed audio-video joint captioning is essential for multimodal video understanding and generation. However, prior works are constrained by three main limitations: (1) the scarcity of high-quality public datasets with fine-grained audio-visual joint captions; (2) reinforcement-learning methods that rely on coarse reward signals; and (3) the lack of a benchmark and metric for evaluating detailed audiovisual captions at the atomic level. To address these challenges, we propose: (1) AVCap-100K, a high-quality dataset of 100K temporally aligned, detail-rich audio-video captions; (2) AVCap, a model optimized via Detail-Aware GRPO (Da-GRPO) that achieves state-of-the-art performance among open-source models and matches or surpasses proprietary models on several evaluations; and (3) AVCap-Bench and AVCap-Score, a specialized benchmark and metric for evaluating atomic-level details in audiovisual captions. Our code, models, and datasets are available at https://huggingface.co/collections/Apryle/avcap.

Large language models can infer sensitive personal attributes, such as age, location, and occupation, from ordinary text, turning everyday writing into a privacy risk. Adversarial anonymization defends against this by rewriting a text with a capable language model that also plays the attacker, but it needs a powerful model at inference time and thus sends private text to a third party, the very exposure anonymization should prevent. Recent work distills this behavior into a small on-device model using supervised fine-tuning and direct preference optimization (DPO), but DPO only imitates the teacher's offline choices and never directly optimizes the privacy--utility objective we care about. We introduce \textbf{GRASP} (\textbf{G}roup-\textbf{R}elative \textbf{A}nonymization via \textbf{S}elf-refinement \textbf{P}olicy-optimization), which reinforces the local anonymizer online with Group Relative Policy Optimization. A single small model acts as anonymizer, adversary, and utility judge, trained against a self-generated reward that hides attributes while preserving meaning, with a design that guards against reward hacking. Trained on Llama-3.1-8B, \ours{} improves the privacy--utility trade-off over the DPO-distilled baseline, consistently across three independent LLM judges. Against adversarial anonymization driven by frontier models such as Gemini2.5Flash and Claude, it achieves a comparable or better overall trade-off while removing substantially more private information, and it runs entirely on-device at roughly $1\%$ of the GPT-4o teacher's cost.

Flow-based generative models are typically sampled by solving a deterministic ordinary differential equation (ODE), whereas online reinforcement learning requires stochastic rollouts for policy exploration and optimization. Existing GRPO methods for flow models therefore replace the inference-time ODE with a stochastic differential equation (SDE) during training. Although the ODE and SDE share the same marginal distributions in continuous time, their finite-step discretizations can differ substantially. In particular, SDE rollouts often become blurry as the exploration noise increases, creating a mismatch between the samples used for reinforcement learning and those generated by the test-time ODE sampler. We introduce LC-GRPO, a flow-based GRPO framework with Langevin correction. Each rollout transition first takes an inference-aligned ODE Euler step and then applies a stochastic Langevin correction targeting the marginal distribution at the resulting timestep. The required score is recovered directly from the flow velocity, requiring no additional score model, while the resulting transition remains an isotropic Gaussian with a tractable likelihood for policy optimization. We theoretically show that, under suitable conditions, one Langevin correction step reduces the Wasserstein error of an imperfect ODE Euler step. At a matched randomness level, we further show that the proposed transition can be more accurate than the standard Euler--Maruyama discretization of the reverse SDE. Experiments on SD3.5-Medium, FLUX.1-Dev, and HunyuanVideo demonstrate that LC-GRPO consistently improves reward optimization across text-to-image and text-to-video tasks, preserves generation quality, and substantially narrows the gap between stochastic training rollouts and deterministic test-time ODE inference.

Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer. However, existing methods for training these agents typically treat all steps within a trajectory uniformly during both supervised fine-tuning (SFT) and reinforcement learning (RL), failing to distinguish useful actions from erroneous or redundant ones. In this paper, we propose Answer-Backtracked Credit Assignment (ABC), a fine-grained credit assignment framework for training long-horizon search agents by converting sparse trajectory-level outcomes into dense step-level supervision that rewards useful actions (even in failed trajectories) while suppressing erroneous or redundant actions. Specifically, given a potentially obscure query and its corresponding ground-truth answer, ABC first performs Answer-Backtracked Clue Recovery, which traces back from the answer to recover intermediate clues required to solve the question. It then applies Clue-Anchored Step Scoring to evaluate each search step against these clues, converting sparse binary outcome supervision into dense step-level rewards. Based on these rewards, we develop ABC-SFT, which reweights the loss of each turn, and ABC-GRPO, which uses the step-level scores as rewards in GRPO. Building on this framework, we train ABSeeker based on Qwen3.5-4B with only 8.5k examples. ABSeeker achieves 37.3% on BrowseComp and 39.1% on BrowseComp-ZH. With context management, the scores further improve to 55.3% and 52.9%, respectively, significantly outperforming same-scale (4B) agents and even matching the performance of larger ones (approximately 30B). These results demonstrate the effectiveness of answer-backtracked step-level credit assignment for training long-horizon search agents.

This work studies model-free reinforcement learning for co-safe linear temporal logic (sc-LTL) objectives in finite Markov decision processes, which can be reduced to maximal reachability objectives via the standard product construction. For this problem, direct sample-based bootstrap methods (e.g., TD or Q-learning) may fail to converge to optimal policies due to the noncontractive nature and nonuniqueness of solutions to the Bellman equation. We develop a new two-step model-free reinforcement learning method that first uses a discounted surrogate to identify a clamp set that resolves this nonuniqueness, and then applies undiscounted policy evaluation and greedy policy improvement with guarantees of finding an optimal solution. We prove almost-sure convergence of the policy evaluation step and finite termination of the policy iteration algorithm at an optimal policy. These theoretical results are validated through numerical experiments on a stochastic grid world.

Reinforcement learning (RL) post-training improves the reasoning capabilities of large language models, but autoregressive rollout generation remains a major efficiency bottleneck. Speculative decoding can accelerate generation, yet applying it during RL is difficult because the target policy continually evolves: static proposers become stale, while frequent drafter updates add substantial overhead. We introduce SpecRoll, a speculative rollout engine that preserves the target model's sampling distribution while adapting at two timescales. Lightweight future-token heads generate parallel proposals, while our proposed Reflex module uses delayed verifier feedback to perform bounded, trajectory-local hidden-state corrections without backpropagation. A complementary slow path updates the head parameters only when sustained degradation is detected. SpecRoll combines these mechanisms with concurrency-aware sparse-tree verification and exact target verification, leaving the target rollout distribution and GRPO objective unchanged. Across five models ranging from 1.5B to 14B and three mathematical reasoning datasets, SpecRoll achieves 1.26-2.15x generation speedup and 1.21-2.04x end-to-end speedup over vanilla GRPO. It also outperforms FastGRPO in both generation and end-to-end time across all 15 matched settings, with an average pairwise end-to-end gain of 1.18x. Controlled ablations show that the fast and slow adaptation paths provide complementary benefits. Our source code is available at https://anonymous.4open.science/r/SpecRoll-26062006.

We tackle the challenging yet underexplored task of Generalized Referring Expression Comprehension (GREC), which requires a model to localize the object described by a textual expression when it exists (positive sample) and to refuse output when it does not (negative sample). Although Multimodal Large Language Models (MLLMs) excel at localizing existing objects, they often fail to reject nonexistent ones due to the absence of negative samples during training, producing hallucinated bounding boxes. Existing post-training approaches such as supervised fine-tuning (SFT) and reinforcement learning (RL) enhance refusal behavior but usually degrade localization accuracy on positive samples, undermining the model's core competence. To address this, we propose Refusal-Calibrated Group Relative Policy Optimization (RC-GRPO), a calibrated RL strategy that strengthens the refusal ability of MLLMs while preserving localization performance. It enforces "None" outputs in rollouts for valid advantage estimation on negative samples and applies a penalty to prevent over-refusal on positives, achieving a balanced trade-off between accuracy and reliability. A second-stage reasoning reinforcement further consolidates causal understanding and interpretability. Experiments on three GREC benchmarks demonstrate that RC-GRPO attains superior localization accuracy while maintaining strong refusal capability.

