Reward Modeling

Monte Carlo Tree Search (MCTS) is a powerful framework for solving complex decision-making problems, yet it often relies on the assumption that the simulator and the real-world dynamics are identical. Although this assumption helps achieve the success of MCTS in games like Chess, Go, and Shogi, the real-world scenarios incur ambiguity due to their modeling mismatches in low-fidelity simulators. In this work, we present a new robust variant of MCTS that mitigates dynamical model ambiguities. Our algorithm addresses transition dynamics and reward distribution ambiguities to bridge the gap between simulation-based planning and real-world deployment. We incorporate a robust power mean backup operator and carefully designed exploration bonuses to ensure finite-sample convergence at every node in the search tree. We show that our algorithm achieves a convergence rate of $\mathcal{O}(n^{-1/2})$ for the value estimation at the root node, comparable to that of standard MCTS. Finally, we provide empirical evidence that our method achieves robust performance in planning problems even under significant ambiguity in the underlying reward distribution and transition dynamics.

A walking robotic hand must use the same fingers to move its body, support its weight, and interact with the environment. We show how an anthropomorphic hand can learn these skills while retaining its finger design and position controller. Onboard power and computation make the platform self-contained. Our reinforcement learning approach accounts for the hand's unequal fingers, with training in a simulator calibrated from hardware measurements. In simulation, the hand moves faster with our reward formulation than with tuned rewards originally designed for quadrupeds. On hardware, task-specific policies enable untethered crawling, steering, and fall recovery. While supporting its own weight, the hand also executes successive keyboard commands without vision and pushes an object to targets using overhead visual feedback. These results demonstrate a compact mobile manipulator that reuses its fingers for locomotion and interaction, without a separate locomotion mechanism.

Formulaic alpha discovery is a pool-dependent symbolic search problem in which informative feedback is observed primarily when a complete expression is evaluated. This delayed feedback creates two coupled difficulties: the retained alpha pool does not preserve the full history of realized evaluation feedback, and the value of an intermediate construction action is uncertain because its consequence depends on the formula eventually completed. We introduce AlphaRJM, which addresses these difficulties through Reward-Jump Memory, an event-driven latent state that remains fixed during token construction and updates only at terminal evaluation events using the realized pool reward and evaluation outcome, and an action-conditioned SDE return critic that represents future discounted discovery returns with stochastic particles. The particles guide action selection through their mean and uncertainty and are learned using a distributional Bellman objective combining energy-distance matching, mean calibration, and jump regularization. Empirically, AlphaRJM delivers strong and stable gains across multiple equity universes, forecasting horizons, and random seeds, while ablations confirm the complementary roles of persistent evaluation history, stochastic return modeling, and distributional supervision.

Recent offline reinforcement learning (RL) studies report policies that outperform physician decisions on clinical outcomes. We conduct a systematic, partially crossed evaluation of five offline RL algorithm families and 14 reward designs in 44,894 post-2018 acute ischemic stroke patients from a nationwide registry (N = 129,033). Standard Fitted Q-Evaluation (FQE) yields an apparent policy-improvement estimate of +0.0069; adding an Early Neurological Deterioration penalty increases it to +0.0101. We identify reward-embedded confounding, in which a proxy terminal reward encodes baseline severity and prognosis as well as treatment efficacy. A 2 x 2 factorial analysis finds that terminal reward confounding accounts for 218.6% of the observed signal change, so its removal overshoots the null. After DML-inspired GBM reward residualization, the FQE estimate attenuates to +0.0033 (p = 0.132), and full deconfounding yields +0.0025 (p = 0.291). FQE-based diagnostics, T-learner analyses, and direct recurrence analyses converge away from a clinically meaningful aggregate improvement. A 1-year mRS factorial analysis replicates the attenuation. We provide an empirically motivated six-step evaluation checklist. NIHSS-stratified heterogeneity is hypothesis-generating for prospective trial design; hospital-level disagreement does not persist after full reward deconfounding.