Text-to-image (T2I) models can produce visually compelling images, yet they remain limited on open-world tasks that require complex semantic understanding, multi-step reasoning, and the integration of external world knowledge. Existing efforts introduce agent capabilities into image generation, but they either prescribe a fixed workflow or place only a subset of the open-world image generation process under agent control. Consequently, reasoning, tool invocation, and image generation are not coordinated by a single policy. We propose ToolArtist, a fully agentic image generation model obtained by post-training a Unified Multimodal Model (UMM). ToolArtist dynamically orchestrates reasoning, external tool use, and native image generation within one unified policy. During Supervised Fine-Tuning (SFT), we equip a teacher agent with search tools alongside an image-generation tool. We then convert the collected trajectories into a UMM compatible format, where the image-generation tool is concealed while the resulting generated images are retained. During Reinforcement Learning (RL), we develop an agentic RL infrastructure for UMMs and introduce Reason-Act-Draw GRPO (RAD-GRPO), which uses complementary intent and quality rewards to jointly optimize the model. Experiments show that placing the entire open-world image-generation process under an agent policy consistently outperforms approaches with fixed pipelines or only partially agent-controlled components. We release the training data and the complete post-training infrastructure.

Generative Flow Networks (GFlowNets) have emerged as a flexible framework for amortised inference over discrete and mixed discrete-continuous objects, requiring only an unnormalised target density specified through a reward. In this work, we formulate forward-policy training in GFlowNets through the information geometry of the induced trajectory sampler. Treating the forward policy as an induced trajectory sampler, we show that its intrinsic first-order geometry is given by the Fisher-Rao metric of the trajectory family, and that the associated natural gradient provides the canonical local update whenever the corresponding Fisher information is computable or accurately approximable. We derive an exact decomposition of the trajectory Fisher into per-step conditional second moments, which clarifies when temporal score interactions vanish and when dense couplings remain under shared parameterisation. This leads to three computational regimes: settings with tractable exact Fisher information, settings where Monte Carlo estimators of the expected Fisher are sufficient, and structure-exploitable settings in which target locality or factorisation yields accurate approximations of the Fisher expectation. In the latter case, graphical-model tools such as exact marginalisation, separator methods, and belief propagation provide principled surrogates for natural-gradient updates. The resulting framework turns target structure into optimisation geometry and yields a tractable route to structure-aware forward-policy training in GFlowNets. We illustrate the framework empirically through examples comparing convergence and exploration behaviour under Riemannian and Euclidean optimisation.

Reinforcement fine-tuning (RFT) is widely believed to inherently resist catastrophic forgetting in continual post-training of multimodal large language models. Under pronounced task distributional shifts, however, forgetting across representative RFT algorithms escalates sharply. This stems from the implicit reward-variance regularization inherent to RFT, which proves incapable of suppressing uncontrolled optimization risk. We propose Risk-Aware Policy Optimization (RAPO), the first dual-channel framework for explicit risk governance in continual RFT. On the policy channel, Risk-Aware Policy Scaling adaptively calibrates per-sample update magnitude via rollout reliability and Fisher-inspired local predictive sensitivity; on the data channel, Risk-Aware Dynamic Bucket Sampling reorganizes training batches through dynamic risk stratification, steering optimization toward informative yet stable samples. As a plug-and-play strategy requiring no cross-task memory, RAPO generalizes to any RFT algorithm without modification. On the public MLLM-CL benchmark, RAPO reduces final forgetting by 79.8% relative to its RLOO backbone while retaining new-task competitiveness.

Reinforcement learning with verifiable rewards (RLVR) com- monly optimizes each correct completion as an independent learning signal. In GRPO, this completion-level uniformity creates structure-level skew: recurring correct solution forms accumulate positive coefficient mass in proportion to how often they are sampled, while rare forms receive limited credit. We formalize this behavior as multiplicity-induced structure-level credit concentration and introduce a partition- conditioned rule that redistributes positive advantages accord- ing to cluster rarity. Cue-GRPO instantiates this rule with- out auxiliary-model inference by using deterministic Strategy Cues to construct rollout-local partitions of verified-correct traces. Across Qwen2.5-Math-7B and Llama-3.1-8B-Instruct, Cue-GRPO improves AIME repeated-sampling performance, with the largest gains at high sampling budgets. Credit Re- distribution (CR) under Judge Partitions (JP) further indi- cates that the proposed redistribution mechanism can oper- ate with judge-derived partitions. Cue-GRPO adds only 6% wall-clock training overhead over GRPO. These results sup- port structure-level credit redistribution as a practical design axis for RLVR, with Strategy Cues providing a low-overhead implementation for competition mathematics. Code is avail- able at https://github.com/CzZ12/When-Correct-Solutions- Repeat-Rarity-Aware-Credit-Redistribution-for-GRPO.

Reinforcement Learning with Verifiable Rewards (RLVR) improves LLM reasoning but typically relies on ground-truth (GT) answers, limiting scalability. Voting-based label-free RLVR replace gold supervision with answer-level consensus from model samples. However, collapse arises when the same answer-level signal is used both to estimate rewards and to drive token-level policy optimization, encouraging the model to directly reinforce answer tokens rather than improve reasoning. We propose OM-GRPO, a label-free RLVR framework that decouples reward estimation from policy optimization. OM-GRPO masks gradients on the answer span while retaining answer-level rewards through a soft consensus signal, shifting optimization pressure away from answer tokens. We further introduce Contrast-Augmented Reward, which refines reward estimation via low-cost pairwise comparisons over existing trajectories without additional rollouts. Across diverse reasoning benchmarks and three LLM backbones, OM-GRPO consistently outperforms existing label-free RLVR methods and matches supervised GT-reward training with stable optimization. This stability is particularly beneficial in the Test-Time Training setting, where OM-GRPO surpasses majority voting by 4.24 points.

We aim to improve model performance in multi-reward reinforcement learning training process. Existing Group reward-Decoupled Normalization Policy Optimization (GDPO) has mitigated the issue of reward signals masking one another during direct scalarization by normalizing each reward dimension separately before aggregation. However, our experiments show that GDPO still struggles to balance reward signals with different granularities. Specifically, in some particular training tasks, the model may receive a dense reward that assigns fine-grained scores ranging from 0.1 to 1.0, together with a sparse reward that provides only binary feedback of either 0 or 1. In such cases, we find that the sparse reward may provide an insufficient optimization signal, preventing its corresponding capability from being effectively reinforced. Therefore, how can we strengthen the optimization signal from the sparse reward without sacrificing the capability already learned from the fine-grained reward? To overcome this limitation, we propose Specialize-and-Merge Online Policy Distillation (SMOPD), a two-stage training method for multi-reward optimization. Stage1-Specialize: SMOPD first employs reward-priority configurations to train multiple reward-specialized teachers, allowing each reward to be learned under conditions where its signal can effectively drive optimization. Stage2-Merge: SMOPD then utilizes online policy distillation to combine the reward-specialized capabilities of these teachers into a single student policy, while maintaining balanced task-level optimization. To validate our method, we conduct experiments on two multi-reward settings: complementary rewards(tool-calling accuracy and format) and conflicting rewards (helpful and harmless rewards). Based on above settings, SMOPD outperforms GDPO across 1.5B, 3B and 7B backbones.

Reinforcement learning (RL) has emerged as an effective method for enhancing the reasoning capabilities of large language models (LLMs). However, existing methods suffer from insufficient precision in feedback on generated answer trajectories and exhibit the phenomenon of problem difficulty drift. To address these challenges, we propose CVPO - Curriculum-guided Value-Variance Policy Optimization. At the response trajectory level, we find that token-level value-variance correlates with exploration intensity. Our theoretical analysis shows this variance bounds policy update magnitude. We then use the estimated trajectory value-variance to quantify the intrinsic randomness in generation. Based on this, we design a variance-aware advantage adjustment mechanism for different reward types. At the question level, we introduce a dynamic curriculum weighting method that adapts to question difficulty. This helps the model focus on tasks matched to its current ability during each training stage. Experimental results show our method outperforms strong value-based baselines like VAPO. It achieves better performance and stronger exploration, enabling more accurate and robust reasoning in language models across various math tasks.

Preference-based reinforcement learning (PbRL) for general stochastic MDPs often requires training a reward model. Existing reward-model-free methods are either restricted to bandits or deterministic MDPs, such as DPO or P3O, or use zeroth-order, gradient-free optimization, which in general exhibits a slower convergence rate than gradient-based algorithms. Furthermore, existing reward-model-free preference-based RL algorithms almost exclusively use trajectory-level feedback, which can require significant effort from a human evaluator when trajectories are long. On the other hand, segments are much shorter, so they are easier to compare and evaluate. In this paper, we introduce a novel reward-model-free, critic-free, and gradient-based PbRL algorithm compatible with segment preferences named Segment Pairwise Proximal Policy Optimization (SP3O). SP3O utilizes segment-level preference feedback to construct an accurate policy value difference estimator via off-policy importance sampling, and then uses the estimator to compute the policy gradient via a PPO-type loss function. We provide a theoretical basis for the algorithm and analyze the tradeoff in choosing the segment length. We also evaluate it experimentally against other PbRL/RLHF algorithms in robotic control and LLM finetuning settings to show its improved performance, especially in long-horizon tasks.

Proximal Policy Optimization (PPO) for large language models typically trains its critic by mean-squared-error (MSE) regression on scalar value targets. Although scalar MSE is statistically valid for estimating the conditional expected return, sparse binary rewards in reinforcement learning with verifiable rewards (RLVR) make critic optimization and calibration especially consequential: small value errors directly distort the scalar advantages used by PPO. We study whether a classification-based training objective can improve this critic signal. HL-Gauss PPO replaces the scalar MSE head with a categorical predictor over a discretized value support, trained by cross-entropy against smoothed HL-Gauss targets. Its output is decoded to a scalar expectation for standard GAE and PPO; the actor update is therefore unchanged and is not distributional. Across mathematical reasoning, tool-augmented math, and Search-R1, and on both Qwen2.5 and Qwen3 backbones, HL-Gauss PPO consistently improves over strong PPO and DAPO baselines. Controls with one-hot, two-hot, and Bernoulli two-bin critics show that neither a larger output head nor binary classification alone explains the gains. On a common collection of reasoning prefixes, HL-Gauss improves Brier score and calibration error and yields more symmetric, lower-variance advantages. These results position categorical value learning as an effective optimization surrogate for PPO critics in RLVR.

Reinforcement learning has become a central paradigm for improving the reasoning capabilities of large language models. Existing methods generally aim to reduce the failure probabilities induced across problems. In this paper, we introduce a moment-based perspective on policy optimization for LLM reasoning by treating the failure probability of a randomly sampled problem as a random variable and characterizing optimization objectives through its moments. Under this perspective, many existing methods optimize only a single moment of the failure-probability distribution, leaving its broader distributional structure largely uncharacterized. We propose \textbf{M}ulti-\textbf{M}oment \textbf{P}olicy \textbf{O}ptimization (MMPO), a novel policy optimization framework that jointly minimizes multiple moments of the failure-probability distribution. MMPO admits a direct operational interpretation as minimizing the expected truncated time required to obtain the first successful response. Beyond MMPO, we further develop a general moment-transformation framework that systematically induces different moment profiles and provides a unified view of a broader family of policy optimization objectives. Experiments across five mathematical reasoning benchmarks and models of different scales demonstrate that MMPO consistently outperforms strong baselines. We hope this moment-based perspective offers new insights into the design of policy optimization objectives for LLM reasoning.

Long-horizon video editing agents receive final-product feedback only after many interdependent decisions. Yet editing quality is subjective, admits multiple valid solutions, and is not meaningfully calibrated across heterogeneous requests, making a global scalar objective both ambiguous and temporally uninformative. Our key observation is that fixing the request, materials, and production constraints converts this subjective objective into an ordinal comparison among directly comparable alternatives. We introduce Group-Relative Preference Backpropagation (GRPB), which transforms same-task rankings into zero-sum advantages and redistributes them as bounded credit over semantic editing segments. A lagged allocator and guarded transmission prevent current judgments or unreliable estimates from directly shaping the same rollout group. We manually construct a project-disjoint, horizon-stratified suite of realistic editing tasks for training and controlled evaluation. Across matched baselines, credit interventions, external benchmarking, and blinded human evaluation, GRPB improves both editing behavior and rendered products. The resulting 9B Crayotter model surpasses several proprietary systems on AgenticVBench, supporting task-local preference reduction as a practical approach to learning from subjective, delayed outcomes. Code and all supporting materials are publicly available at https://github.com/idwts/Crayotter.

Autoregressive rollout generation is a major computational cost in reinforcement learning for large language models. Reusing each rollout batch for additional learner updates amortizes this cost, but later updates become increasingly off-policy as the learner departs from the behavior policy. At a token position, exact off-policy correction must account for both the current action and the probability of reaching its prefix. The cumulative importance ratio provides this correction, but its product form can produce an unwieldy dynamic range. We study Prefix-Normalized Policy Optimization (PNPO), which replaces the cumulative ratio with the geometric mean of likelihood ratios along each causal prefix, preserving causal-prefix dependence at each position while compressing the log-weight scale. In controlled long-context mathematical reasoning experiments, we induce two off-policy regimes by using one or four policy-update epochs per rollout batch. PNPO does not consistently outperform GSPO with one epoch. With four epochs, it attains the highest observed Avg@32 on each benchmark; the unweighted mean of the three independently selected benchmark peaks is 50.24, 3.00 percentage points above GSPO. Under a matched 2,400-update budget, four-epoch PNPO reaches a final macro Avg@32 of 49.66 after 150 rollout batches, comparable to the 49.56 reached after 600 batches with one epoch. These results provide preliminary evidence that PNPO can be advantageous as training moves further off-policy.

Multimodal Large Language Models (MLLMs) are increasingly expected to solve structured perception tasks that require visual recognition, language-to-object binding, object cardinality preservation, and precisely localized grounding and segmentation outputs. However, existing group-relative reinforcement learning methods provide only response-level supervision, creating a granularity mismatch for structured multi-object prediction: a single advantage is broadcast to all tokens in a response, without distinguishing individual box contributions. To address this mismatch, we propose MCR-GRPO, a marginal contribution assignment framework that derives box-level credit directly from each sampled response. Specifically, Marginal Contribution Reward (MCR) estimates each predicted box's contribution through a leave-one-out comparison, measuring how the matched set value changes when the box is removed from the response. After within-response normalization, records that improve the set value receive positive credit, while redundant or harmful ones are suppressed. To make marginal attribution stable and informative, we further introduce a Continuous Matched Set Value Evaluator that integrates permutation-invariant matching, count-aware normalization, and graded localization. MCR-GRPO maps normalized box-level marginal advantages to the token spans that generated each box, preserving GRPO's response-level comparison while enabling box-aware optimization of structured multi-object grounding. Experiments across REC, DOD, segmentation, and counting benchmarks show state-of-the-art performance over prior GRPO-based baselines.

Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models (LLMs). While Group Relative Policy Optimization (GRPO) is widely adopted, it suffers from sparse reward signals and loses gradients entirely when all responses within a group receive identical rewards. On-policy distillation (OPD) offers a natural remedy by providing dense, token-level supervision from a teacher model. However, naively combining GRPO with OPD leads to degraded performance, due to three underlying causes: not all samples benefit from distillation; fitting too quickly to the teacher undermines the exploratory capacity of RL; and OPD's advantages are asymmetric, suppressing most tokens. To address these challenges, we propose RSTG (Recovering Learning Signals via Adaptive Teacher Guidance), which applies distillation selectively and precisely where it matters most. At the sample level, OPD is restricted to negative zero-variance prompts with each sample weighted by the teacher's confidence score. At the token level, distillation targets only tokens with high student entropy or large teacher-student divergence. We further augment training with SFT on correct trajectories generated by the teacher model, injecting positive gradient signals where RL yields none. Experiments demonstrate that RSTG substantially outperforms naive GRPO+OPD by +4.02% on math and +3.05% on code.