Using reinforcement learning to post-train joint video-audio generation models requires a reward signal. Existing methods construct this reward by combining metrics for individual quality dimensions, including audio quality, visual fidelity, and synchronization. However, these metrics evaluate perceptual dimensions separately and fail to capture the overall semantic and temporal coherence among the text prompt, video, and audio that shapes human preferences. Optimizing models against these metrics encourages reward hacking, generating video-audio content that achieves high scores on these metrics yet appears incoherent or unfaithful to human viewers. To address this problem, we first construct a large-scale human-preference dataset VAPref-10K for joint video-audio generation, comprising 9K prompts and 10.3K fine-grained paired comparisons from open-source generation models. We also introduce the VA-Judger-Bench benchmark with both in-domain and out-of-domain model comparisons to evaluate whether reward models truly align with human preferences. We further propose VA-Judger, a chain-of-thought omni-reward model for joint video-audio generation. In particular, VA-Judger first learns from pairs with clear quality gaps to establish structured output and coarse preference discrimination, then distills reliable preference explanations for harder near-quality comparisons via rejection sampling verified against human annotations, and finally performs dimension-wise reinforcement learning that decomposes human feedback into individual quality dimensions for denser reward signals than a single binary preference label. Experiments show that VA-Judger outperforms metric baselines in predicting human preferences on both in-domain and out-of-domain evaluations. Using its human-aligned rewards for post-training audio-video generation model also yields significant improvements in generation quality.

Personalizing marketing messages with contextual multi-armed bandits (CMABs) drives real business value, yet the objective that ultimately matters - a downstream conversion - is observed only weeks later, too late to drive online learning. Teams therefore train the bandit on a fast proxy reward, and separately must judge whether a contextual bandit is worth its complexity over sending one best message. Settling both decisions with the usual offline checks - a batch off-policy estimate, a marginal arm-discrimination test, a confidence interval - can mislead systematically under delayed feedback. We give an ordered diagnostic protocol that screens a reward-and-policy candidate on two axes, alignment (does optimizing the reward move the north-star?) and learnability (can the bandit identify the reward-optimal policy?), before trusting any reported lift. We validate it where the truth is known - a public off-policy-evaluation benchmark and a controllable synthetic generator - and illustrate it on a deployed large-marketplace push system (where, with five arms and one split, the evidence is directional rather than powered). Two lessons recur. (N1) A single offline number can mis-rank rewards: a denser reward signal gives the bandit more to learn from, so rewards that look tied in a static estimate pull apart once learning happens online. (N2) If you cannot tell in advance which single message is best, a per-user policy partly just avoids betting on the wrong one - that looks like personalization but is really robustness, so a "personalization premium" is easily overstated. Our contribution is methodological rather than algorithmic: the ordered protocol, the two lessons it surfaces, and the end-to-end experience of applying it to a delayed-feedback CMAB.

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.

Large language models are increasingly aligned to human preferences via reward modeling, but user preference data are sensitive and often cannot be centralized. Federated learning keeps such data local while learning a shared initial reward model, which is later personalized for each client through local fine-tuning. Because users often assign opposite labels to the same pair of responses, existing federated methods address preference heterogeneity by clustering similar clients and training one reward model per group, assuming that each group requires its own initialization. We show that this assumption is unnecessary. Under balanced preference groups, a single FedAvg model, despite starting at nearly random accuracy, surpasses reward models trained separately for each ground-truth group after only a few local optimization steps. We attribute this phenomenon to the flatness of the shared initialization: averaging across all clients learns richer shared representations that distinguish responses while canceling conflicting preference directions, leaving the model near a decision boundary that can be rapidly adapted. Group imbalance breaks this effect as the cancellation becomes asymmetric and leaves minority clients too far from the boundary to recover. Motivated by this observation, we propose FedGD (Federated Learning with Group Debiasing), which discovers latent preference groups during federated training and learns a single reward model using group-debiased client sampling. By counteracting the effect of group imbalance, FedGD learns an initialization that remains highly adaptable, enabling effective personalization without prior knowledge of the underlying groups.

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.

Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks. Rubric-based judges offer a transparent way to decompose such judgments into explicit evaluation criteria, but existing annotation-free rubric generators typically rely on a single generic evaluator. As a result, they may overlook important dimensions of human preference, a failure mode we term dimensional blind spots. To address this limitation, we propose Multi-Role Rubric Generation (MRRG), a training-free and reference-free framework that elicits evaluation criteria from multiple complementary roles and consolidates them into an auditable rubric-based scorer. This scorer can be used both to validate pairwise preferences and to provide rewards for GRPO-style Reinforcement Learning with Verifiable Rewards (RLVR). Experiments on preference validation benchmarks show that MRRG consistently outperforms single-role rubric generation baselines across multiple backbone models. Further RLVR experiments demonstrate that MRRG yields a stronger reward signal for improving open-ended generation.