Cooperative task scheduling in communication-constrained distributed multi-agent systems is challenging because each agent must make decisions from partial and dynamic observations while satisfying complex practical constraints. Existing heuristics rely on handcrafted bidding rules and repeated consensus, whereas many learning-based methods assume global observations and lack explicit communication-based coordination. To address these limitations, this paper proposes a neural scheduling framework for distributed multi-robot task allocation (MRTA), consisting of a multi-decoder graph attention model (MDGAM) policy model and a critic-free group relative multi-agent policy gradient (GRMAPG) training algorithm. MDGAM uses an extended graph attention mechanism to jointly update node and edge features, and employs multiple decoders to generate task-selection decisions and communication messages. GRMAPG constructs group-relative advantages from equivalent task-planning instances to replace the critic network used in conventional MARL algorithms, thereby reducing training difficulty and improving convergence performance. Experiments under different problem scales and communication ranges show that the proposed method improves task-completion performance over existing heuristic and learning-based methods, while ablation, complexity, and generalization tests further validate the proposed innovations.

Recent advances in image generation and editing have made prompt quality a key bottleneck for e-commerce creatives. Vision-language models (VLMs) can generate image-editing prompts from product images and metadata, but further improving their prompt-writing capabilities requires post-training with feedback from the generated images. Group Relative Policy Optimization (GRPO) is a natural framework for such outcome-level reward optimization. However, it assigns credit only at the full-prompt level, even though image quality often depends on specific design elements such as composition, background, and the presentation of selling points. Existing fine-grained credit assignment methods typically require step-level supervision or learned critics. To address this, we propose EAGLE-GRPO (Element-Aware Group Learning for E-Commerce Image Generation), which decomposes the group-centered reward over predefined elements. We cast element-level credit assignment as a kernel ridge regression problem and derive a closed-form solution, without additional rollouts or separate credit-assignment models. This yields interpretable per-element advantages and more precise policy updates. Experiments show that EAGLE-GRPO sustains performance gains over more training steps before plateauing and generates prompts that produce higher-quality e-commerce images than competitive VLM prompt-writing baselines.

This paper studies the policy gradient update for a multi-arm bandit problem in diffusion environment that is described by a stochastic differential equation (SDE) under the continuous-time reinforcement learning framework by Wang et al. (2020), Jia and Zhou (2022b). With the logit parameterization for the stochastic policy, we show that it converges almost surely to the optimal arm under an arbitrary constant learning rate. Furthermore, we derive the non-asymptotic regret upper bound when the constant learning rate is below a time-invariant threshold; and the regret bound has order $O(\log T)$. We improve the analysis in Lattimore (2026a) for the same SDE by constructing a novel Lyapunov function and demonstrate the transparency of analyzing policy gradient using the tools in SDEs. In addition, the same Lyapunov function is also helpful in analyzing the discrete-time policy gradient algorithm.

Predicting the 3D structures of atomic systems is fundamental to advancing material science and drug discovery. While flow-matching models (, FlowDPO) have recently shown promise in this domain, their performance relies heavily on alignment with ground-truth coordinates via supervised preference learning. However, obtaining experimental labels for novel crystal phases or de novo proteins is prohibitively expensive, creating a bottleneck for structural modeling in data-scarce regimes. In this work, we propose (Atomic Policy Optimization), a fully unsupervised alignment framework that eliminates the need for ground-truth reference structures. APO adapts group-relative policy optimization to 3D atomic environments, utilizing a novel dual-reward mechanism: (i) a that reinforces the policy's dominant latent structural modes through eigen-decomposition of sample similarities, and (ii) a that enforces thermodynamic stability. Our framework enables the model to ``self-correct'' by identifying physically plausible configurations within sampled groups. Extensive benchmarks on crystal and antibody structure prediction demonstrate that APO consistently outperforms fully supervised baselines, achieving a new state-of-the-art in match rates and structural fidelity. Furthermore, we show that APO effectively straightens probability paths, significantly improving inference efficiency. Our results suggest that intrinsic physical consistency can serve as a superior guide for alignment compared to noisy, supervised coordinate matching.

This thesis studies policy learning in interactive systems where an agent observes a context, selects an action from a very large set, and receives partial feedback. The main framework is contextual bandits, with two paradigms: on-policy learning, where the agent interacts sequentially with the environment and minimizes regret, and off-policy learning, where it learns from logged data collected by a logging policy. In large action spaces, both settings face major challenges: inefficient exploration, sparse data coverage, high-variance importance weights, extrapolation bias, and difficult optimization landscapes. The first part develops structured Bayesian methods for on-policy learning. We introduce meTS, a mixed-effect extension of Thompson sampling, and dTS, which leverages diffusion-inspired priors to model dependencies between actions. These methods share information across actions and yield regret guarantees depending on an effective number of actions. The second part addresses off-policy learning. We propose sDM, a structured direct method based on latent variables, show that optimization error can dominate estimation error in large action spaces, and introduce concave, efficiently optimizable policy-weighted log-likelihood objectives. Finally, we develop differentiable pessimistic methods based on exponential smoothing and PAC-Bayesian bounds to control the bias-variance trade-off of regularized importance-sampling estimators.

Computer-use agents often fail on transient GUI events because they produce the correct action only after the relevant window has already closed. We identify the main cause as expensive autoregressive decoding on the decision-time critical path. We propose Adaptive Anticipatory Policy Trees (AAPT), which eliminates this delay without modifying the underlying model. During idle screen periods, the same frozen multimodal model constructs a bounded conditional policy tree with observable guards, pre-authorized actions, and branch-specific deadlines. The tree is sized to cover the model's own decoding latency. When an event occurs, a lightweight observer matches change-gated frames to a prepared branch and immediately executes the corresponding action without generating new text. In paired trials with pre-registered endpoints and exact McNemar tests, AAPT improves the success rate from 0.50 to 0.79 within a contested decision window ($p=1.8\times10^{-3}$), while producing no incorrect actions. Both open-loop and predict-and-replan baselines achieve zero success because they still decode during execution. A preparation-time sweep shows that the gain emerges where the latency-based tree-sizing rule predicts, and ablations reveal three key requirements: fast observer decoding, valid tree planning, and accurate branch routing. A pre-registered oracle probe rejects our initial hypothesis and instead points to branch routing as the causal bottleneck. We further reproduce the effect on an independent general-purpose multimodal model over 126 paired trials ($p=4.9\times10^{-13}$). On an external benchmark, AAPT matches the overall performance of a reactive baseline, although the two methods exhibit complementary strengths. Together, these results suggest that AAPT performs best when candidate actions can be enumerated in advance, whereas reactive execution remains stronger when they cannot.

Recently, Reinforcement Learning (RL) has emerged as a crucial paradigm for the post-training of Large Language Model (LLM) agents. However, existing methods predominantly rely on sparse task rewards for policy optimization, failing to fully exploit another class of inherently dense supervisory signals naturally present during online interaction: environmental feedback following action execution. Recent theoretical studies suggest that generalization in multi-step, goal-oriented tasks hinges on predictive knowledge of environmental consequences. Inspired by this, we propose TAPO: Transition-Aware Policy Optimization for LLM Agents, a unified training framework that alternates between policy optimization and transition supervision. Beyond standard RL updates, TAPO repurposes rollout data to apply action-conditioned next-observation prediction supervision on a shared backbone model. This approach enhances the model's sensitivity to environmental transition dynamics and action consequences while concurrently optimizing the policy. It serves as a computationally lightweight, plug-and-play enhancement module for existing agent RL algorithms, requiring no additional expert data, extra sampling costs, or inference-time overhead. We conduct systematic experiments on WebShop and ALFWorld, integrating foundation models of various scales with different policy optimization algorithms. Empirical results demonstrate that TAPO consistently improves task performance over pure policy optimization baselines.

Reinforcement learning from verifiable rewards (RLVR) for mathematical reasoning suffers from a structural blind spot: on "cliff" prompts-those on which every sampled rollout in a group fails-the group-normalized advantage is identically zero, so GRPO produces no gradient on precisely the prompts at the frontier of the model's capability. We introduce LoRA Scaffolded Policy Optimization (LSPO), a sampling-time mechanism that recovers this lost gradient. Each RL step, LSPO detects cliff prompts, fits a small low-rank (LoRA) adapter by a brief supervised step on their ground-truth solutions, re-rolls the cliffs with the base-plus-adapter model, splices the now-successful completions back into the RL batch with an importance-sampling correction, and takes a GRPO step on the base alone; the adapter receives only the supervised gradient and is discarded at checkpoint, yielding a base-only model. On DeepMath-103K with DeepSeek-R1-Distill-Qwen-1.5B, evaluated over n=5 paired seeds per arm at a matched 1000-step reporting horizon, LSPO's 5-seed mean matches or beats a DAPO baseline on all 16 (benchmark, pass@k) cells (15 strict wins and one exact tie), with gains of up to +10.7 points on AIME24/pass@4, +6.7 points on AIME24 and AIME26 at pass@16, and +2.4 points on MATH500/pass@1; averaged over the 16 cells the improvement is +3.8 points.

A single reinforcement-learning run can produce a strong reasoner yet an incomplete teacher: it often amplifies only a subset of the valid solution modes. We argue that reinforcement learning (RL)-trained policies should therefore be viewed as local probes of a multi-basin reasoning solution manifold, rather than as globally reliable supervisors. Based on this view, we propose an expand-then-compress framework that couples teacher construction with multi-teacher policy distillation. In the expansion stage, Residual Group Relative Policy Optimization (RGRPO) trains a sequence of teachers from a common initialization and redirects each later round toward examples not yet covered by the accumulated teacher union. In the compression stage, reliability-gated Teacher-Union On-policy Distillation (TU-OPD) lets the student learn from its own response prefixes. For each example, only reliable teachers contribute, and their sampled-token OPD losses are weighted by their per-example quality. We further introduce Consensus-Residual Decomposition, which preserves a winner teacher's excess token preferences over its reliable peers, preventing specialist behavior from being suppressed during teacher aggregation. Experiments on mathematical reasoning, code generation, and instruction following show that the resulting Qwen3-1.7B student consistently outperforms the strongest individual teacher across all three domains, yielding relative improvements of 2.0%, 8.3%, and 6.9%, respectively, while retaining single-model inference. These results establish a simple but powerful principle: stronger students can be obtained not by selecting a single better teacher, but by deliberately constructing and compressing a complementary teacher union.

Spoken dialog systems are typically designed for clean, dyadic interactions in which a single user and an assistant take turns speaking. Real-world social conversations, however, are often more ambiguous: multiple speakers may participate in the same conversation amid irrelevant speech and background noise. Each utterance may be directed to the assistant, addressed to another speaker, or completely irrelevant. In such settings, the assistant must decide not only what to say, but also whether to speak at all. In this paper, we introduce Cocktail-Talker, a speech LLM framework for multi-speaker spoken dialog modeling in noisy social environments. We model the assistant's behavior with three action tokens: <|respond|>, <|listen|>, and <|ignore|>, placed before a response or silence. Cocktail-Talker is trained via supervised finetuning and reinforcement learning to generate the appropriate action token and, only in <|respond|> mode, a speech response. To prepare the training data, we develop Cocktail-DialogGen, an LLM-based data pipeline that simulates realistic multi-speaker dialogs with speaker roles across diverse social settings. Together, these components take a step toward spoken dialog systems that interact more naturally and selectively in complex social environments.

Activation steering has emerged in large language models as a lightweight alternative for dynamically changing a model's behavior at inference time. However, we show that existing steering methods fail to steer even a simple policy in a two-route gridworld environment. To address this limitation, we propose Policy Gradient Steering (PGS), which formulates steering as a reinforcement learning problem. PGS accumulates gradients of a temporary behavioral objective over a small set of rollouts or demonstrations to construct a removable task vector. We first demonstrate the calibration and reversibility of PGS in a two-route gridworld environment. Using chess puzzles, we then evaluate independently fitted PGS vectors both in isolation and in combination, finding that compatible tactical objectives accumulate constructively. Finally, in competitive football, we show that PGS can alter specific team behaviors and that its effects transfer across opponents. Together, these results show that policy gradients provide a natural interface for constructing temporary and composable behavioral adaptations across diverse decision-making domains.

Group Relative Policy Optimization (GRPO) has become a standard reinforcement learning method for post-training language models. Recent work shows that GRPO can reduce the base model's reasoning capacity and underperform it in Pass@k when k is large, indicating reduced coverage of reasoning paths. We find that this reduction is associated with GRPO concentrating on responses that the base model already generates with high probability. We trace this concentration to two mechanisms in the GRPO update. At the response level, high-probability responses dominate the group gradient through repeated occurrence. At the token level, GRPO's importance ratio scales gradients, further reinforcing tokens that become more likely under the current policy. We propose ReCo, a reweighting method that addresses both effects. Response contributions are normalized by their expected occurrence within the rollout group, and the token-level importance ratio is replaced with a variance-based ratio that gives larger update scale to non-saturated decision points where alternative token choices remain plausible. Across Qwen2.5-Math-1.5B/7B and Llama-3.1-8B-Instruct on five mathematical reasoning benchmarks, ReCo improves Pass@k for large values of k and is comparable to GRPO for small values of k.

Face anti-spoofing (FAS) is increasingly expected to provide not only bona fide/spoof decisions, but also attack semantics and image-grounded evidence for human inspection. Existing discriminative FAS models remain largely label-centric, while recent MLLM-based methods offer structured outputs but still rely mainly on supervised fine-tuning, often producing template-like rationales and weak optimization for difficult attacks. We propose FAS-R1, a two-stage reasoning-oriented MLLM framework for unified FAS prediction, covering authenticity classification, attack-type recognition and spoof-region localization. FAS-R1 first uses FAS-R1-23K, a high-quality long-CoT dataset, for cold-start supervised fine-tuning, and then performs FAS-specific GRPO post-training. Degradation-Simulated Augmentation (DSA) encourages stable spoof-cue reasoning across visual-quality shifts, while Difficulty-Aware GRPO (DA-GRPO) mitigates easy-sample dominance that may leave difficult task--attack groups under-optimized, especially for subtle or ambiguous attacks such as makeup and mask attacks. The main 3B FAS-R1 model achieves 98.75% authenticity accuracy, 93.33% attack-type accuracy, and 96.30/94.73% AP@40/AP@50 in-domain. It also outperforms the compared systems in cross-domain authenticity generalization and answer-and-rationale quality. Experiments with different base models further show favorable scaling behavior. The code will be released soon.

Reinforcement learning with verifiable rewards (RLVR) is bottlenecked by rollout generation, yet many sampled prompts produce saturated groups (all responses correct or all incorrect) whose zero reward variance yields no policy-gradient signal. Existing remedies either oversample a larger candidate pool and discard saturated prompts (dynamic sampling), paying heavy extra rollouts, or predict prompt difficulty before sampling, which is fragile under a shifting policy. We observe that a group's effectiveness is usually decided early, within the first few of its rollouts, so spending a full group on an already-decided prompt is wasteful. We cast per-step rollout collection as a budget-constrained sequential allocation (optimal stopping) problem and introduce SARA (Sequential Adaptive Rollout Allocation). SARA maintains a Beta posterior over each prompt's success rate, evaluates a closed-form predictor of group effectiveness, and applies a two-threshold, SPRT-style rule that commits effective groups, abandons saturated ones after a short probe, and reallocates the freed budget to fresh prompts, without any extra prediction rollouts. We prove abandonment reliability, expected rollout savings, fixed-budget yield dominance, and a link between effective-group yield and the GRPO gradient norm. On mathematical reasoning and planning with 1.5B/3B models on a single GPU, SARA matches DPS (both below the DS oracle) while using 22% fewer rollouts than DS; composing SARA with DPS yields the best accuracy, slightly above DS, at 67% fewer rollouts (near-uniform cost).