The development of decision-pretrained transformers, algorithm distillation, long-context meta-RL, and retrieval-augmented agents has renewed interest in in-context reinforcement learning (ICRL): the ability of a pretrained or fine-tuned decision model to infer latent task rules and improve future behavior from interaction context, without test-time parameter updates. This line of work asks when trial-and-error evidence, rewards, transitions, demonstrations, feedback, or retrieved experience can make learning-like computation happen inside the context window. However, existing surveys of ICRL mainly organize the field around pretraining objectives, architectures, context formats, evaluation protocols, and theoretical mechanisms, while the non-stationary setting remains comparatively underexamined. In changing environments, accumulated context is not merely more evidence about a fixed task: the reward specification, transition kernel, observation channel, action interface, constraint model, or demonstration and memory distribution can fall out of alignment with the current regime. Previously useful context can therefore become stale, misleading, or useful again when an old regime returns. We survey non-stationary ICRL as the problem of adapting through context while deployed policy parameters remain fixed: the policy must infer both the current decision rule and which parts of its accumulated evidence still support that rule. We define non-stationary ICRL, relate it to meta-RL, decision sequence modeling, retrieval-augmented RL, value- and model-aware ICRL, and reward-feedback agents, and organize the literature along three questions: what changes, how the change unfolds, and how observable the change is to the agent.

We develop a first-principles reduced-order model of these dynamics. Under a single mean-field assumption that summarizes the policy by its expected reward, we reduce the GRPO update to a stochastically-forced damped oscillator whose mass, damping, and stiffness are fixed in closed form by the optimizer hyperparameters together with a single measured curvature scale -- momentum supplies the inertia, off-policy lag erodes the damping, and the group size enters, to leading order, as a noise temperature. The reduction has three consequences. First, it subsumes the empirical single-exponential saturation law as its overdamped limit, recasting the fitted plateau, timescale, and size exponent as the fixed point, inverse stiffness, and curvature-scaling exponent of the underlying potential, and adding, through the retained inertial term, the slow-start phase the single exponential cannot represent. Second, it yields predictions tied to independently measurable quantities rather than fitted ones: group-size invariance of the deterministic trajectory with a $1/G$ stationary fluctuation, a sharp stability threshold in the refresh interval, and an overdamped-to-oscillatory transition. Third, it furnishes diagnostics that separate failure modes a reward curve alone conflates -- reward hacking, advantage degeneracy, policy concentration, and dynamical instability. Across three models and two group sizes, the closed-form trajectory fits training reward to $R^2 \geq 0.91$ and the mean trajectory is group-size invariant to leading order -- on both the reward curve and out-of-distribution transfer to eight math benchmarks -- while the within-group reward spread retains a residual $G$-dependence that the leading-order temperature picture does not capture.

Hallucination is the reliability bottleneck for LLM-based agents, and fact attribution verifiers are the last line of defense -- yet today's verifiers emit only opaque binary labels, leaving agents unable to self-correct and operators unable to audit. We present SEVA, a structured verification agent that emits evidence alignments, step-by-step reasoning chains, calibrated confidence, and a six-category error diagnosis with actionable fixes. Training such an agent with RL is non-trivial: standard binary reward on multi-component output triggers advantage collapse -- within-group reward variance vanishes and the GRPO gradient disappears. We resolve this with a process reward that decomposes verification quality into five independent components weighted 70/30 toward process signals, restoring the gradient and inducing an implicit curriculum -- the agent first masters verification behavior (alignment 0.917 -> 0.997, format 72% -> 100%), then outcomes (F1 64.9 -> 69.0). Structured output further enables a Verify -> Reflect -> Probe -> Refine self-evolution loop, which over four rounds on a 7B model surfaces an unexpected structural finding: each round produces a benchmark-specialist, not a generalist (+15 pp on HaluEval, -10 to -14 pp on TruthfulQA in the same model, persistent at 4x data). On ClearFacts, SEVA-3B matches GPT-4o-mini (69.0 vs. 69.8 F1) while producing substantially richer, auditable output -- confirming a principle that should generalize: for any RL task with multi-component generation, reward granularity must match output granularity.

Critic-free reinforcement learning with verifiable rewards (RLVR), exemplified by Group Relative Policy Optimization (GRPO), avoids training a value function (critic) and reduces memory and compute overhead relative to critic-based PPO pipelines for aligning large language models. However, GRPO-style advantage estimation depends on prompt-local (within-prompt-group) reward statistics and can be unstable. In particular, when all rollouts in a prompt group receive identical rewards, the within-group reward variance becomes zero, and group normalization yields zero advantages for that group, impeding learning in cold-start regimes with binary verifiers. We introduce BV-Blend, a critic-free framework that stabilizes advantage estimation by combining prompt-local on-policy statistics with semantic-cluster-conditioned historical moments. BV-Blend maintains EMA-tracked reward moments for each cluster, derives a confidence weight from a standard error of the mean (SEM) proxy, and uses this weight to blend historical and prompt-local baseline and variance statistics into a standardized advantage for PPO-style clipped updates. Experiments on verifiable reasoning benchmarks show that BV-Blend improves training stability and performance, and remains robust in regimes where group-normalized methods may stall.