Rubric-based reinforcement learning enriches language model training by evaluating model outputs against explicit criteria. Yet in GRPO-style pipelines, these structured judgments are reduced to a scalar response-level reward and converted into a response-level advantage, which is broadcast uniformly to all generated tokens. This leaves no explicit mechanism for allocating credit within a response, even when different criteria are grounded in different spans, formatting decisions, or semantic choices. We propose CoRT, a token-level credit weighting method for rubric-conditioned GRPO. Instead of training an auxiliary token scoring model, CoRT uses counterfactual replay to rescore the same sampled response under the original rubric-conditioned prompt and a matched criteria-free prompt. The resulting tokenwise log-likelihood contrasts serve as a proxy for dependence on the rubric context. CoRT maps these contrasts to bounded, response-normalized weights and uses them to redistribute the signed GRPO advantage across tokens, without introducing an auxiliary scorer or changing the response-level reward. Experiments across instruction-tuned models and reward granularities show that CoRT improves over matched response-level GRPO in the vast majority of comparisons, with an average gain of 4.4 percentage points. The method remains competitive with learned token-level credit baselines while avoiding a separate relevance-learning stage. These results suggest that policy-internal counterfactual likelihood contrasts provide an effective training signal for within-response credit allocation while retaining the simplicity and stability of GRPO.

Variational Autoencoders are widely used to encode high-dimensional and noisy observations in robotics. However, their stochastic latent creates a mismatch with Proximal Policy Optimization (PPO): an effective policy marginalizes over the latent distribution, whereas former implementations estimate its probability ratio and KL divergence using only one latent sample. We identify a fundamental but overlooked theoretical cause: naive single-sample approximations in stochastic latent space induce significant variance and bias in the surrogate loss. To address this, we introduce P^3 (Probabilistic Policy Propagation), a distribution-aware optimization framework for VAE-based policies. $P^3$ couples moment-based probabilistic method for stable and efficient learning with sampling-based calibration for robust policy behavior under latent uncertainty. In our experiments, P^3 boosts data efficiency from 64.6% to >96%, reduces convergence steps by >20%. Furthermore, P^3 is evaluated on challenging humanoid parkour tasks and shows an effective foundation for VAE-based PPO. Code is available at https://github.com/ylyem9x/P3_Open.

Agentic systems have rapidly advanced in their ability to interact with real-world environments, leverage external tools, and provide services for users. However, unlike natural-world tasks that assume well-defined instructions, human-centered scenarios are characterized by ambiguous requests that lead to large, open-ended solution spaces. Decoding users' personalized preferences is therefore essential for narrowing the candidate solution space. This introduces a new challenge, personalized agentic reasoning, which requires agents to jointly interact with both users and environments to deliver personalized services. In this paper, we present ODYSSE, a Reinforced Fine-Tuning (RFT) framework for personalized agentic reasoning. At its core, ODYSSE proposes Episode-wise GRPO (ESPO), a novel extension of Group Relative Policy Optimization (GRPO) designed to address long action horizons and strong cross-step dependencies in personalized agentic reasoning. Rather than optimizing individual steps independently, ESPO introduces an episode-level reward mechanism together with episodic advantage estimation, enabling upstream evidence to effectively guide downstream personalized decisions and allowing agents to progressively resolve ambiguous user requests across multiple interaction steps. We further propose an episodic batch sampler that groups actions from the same episode into unified training batches, facilitating coherent optimization under ESPO. We evaluate ODYSSE on realistic long-horizon personalized GUI reasoning tasks. Experimental results demonstrate that ODYSSE consistently outperforms both specialist and general-purpose LVLMs, highlighting its effectiveness for personalized agentic reasoning.

The alignment of Small Language Models (SLMs) in the 70--500M parameter range using reinforcement learning is often considered unstable, though the underlying failure mechanisms have not been systematically investigated. In the State-of-the-Art (SOTA) research, fifteen (model, corpus) configurations were trained using Proximal Policy Optimization (PPO). The experiments included Pythia-70M, 160M, 410M and SmolLM2-135M, 360M on the TinyStories, CNN/DailyMail, and Wikitext-103 corpora. Three reproducible failure modes were identified in small-scale language models: silent LoRA parameter freezing in standard PEFT/TRL pipelines, numerical overflow in importance ratios when using bfloat16, and catastrophic policy collapse due to reward-model error. These issues were addressed using a merge-and-reinitialize adapter technique, float32 precision during PPO updates, and a three-layer safety mechanism comprising reward whitening, importance-ratio guarding, and weight rollback. In this paper, a capacity-headroom hypothesis is proposed, which states that PPO performance at the SLM scale depends on both a fluent supervised model ($\text{PPL}<20$) and a discriminative reward signal, rather than on the number of model parameters. The proposed system converged stably in all experiments and improved preference win rate over the SFT baseline in configurations with a fluent prior and an informative reward signal. Furthermore, it outperformed instruction-tuned baselines while requiring significantly less training data. All checkpoints, preference datasets, and training scripts are publicly released$^§$.

Large language model (LLM) performance increasingly depends not only on the base model, but also on the inference-time controller used to organize reasoning. Existing post-training methods, however, typically optimize for a single fixed interaction pattern, despite real deployments relying on diverse controllers such as Chain-of-Thought, self-consistency, debate, planning, and verification pipelines. This creates a training--deployment mismatch and limits transfer to new workflows. We introduce CALM (Controller-Aware Language Models), a post-training framework that explicitly places controllers in the training loop. We formulate controller-aware post-training as multi-task reinforcement learning over controller-induced interaction protocols, where controllers are compositions of reusable local reasoning modules. This structure also induces a module-level decomposition of mixed-controller training under a turn-level GRPO objective, enabling a systematic study of controller and module-aware training strategies. We evaluate CALM on held-out controller compositions and broader controller shifts, showing that controller-aware post-training improves generalization across inference-time workflows beyond single-controller optimization.

Group Relative Policy Optimization (GRPO) is the dominant reinforcement learning algorithm for training reasoning capabilities in large language models, notably adopted by DeepSeek-R1. The recent improvement Dr. GRPO (COLM 2025) identifies the response-level length bias caused by per-trajectory length normalization in GRPO and proposes removing this normalization, claiming the resulting optimizer is "unbiased." We show that this claim is incomplete. Specifically, we establish an impossibility theorem: under the standard outcome reward + GRPO setting, no length-based weighting scheme can simultaneously achieve the following two properties. (P1) Gradient unbiasedness: the gradient estimator is an unbiased estimate of the true policy gradient. (P2) Length invariance: each trajectory's effective contribution to the gradient is independent of its token length. GRPO approximately satisfies P2 but violates P1; Dr. GRPO satisfies P1 but violates P2. We characterize the complete tradeoff spectrum via the parametric family f_alpha(L) = L^{alpha - 1}, where alpha = 0 recovers GRPO, alpha = 1 recovers Dr. GRPO, and provide quantitative analysis showing that Dr. GRPO's length bias can cause longer trajectories to dominate gradient updates by a factor proportional to the length ratio. Our results reveal that neither algorithm is universally "done right"; they occupy opposite ends of a fundamental and unavoidable tradeoff.

Large language models (LLMs) deployed in educational settings often behave as direct answerers: they disclose target concepts in the opening turn instead of guiding students through progressive inquiry, as Socratic pedagogy prescribes. We present HeuristicEdu, a two-phase pipeline that aligns Qwen2.5-7B toward Socratic tutoring via supervised warm-up and Group Relative Policy Optimization (GRPO). Training uses SocraticEdu, 797 multi-turn Chinese children's science dialogues reconstructed from a live platform, with a heuristic reward over cognitive depth (R_cog), curiosity engagement (R_eng), and directness (R_dir), together with a K_query correction for student-introduced terms. We introduce Scaffolding Effectiveness (SE) and Conversation Depth (CD) to evaluate outcomes beyond surface fluency. On 30 held-out questions, the best GRPO variant improves SE from 30.0% to 63.3% and lowers keyword leakage from 30.0% to 13.3%. Notably, this best variant omits the directness penalty during optimization, suggesting that explicit anti-leakage terms can conflict with gradient-based behavioral alignment. An unaligned Qwen-72B baseline reaches 0% SE and 96.7% leakage, showing that scale alone does not induce Socratic behavior.