Process reward models (PRMs) enhance the reasoning capabilities of large language models (LLMs) by providing fine-grained feedback, yet training PRMs typically requires expensive stepwise annotations. Outcome-supervised PRMs offer a scalable alternative by learning from final-answer correctness alone, but this introduces a fundamental credit assignment challenge, i.e., attributing outcomes to responsible reasoning steps. Existing approaches rely on either uniform or causal assignment, both of which fail to anchor credit in step correctness and thus hinder process error identification. In this work, we propose Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment (LCA), an outcome-supervised PRM framework that jointly learns credit assignment and reward modeling under the principle of Weakest Link Assignment: a reasoning chain is as strong as its weakest link. To address mutual dependence between credit assignment and reward modeling, we formalize outcome-supervised PRM as a Multiple Instance Learning (MIL) problem and introduce Softmax-Weighted-Sum (SWS) pooling, an MIL pooling technique tailored for strong dependence and redundancy among reasoning states. We prove Bayes consistency of our algorithm under mild assumptions. Extensive experiments demonstrate that LCA consistently outperforms state-of-the-art outcome-supervised PRMs across multiple tasks and backbones. Code is available at https://anonymous.4open.science/r/LCA.

Can representations learned for image generation also support the evaluation of generated images? We study text-to-image reward prediction as a downstream task of generative representation learning. To this end, we introduce DiT-Reward, which converts a pretrained text-to-image Diffusion Transformer into a reward model by processing near-clean image latents and aggregating text-conditioned image representations across transformer layers. Under the same training data mixture as HPSv3, DiT-Reward outperforms HPSv3 on all four evaluated preference benchmarks, reaching 85.6% on HPDv2 and 77.6% on HPDv3. When the generative backbone is frozen, a lightweight learned head can still extract meaningful preference predictions from its representations. Probing across depth further reveals that downstream reward performance is strongest in the middle-to-late layers and benefits from combining representations across different stages. We also observe consistent positive scaling with generative backbone capacity. Finally, when used to optimize Stable Diffusion 3.5 Large with Flow-GRPO, DiT-Reward outperforms HPSv3 along the matched training trajectory, with particularly clear gains in realism. Direct latent scoring also achieves a 1.65x inference speedup over HPSv3 with comparable peak memory. These results show that pretrained generative DiTs provide transferable representations for reward modeling and policy optimization.

This paper introduces an interpretation of Temporal Behavior Trees (TBTs) as Reward-Petri-Nets (RPNs) for reinforcement learning (RL). Designing reward functions for complex, long-horizon robotic tasks is notoriously difficult, especially when tasks have hierarchical structure and temporal constraints. TBTs extend conventional behavior trees (BTs) used in robotic applications by incorporating temporal properties into their leaf nodes. This allows TBTs to represents not only the behavioral task structure defined by BT operators such as Sequence, Fallback, and Parallel, but also the task's temporal constraints. In this work, the constraints are specified in the leaf nodes using Linear Temporal Logic. In order to inform RL rewards using TBTs, we provide a translation from TBT into a Petri Net (PN) and show how rewards can be automatically assigned based on the TBT's structure, resulting in a RPN. In a series of increasingly challenging environments, we demonstrate how TBT-based rewards enable learning where vanilla RL fails, improve sample efficiency, and offer flexible, intuitive control over the learning progress. We showcase the learning impact by using different reward distribution schemes and TBT structures.

The temporal structure of reward composition in reinforcement learning (RL) is typically hand-designed and held fixed throughout training, leaving the progression of motivational priorities largely unexplored. In this work, we propose an evolutionary framework for discovering developmental reward schedules, in which three distinct biologically inspired motivational components -- agency, novelty, and reactivity -- are combined through time-varying weights that dynamically shift over the course of training. Evaluated on two sparse-reward MiniGrid tasks: DoorKey-6x6 and KeyCorridorS3R1, our framework compares the generalizability of four evolutionary algorithms: CMA-ES, xNES, DE, and L-SHADE against an extrinsically motivated baseline (our main comparison point), and three additional hand-designed methods. On DoorKey-6x6, all evolved methods outperform the non-evolved baselines, with L-SHADE achieving the best performance -- an approximate relative mean improvement of 11.4% over the extrinsic only baseline. On KeyCorridorS3R1, CMA-ES achieves the best overall performance, with the remaining evolved methods showing weaker and less reliable generalization capability compared to the extrinsic only baseline. Interestingly, the discovered schedules diverge from our defined developmental ordering, with novelty consistently emerging as the dominant early signal during training, across both tasks. Collectively, our results position evolutionary optimization as a promising approach for developmental reward schedule discovery in deep reinforcement learning, and suggest that what evolution finds to be optimal in computational settings may differ from what it finds to be optimal in biology. The code for this project can be found at: https://github.com/alannadels/Evolutionary_RL.git.