Natural Policy Gradient (NPG) is a well-established Reinforcement Learning algorithm that underlies widely used methods such as Trust Region Policy Optimization and Proximal Policy Optimization, both of which have demonstrated strong empirical success. In this paper, we study exact NPG in finite-horizon Markov Decision Processes with known dynamics and horizon-dependent transition kernels. We provide the first finite-time convergence guarantees for this algorithm in this setting, for which we consider both constant and increasing step size regimes. With a constant step size $η_t=η$, we prove that NPG converges sublinearly with a rate of $\mathcal{O}(H^{2}/t)$ after $t$ iterations, where $H$ is the horizon length. We also extend this constant step size analysis to linear MDPs in an exact population-projection oracle under a full support projection distribution, recovering the same sublinear rate as in the tabular setting. Furthermore, with increasing step sizes, we prove that this algorithm achieves a linear convergence rate of $\mathcal{O}\left(\left(1-\frac{1}{\vartheta_ρ}\right)^t\right)$ for a problem-dependent constant $\vartheta_ρ> 1$, and the horizon-only robust schedule of the form $η_t=η_0(H/(H-1))^t$ where $η_0>0$ and $H \geq 2$, attains this same geometric rate.

Off-Policy Evaluation and Learning (OPE/L) in contextual bandits is rapidly gaining popularity in real systems because new policies can be evaluated and learned securely using only historical logged data. However, existing methods in OPE/L cannot handle many challenging but prevalent scenarios such as few-shot data, deterministic logging policies, and new actions. In many applications, such as personalized medicine, content recommendations, education, and advertising, we need to evaluate and learn new policies in the presence of these challenges. Existing methods cannot evaluate and optimize effectively in these situations due to the notorious variance issue or limited exploration in the logged data. To enable OPE/L even under these unsolved challenges, we propose a new problem setup of Cross-Domain OPE/L, where we have access not only to the logged data from the target domain in which the new policy will be implemented but also to logged datasets collected from other domains. This novel formulation is widely applicable because we can often use historical data not only from the target hospital, country, device, or user segment but also from other hospitals, countries, devices, or segments. We develop a new estimator and policy gradient method to solve OPE/L by leveraging both target and source datasets, resulting in substantially enhanced OPE/L in the previously unsolved situations in our empirical evaluations.

Reinforcement learning with verifiable rewards (RLVR) has emerged as a highly effective framework for improving LLM reasoning, with methods such as GRPO among its most successful instantiations. However, GRPO relies on repeated generation of long chain-of-thought rollouts. Training time scales with the number of rollouts, a large fraction of which are uninformative. Thus, GRPO is computationally expensive and unstable. To mitigate this, existing approaches either generate a larger pool of rollouts and filter the most informative prompts, or leverage historical signals for filtering at later stages of training. These strategies offer modest performance gains, but slow down the overall process. To address this, we propose VarIance Guided Online Rollout allocation (VIGOR) which instead of allocating a fixed rollout budget per example, begins with a small number of rollouts for all examples in a batch and iteratively allocates additional rollouts to those with the highest group reward variance until a fixed total rollout budget is reached. Theoretically, we show that under RLVR, reward variance controls the gradient magnitude, and derive VIGOR's closed-form speedup ratio over GRPO, which grows with refinement rounds under Pareto-distributed reward variance. Experiments on mathematical reasoning and coding tasks show that VIGOR reaches target accuracy with up to 2.3$\times$ fewer rollouts on math, reaches GRPO's final coding full pass rate with 1.49$\times$ fewer rollouts, and improves the coding average test pass rate by 3.4 points.

Recent large reasoning models often develop long chain-of-thought responses during reinforcement learning (RL), resulting in high inference latency and deployment cost. Existing methods for response length control typically rely on explicit length penalties or additional control modules, which require careful tuning and may compromise reasoning quality. We propose Quadrant-weighted Sampling for Length-aware Policy Optimization (QLPO), a simple resampling-based variant of GRPO that introduces implicit length control without modifying the reward function. QLPO first over-generates candidate responses and then resamples the training group by preserving the empirical correct/incorrect ratio while favoring short correct responses and long incorrect responses. This reshapes the training distribution and implicitly encourages shorter model outputs. Across models ranging from 1.5B to 32B parameters, including both base models and strong reasoning models, QLPO consistently improves the accuracy-length trade-off. It reduces response length by 30% to 70% while preserving reasoning performance. These results suggest that structured resampling provides an effective and robust approach to efficient reasoning.

In this work, a quantum architecture search framework for approximate quantum state preparation (QSP) is proposed. QSP is a challenging task, since the search space grows exponentially with the number of qubits, making the identification of the optimal circuit non-trivial. To address this problem, deep reinforcement learning is employed through an agent based on proximal policy optimization. The objective of the agent is to identify the best possible approximation of the target state while simultaneously minimizing the number of gates used. At each step, the agent appends a new gate to the circuit and recomputes the fidelity between the approximated state and the target states. Various experiments have been performed from 2 to 5 qubits. Both predefined states, such as Bell, GHZ, W, and Dicke states, and completely random states are considered. The proposed framework is able to achieve approximation errors of $10^{-14}$.

Multi-drone payload transportation has emerged as a promising research paradigm with potential applications in construction, logistics, and disaster response. However, the complex coupled dynamics among drones, cables, and payloads pose significant challenges, and existing approaches remain limited in safety and scalability, particularly in dynamic and unstructured environments. In this work, we propose a learning-based framework for safe and scalable multi-drone cooperative payload transport. We introduce a minimal 2D abstraction that preserves the task-relevant drone-payload coupling required for coordination and safety, while remaining computationally efficient for large-scale learning. Using domain randomization over team size and physical parameters, we train a fully distributed policy via Discrete Graph Control Barrier Function Proximal Policy Optimization (DGPPO), enabling robust zero-shot sim-to-real transfer without fine-tuning. Extensive real-world evaluations demonstrate that a single learned policy generalizes across varying team sizes and task scenarios. Furthermore, multi-group hardware experiments show that the same policy can safely operate in dynamic environments, where other drone teams act as moving obstacles. These results indicate that the proposed framework enables efficient, safe, and scalable multi-drone payload transportation with strong generalization to complex real-world conditions.

Group-based policy optimization has been increasingly used to train large language model (LLM) agents from sparse outcome rewards by comparing trajectories or steps within a group. However, on difficult long-horizon tasks, this comparison can suffer from a sampling imbalance: repeated or low-effect actions dominate the high-probability region of the policy while useful state-changing actions remain under-sampled. This imbalance produces many all-failed rollout groups, where outcome rewards provide no direction for correcting the policy. Together, these effects can form a self-reinforcing credit trap: failure-dominated sampling yields no outcome-based correction, allowing repeated low-effect actions to persist. To break this loop, we propose Progress-conditioned Group Policy Optimization (ProGPO), which uses first-visit observation coverage only when all samples in a group receive zero outcome reward. Specifically, within such groups, ProGPO assigns higher relative advantages to trajectories or steps that visit more new states since reaching new observations is a prerequisite for task success. Experiments on two challenging agentic benchmarks, ALFWorld and WebShop with Qwen2.5-1.5/7B-Instruct, show that ProGPO consistently improves over group-based baselines, with particularly large gains on hard tasks.

Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models. Yet, typical RLVR approaches fail on difficult problems: when a model cannot generate any correct solutions, it receives \textit{zero} learning signal. Providing privileged guidance during training, such as solution prefixes, can help overcome this learning cliff by steering the model towards {correct solutions with non-zero reward}. {We call these rollouts \textit{off-context}: they are generated from a training prompt that contains privileged guidance, while the target objective is defined by the original prompt without that guidance.} {We introduce} Off-Context GRPO (OC-GRPO), a minimally modified variant of GRPO that uses guided rollouts but applies an importance-corrected objective to steer the update back toward the original unguided objective, avoiding the mismatch that destabilizes uncorrected guided training. Empirically, our algorithm achieves a 3.9% absolute improvement (13.8% relative gain) over vanilla GRPO on average across standard mathematical reasoning benchmarks with negligible additional cost.

Medical imaging is a cornerstone of diagnostics, yet automated chest X-ray report generation struggles with structural adherence, anatomical completeness, and semantic faithfulness. We introduce DobicVLM, a vision-language model combining supervised fine-tuning on MedGemma-4B with Group Relative Policy Optimization (GRPO) and clinically-grounded programmatic rewards. Our approach uses interpretable, rule-based reward components; structural verification, anatomical checklist, semantic similarity, and length constraints to enforce clinical standards without neural reward models. Trained on 1,000 de-identified image-report pairs from a private clinical dataset (with ethics approval and compliance to local regulations), DobicVLM is evaluated via blinded expert review on 69 held-out cases. DobicVLM outperforms Gemini 2.5 Flash across the majority of criteria, achieving the highest impression accuracy (27.2%) and medical terminology (86.5%) compared to both Gemini 2.5 Flash and MedGemma 4B baselines, with minor trade-offs in completeness and referrals. This demonstrates GRPO's value for transparent alignment in resource-limited settings. Keywords: Vision-Language Models, Radiology Report Generation, Reinforcement Learning, Medical AI, GRPO

With the rapid advancement of large language models (LLMs), modern systems not only possess strong foundational capabilities and extensive knowledge, but can also solve complex problems via long, multi-step reasoning. However, as reasoning traces become longer, LLMs may produce a substantial amount of hallucinated content during the reasoning process, which is often difficult to detect. In this work, we conduct a fine-grained analysis of hallucinations arising in LLM reasoning and find that the reasoning traces are particularly prone to Context-Sensitive Factual Hallucinations: cases where the model actually has the relevant knowledge, yet makes factual errors due to contextual interference during reasoning. To address this issue, we propose Step-level Self-Consistency Group Relative Policy Optimization (SSC-GRPO), which assigns step-level rewards to reasoning traces by computing self-consistency scores of individual steps across multiple rollouts. Compared with prior methods, SSC-GRPO achieves state-of-the-art performance on both mathematical reasoning benchmarks and hallucination leaderboards. Our results offer a new perspective for detecting and mitigating hallucinations in the reasoning process of large language models.

Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback, where sampled rollouts can be compared within a group using task-provided correctness signals. However, extending group-relative optimization beyond verifiable settings is challenging because success in many tasks is not captured by a single correctness criterion. We propose \textbf{Reference-Relative Policy Optimization (RRPO)}, which generalizes GRPO by replacing direct correctness-based advantage construction with reference-relative contrastive comparisons. RRPO first uses \emph{stratified conditional rollouts} to construct positive and negative anchor sets, and then trains a metric projection head with a set-contrastive objective to compare candidate rollouts against these anchors. The resulting alignment scores directly define contrastive advantages: during policy optimization, the projection head is frozen, and the scores are centered within each rollout group in a standard group-relative objective. We evaluate RRPO using anchor-based contrastive advantages throughout policy optimization, without relying on task ground-truth verifiers. Across verifiable reasoning, open-ended generation, and post-SFT settings, RRPO remains competitive with verifier-based optimization, improves over weakly supervised baselines, and provides additional gains after supervised fine-tuning.

PPO and the GRPO baseline studied here use clipped surrogate objectives whose favorable-direction saturation introduces an abrupt change in the scalar objective's derivative. We ask whether Output Reset (OR), a smooth one-sided saturation rule, offers a useful alternative for large language model post-training. PPO-OR and GRPO-OR replace the clipped policy term with an OR squared-margin loss in rollout-relative token log-ratio space; the advantage sign determines the update direction, and a token contributes zero direct OR residual after crossing the favorable margin. We compare PPO-clip with PPO-OR under generalized advantage estimation (GAE), and GRPO with GRPO-OR under group-relative advantages, using \texttt{Llama-3.2-1B-Instruct} on Anthropic \texttt{hh-rlhf} with one shared reward model and three seeds per method. Under GAE, PPO-OR has a mean final training-time reward-model score $0.305$ higher than PPO-clip, with a larger observed across-seed spread. Under group-relative advantages, GRPO-OR does not have a higher mean score, but shows a smaller observed spread, a near-zero terminal OR residual, and a declining overshoot fraction, while the matched GRPO clipped-objective trace remains variable. Both group-relative methods exhibit substantially larger rollout-to-current log-ratio displacement than the GAE methods, and OR does not consistently reduce it. Thus, OR changes optimization behavior in both matched comparisons, but the observed reward effect differs between them. At $G=2$, the GRPO-OR diagnostics do not translate into a reward-score gain. Whether larger groups change this outcome remains open. The reported scores are training-time reward-model measurements, not held-out human-preference performance.

Rubric-based RL has recently shown promise in improving LLMs on open-ended tasks. A widely recognized limitation of rubric-based RL is limited exploration: criteria that no rollout manages to satisfy (Unexplored Criteria, UC) receive no optimization signal. Recent methods address this by incorporating rubric information as external guidance during rollout, yet they introduce a train-inference mismatch: the policy is optimized on rollouts produced under external guidance while this guidance is absent at inference time, causing error accumulation through autoregressive decoding. Moreover, these exploration-focused approaches overlook a fundamentally different failure mode that we term Suppressed Criteria (SC) -- criteria that are satisfied by some rollouts yet whose learning signals are lost during optimization because scalar reward aggregation assigns them non-positive aggregate advantages. Our analysis reveals that SC are remarkably prevalent: over 57% of samples exhibit this failure mode throughout training, with an average of 1.8 SC per sample. To simultaneously address both UC and SC without introducing training-inference mismatch, we propose Criterion-Distilled Policy Optimization (CriPO), which enhances rubric-based RL via on-policy self-distillation. For UC, CriPO constructs a criterion-injection self-teacher and computes a localized forward-KL loss to inject missing behaviors into the policy. For SC, CriPO employs a counterfactual self-teacher to locate criterion-relevant tokens in negative-advantage rollouts and flips their token-level advantages to positive values, preserving useful patterns that would otherwise be suppressed. Experiments on medicine and science benchmarks demonstrate that CriPO consistently outperforms rubric-based RL, achieving stronger final performance with approximately $2\times$ fewer optimization steps.

Multi-task neural solvers aim to handle multiple Vehicle Routing Problem (VRP) variants within a unified model, avoiding separate training for each constraint combination. However, VRP variants differ in optimization difficulty, while existing methods lack stage-wise feedback on their training status, making the model biased to some specific variants. Although meta-learning can support adaptive training, it typically requires bi-level optimization and additional gradient updates, increasing computational cost. To address this limitation, we propose LLM-as-Trainer (LaT), a plug-and-play training paradigm that uses a pretrained large language model as an external trainer. LaT periodically analyzes cross-task validation metrics to generate a stage-wise guidance vector. This vector is combined with the current task's constraint vector and injected into each encoder layer, providing the neural solver with additional training information during subsequent policy optimization. Experiments on 16 VRP variants show that LaT improves the solution quality of several state-of-the-art multi-task neural solvers on both trained and unseen variants, supporting the effectiveness and generality of the proposed training paradigm.

Group Relative Policy Optimization (GRPO) is a powerful reinforcement learning algorithm for aligning generative models with human preferences. While successful in large language models~\cite{shao2024deepseekmathpushinglimitsmathematical}, its extension to diffusion and flow matching models introduces a severe computational bottleneck: gradients must be back-propagated through the high-capacity DiT backbone at \emph{every} timestep of the sampling trajectory, making high-resolution text-to-image (T2I) training prohibitively expensive. Training-free DiT inference acceleration methods (e.g., $Δ$-DiT, ScalingCache) exploit the fact that DiT hidden states and velocity predictions vary \emph{smoothly and nearly linearly} along the trajectory. We ask whether the same linearity can reduce the backward-pass cost of DiT RL training, and answer affirmatively with \textbf{JAGG} (\textbf{J}acobian-\textbf{A}ggregated \textbf{G}roup \textbf{G}radient), which reduces full transformer backward passes from $W$ to $2$ per group of $W$ consecutive steps. JAGG approximates intermediate-step Jacobians via $t$-weighted interpolation of the endpoint Jacobians, then aggregates per-step upstream signals into two composite gradients applied through a single joint backward pass. We prove this interpolation is \emph{exact} when the velocity is linear in $(z,t)$, and a cosine-similarity routing rule (\texttt{jagg_frac}) deploys JAGG only where the assumption holds. Experiments on T2I benchmarks show JAGG delivers $\sim$2$\times$ backward speedup with negligible quality degradation. The code for this work can be accessed through https://github.com/SchumiDing/JAGG.