The coupling in flow matching -- the rule pairing noise vectors with data points -- is typically treated as a computational choice. We show that this coupling can instead serve as an alignment interface: by matching noise and data according to a target molecular property, it embeds controllable structure directly into the learned flow field. Building on this view, we introduce Reward Transport, which uses optimal transport coupling at training time to align a scalar noise-space coordinate with molecular rewards; at inference, varying this coordinate steers the generated distribution without requiring an oracle, reward model, gradient guidance, or additional computation. In the coupling-preserving limit, thresholding this coordinate recovers the Cross-Entropy Method's truncated reward distribution, providing a principled, continuously adjustable distribution-level control knob. Empirically, on ZINC-250K and GuacaMol, sweeping the scalar induces monotone control of logP and consistent QED control over its operating range; most tellingly, the same knob produces opposite structural responses for different targets, growing molecules for logP but shrinking them for QED, which rules out a generic size bias. The interface is complementary to classifier-free guidance and conditional flow matching, while a negative result under epsilon-prediction diffusion clarifies where coupling-level alignment is structurally absent. Code: https://github.com/KehanGuo2/reward-transport

Multi-Agent Systems (MAS) built on Large Language Models (LLMs) require effective orchestration to coordinate specialized agents, yet training such orchestrators is hindered by limited supervision and high computational cost. We propose Orchestration Reward Modeling (OrchRM), a self-supervised framework for evaluating orchestration quality without human annotations. OrchRM leverages intermediate artifacts from multi-agent executions to construct win-lose pairs for Bradley-Terry reward model training. Unlike existing MAS test-time scaling and orchestrator training frameworks that rely on costly sub-agent rollouts, OrchRM operates directly at the orchestration level, enabling efficient and high-performing reward-guided orchestrator training and MAS test-time scaling. OrchRM improves training efficiency by up to 10x in token usage while improving MAS test-time scaling performance by up to 8% in accuracy. These gains consistently transfer across multiple domains, including mathematical reasoning, web-based question answering, and multi-hop reasoning, demonstrating orchestration-level reward modeling as a scalable direction for robust multi-agent orchestration. Code will be available at https://github.com/Wang-ML-Lab/OrchRM.

Open-ended reward modeling requires judges that can follow subtle, domain-specific preferences when verifiable answers are unavailable. Existing rubric-based methods often address this by generating criteria online for each query, but the extra generation step can add inference overhead and produce rigid or misaligned guidance. We introduce Eval-Skill, an exploration-guided method that synthesizes reusable evaluation skills for reward modeling and reframes reward guidance as context evolution rather than parameter training or per-query rubric generation. Using only 100 cases per domain for skill evolution, Eval-Skill synthesizes reusable domain-level evaluation skills through two progressive stages, workflow generation followed by principle generation, with exploration and selection interleaved across both stages. Once generated, a skill is directly injected into the judge context. Across multiple RM benchmarks, Eval-Skill consistently improves diverse judge backbones; on RewardBench 2, it yields significant gains over vanilla judging for each main backbone (+13.44% for Qwen3-8B, and 18.51% for DeepSeek-V4-Flash). Further analyses of evolution-time scaling, generalizability, and transferability show that compact evaluation skills offer an efficient new paradigm for LLM-based evaluation. Code is available at https://github.com/xing-stellus-yue/Eval-Skill.

Reward models (RMs) provide critical feedback signals for LLM post-training, notably in reinforced fine-tuning (RFT) and reinforcement learning (RL) pipelines. However, current reward evaluation relies on heterogeneous criteria such as rule-based verifiers, ground-truth references, procedural checklists, and complex rubrics, where a unified mechanism to integrate all types of evidence remains unexplored. To this end, we propose Skill Reward Model (Skill-RM), a unified framework that reformulates reward modeling as the execution of a reusable Reward-Evaluation Skill. By treating reward computation as a structured agentic task, Skill-RM provides a consistent interface to orchestrate heterogeneous resources, dynamically selecting and aggregating evidence tailored to the specific requirements of each input. This approach enables the reward model to move beyond static evaluation, ensuring consistency and transparency across diverse tasks. Extensive experiments on reward benchmarks and downstream applications, including best-of-N selection and reinforcement learning, demonstrate that Skill-RM consistently outperforms traditional judge baselines. Our findings suggest that Skill-RM not only provides a unified solution for reward modeling but also achieves superior performance through the strategic and dynamic orchestration of evidence. The code is at https://github.com/Qwen-Applications/Skill-RM.

Recent multimodal large language models have demonstrated strong reasoning ability, yet their reliability as automated evaluators remains limited by a critical weakness: when visual evidence conflicts with textual cues, MLLM judges tend to reward plausible narratives over perceptually correct answers. We identify and systematically analyze this phenomenon, which we term Perceptual Judgment Bias. Through controlled visual perturbations, existing multimodal judges frequently anchor on the response text instead of their own visual perception, leading to inconsistent and non-verifiable evaluations. To address this issue, we introduce the Perceptually Perturbed Judgment Dataset, which constructs minimally edited counterfactual responses that isolate perceptual errors and enable verifiable supervision. Building on this dataset, we develop a unified training framework that combines a structured GRPO-based reward with a batch-ranking objective, achieving coherent global ordering without explicit pairwise labels. Experiments across diverse MLLM-as-a-Judge benchmarks show that our approach substantially improves perceptual fidelity, ranking coherence, and alignment with human evaluation. Our results establish a scalable and generalizable pathway for training multimodal judges that are perceptually grounded, interpretable, and robust to visual-reasoning conflicts.

With the continued advancement of text-to-image (T2I) generation, producing high-quality images is becoming increasingly attainable; consequently, user demands are shifting toward images that better satisfy their specific requirements. As reward models play an increasingly important role in assessing whether generated images align with user preference, this trend introduces an important challenge for reward modeling: rather than relying solely on static and general evaluation dimensions, reward models should account for the task-relevant and fine-grained criteria through which users assess whether generated images meet their specific requirements. To address this challenge, we propose DyCoRM, a dynamic, criterion-aware reward model that grounds task-relevant criteria and performs criterion-aware preference comparison. To support this setting, we construct DyCoDataset-20K, which provides dynamic criteria together with criterion-level annotations, and further derive DyCoBench-1K, a benchmark for systematically evaluating reward models under dynamic criteria. We further introduce DyCoPick, which applies criterion-aware reward modeling to selecting T2I images. Our contributions establish the first reward modeling framework for dynamic and fine-grained evaluation and practical application in T2I generation.

Long-form image captioning exposes a reward granularity problem in RL: captions are judged as whole sequences, while the important errors occur at the level of individual visual claims. A good dense caption should be both faithful and informative, avoiding hallucination without omitting salient details. Yet pairwise preferences, reference-based metrics, and holistic scalar rewards compress these local errors into a single sequence-level signal, obscuring the tradeoff between factuality and coverage. We introduce ClaimDiff-RL, a framework that uses reference-conditioned atomic claim differences as the reward unit for caption RL. Given an image, an actor caption, and a reference caption, a multimodal judge enumerates visually grounded differences, verifies each difference against the image, assigns open-vocabulary error types and severity levels, and produces per-difference statistics for reward composition. This makes hallucinated claims and omitted salient facts separately measurable and tunable. Experiments show that holistic scalar rewards can reduce hallucination by increasing missing facts, while ClaimDiff-RL exposes this faithfulness and coverage tradeoff and enables more balanced operating points. On a 160-image human-labeled diagnostic benchmark, public captioning benchmarks, and VQA benchmarks, ClaimDiff-RL improves the hallucination--missing-fact balance, preserves general capability, and even surpasses Gemini-3-Pro-Preview on several fine-grained Capability dimensions such as object counting, spatial relations, and scene recognition. These results suggest that typed, verifiable claim differences are an effective reward unit for fine-grained and diagnosable caption RL.

Recent image editing models have achieved remarkable progress in instruction following, multimodal understanding, and complex visual editing. However, existing benchmarks often fail to faithfully reflect human judgment, especially for strong frontier models, due to limited task difficulty and coarse-grained evaluation protocols. In parallel, reward models have become increasingly important for RL-based image editing optimization, yet existing reward model benchmarks still rely on unrealistic evaluation settings that deviate from practical RL scenarios. These limitations hinder reliable assessment of both image editing models and reward models. To address these challenges, we introduce Edit-Compass and EditReward-Compass, a unified evaluation suite for image editing and reward modeling. Edit-Compass contains 2,388 carefully annotated instances spanning six progressively challenging task categories, covering capabilities such as world knowledge reasoning, visual reasoning, and multi-image editing. Beyond broad task coverage, Edit-Compass adopts a fine-grained multidimensional evaluation framework based on structured reasoning and carefully designed scoring rubrics. In parallel, EditReward-Compass contains 2,251 preference pairs that simulate realistic reward modeling scenarios during RL optimization.

In LLM Reinforcement Fine-Tuning (RFT), curriculum learning drives both efficiency and performance. Yet, current methods externalize curriculum judgment via handcrafted heuristics or auxiliary models, risking misalignment with the policy's training dynamics. In this paper, we introduce METIS (METacognitive Internalized Self-judgment), a novel framework that internalizes curriculum judgment as a native capability. Leveraging a critical observation that within-prompt reward variance effectively gauges prompt informativeness, METIS predicts this metric based on recent training outcomes as lightweight in-context learning examples. This intrinsic self-judgment then dynamically dictates the training allocation. Moreover, METIS closes the loop between judgment and optimization by jointly optimizing the standard RFT rewards and a self-judgment reward. This allows the policy to learn what to learn next, as a form of metacognition. Across extensive discrete and continuous RFT benchmarks from mathematical reasoning, code generation, to agentic function-calling, METIS consistently delivers superior performance while accelerating convergence by up to 67%. By bypassing handcrafted heuristics and auxiliary models, our work establishes a simple, closed-loop, and highly efficient curriculum internalization paradigm for LLM reinforcement fine-tuning.

Diffusion-based posterior samplers use pretrained diffusion priors to sample from measurement- or reward-conditioned posteriors, and are widely used for inverse problems. Yet their theoretical behavior remains poorly understood: even with exact prior scores, their outputs are biased, and in low-temperature regimes their discretizations can become unstable. We characterize this bias by introducing a tractable surrogate path connecting the true posterior to a standard Gaussian and comparing it to the sampler's path. Their density ratio satisfies a parabolic PDE whose reaction term measures the accumulated bias. A Feynman-Kac representation then expresses the Radon-Nikodym correction as an explicit path expectation, identifying which posterior regions are over- or under-sampled. We apply this framework to DPS and STSL, a related sampler. For DPS, the correction is an Ornstein-Uhlenbeck path expectation coupling the data conditional covariance with the reward curvature, revealing where DPS over- or under-samples. Next, we reinterpret STSL as an auxiliary drift that steers trajectories toward low-uncertainty regions, flattening the spatially varying part of the DPS reaction term. Finally, we characterize early guidance-stopping, a common mitigation for low-temperature instabilities caused by forward-Euler integration of the vector field. Together, these results clarify sampler bias, explain existing correctives, and guide stable variant designs.

Large language models have achieved remarkable progress in text generation but still struggle with generative writing tasks. In terms of evaluation, existing benchmarks evaluate writing reward models coarsely and fail to measure performance from the perspective of specific requirements. In terms of training, existing training methods either use LLM-as-a-judge approaches or train coarse-grained reward models, lacking fine-grained requirement-adherence reward modeling. To address these issues, we propose a fine-grained evaluation pipeline WEval for writing reward models and a fine-grained reinforcement learning training framework WRL. The evaluation data of WEval covers multiple task categories and requirement types, enabling systematic evaluation of writing reward models by measuring the correlation between the rankings of the reward model and gold rankings. WRL constructs positive and negative samples by selectively dropping instruction requirements, allowing for more precise reward model training. Experiments show that our models achieve substantial improvements across various writing benchmarks and exhibit strong generalization. The code and data are publicly available at \href{https://github.com/Rainier-rq1/From_Coarse_to_Fine}{https://github.com/Rainier-rq1/From\_Coarse\_to\_Fine}.

We study stochastic multi-armed bandits in which the objective is a statistical functional of the long-run reward distribution, rather than expected reward alone. Under mild continuity assumptions, we show that the infinite-horizon problem reduces to optimizing over stationary mixed policies: each weight vector $w$ on the simplex induces a mixture law $P^w$, and performance is measured by the concave utility $U(w)=\mathfrak U(P^w)$. For differentiable statistical utilities, we use influence-function calculus to derive stochastic gradient estimators from bandit feedback. This leads to an entropic mirror-ascent algorithm on a truncated simplex, implemented through multiplicative-weights updates and plug-in estimates of the influence function. We establish regret bounds that separate the mirror-ascent optimization error from the bias caused by estimating the influence function. The framework is developed for general concave distributional utilities and illustrated through variance and Wasserstein objectives, with numerical experiments comparing exact and plug-in influence-function implementations.

Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS). Yet, they face significant challenges in complex domains. Error propagation from incorrect intermediate reasoning can lead to false positives for seemingly plausible solutions, while lacking external grounding makes verifiers unreliable on computation or knowledge-intensive tasks. To address these challenges, we propose Agentic Verifier, a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process. We introduce complementary forward and backward agents: one traces solutions from premises to conclusions, while the other re-checks conclusions against their underlying premises. This bidirectional process enables a comprehensive, reliable, and interpretable assessment of solutions. To facilitate practical deployment, we propose AgentV-RL. Through proactive exploration and reinforcement learning, the verifier autonomously interleaves tool-use with internal reasoning. Extensive experiments show that Agentic Verifier yields consistent performance gains under both parallel and sequential TTS. Notably, our 4B variant surpasses state-of-the-art ORMs by 25.2%, positioning it as a promising paradigm for agentic reward modeling.

We study reward poisoning attacks in reinforcement learning (RL), where an adversary manipulates rewards within constrained budgets to force the target RL agent to adopt a policy that aligns with the attacker's objectives. Prior works on reward poisoning mainly focused on sufficient conditions to design a successful attacker, while only a few studies discussed the infeasibility of targeted attacks. This paper provides the first precise necessity and sufficiency characterization of the attackability of a linear MDP under reward poisoning attacks. Our characterization draws a bright line between the vulnerable RL instances, and the intrinsically robust ones which cannot be attacked without large costs even running vanilla non-robust RL algorithms. Our theory extends beyond linear MDPs -- by approximating deep RL environments as linear MDPs, we show that our theoretical framework effectively distinguishes the attackability and efficiently attacks the vulnerable ones, demonstrating both the theoretical and practical significance of our characterization.

Reward modeling is central to alignment pipelines such as RLHF, RLAIF, and PPO-based policy optimization, yet its reliability is constrained by limited and heterogeneous human preference data that are expensive to collect at scale. While synthetic augmentation can expand preference supervision, existing methods often augment uniformly or at the representation level, without targeting examples where the reward model is uncertain or prone to mis-ranking. In this paper, we introduce MARS (Margin and Semantic-Aware Data Augmentation for Reward Modeling), an adaptive augmentation framework that prioritizes low-margin preference pairs and uses semantic distance as a second layer for refinement to enhance the contrast between the chosen and rejected responses. Across multiple preference datasets, reward-model backbones, downstream alignment settings, and benchmarks including RewardBench and AlpacaEval, MARS improves both reward-model quality and alignment performance over existing baselines. Our results show that reward-model augmentation is most effective when guided by both model margins and semantic structure.

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is fundamentally governed by reward design. Despite its importance, the relationship between reward modeling and core LLM challenges--such as evaluation bias, hallucination, distribution shift, and efficient learning--remains poorly understood. This work argues that reward modeling is not merely an implementation detail but a central architect of reasoning alignment, shaping what models learn, how they generalize, and whether their outputs can be trusted. We introduce Reasoning-Aligned Reinforcement Learning (RARL), a reasoning-centric taxonomic perspective that organizes diverse reward paradigms for multi-step reasoning. Within this perspective, we present a taxonomy of reward mechanisms, analyze reward hacking as a pervasive failure mode, and examine how reward signals unify challenges ranging from inference-time scaling to hallucination mitigation. We further critically evaluate existing benchmarks, highlighting vulnerabilities such as data contamination and reward misalignment, and outline directions for more robust evaluation. By integrating fragmented research threads and clarifying the interplay between reward design and fundamental reasoning capabilities, this work provides a foundational roadmap for building reasoning models that are robust, verifiable, and trustworthy.

Reward models are critical for reinforcement learning from human feedback, as they determine the alignment quality and reliability of generative models. For complex tasks such as image editing, reward models are required to capture global semantic consistency and implicit logical constraints beyond local similarity. Existing reward modeling approaches have clear limitations. Discriminative reward models align well with human preferences but struggle with complex semantics due to limited reasoning supervision. Generative reward models offer stronger semantic understanding and reasoning, but they are costly at inference time and difficult to align directly with human preferences. To this end, we propose Joint Reward Modeling (JRM), which jointly optimizes preference learning and language modeling on a shared vision-language backbone. This approach internalizes the semantic and reasoning capabilities of generative models into efficient discriminative representations, enabling fast and accurate evaluation. JRM achieves state-of-the-art results on MMRB2 and EditReward-Bench, and significantly improves stability and performance in downstream online reinforcement learning. These results show that joint training effectively bridges efficiency and semantic understanding in reward modeling.

This survey offers a comprehensive foundation on the integration of RL with language models, highlighting prominent algorithms such as Proximal Policy Optimization (PPO), Q-Learning, and Actor-Critic methods. Additionally, it provides an extensive technical overview of RL techniques specifically tailored for LLMs, including foundational methods like Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF), as well as advanced strategies such as Direct Preference Optimization (DPO) and Group Relative Policy Optimization (GRPO). We systematically analyze their applications across domains, i.e., from code generation to tool-augmented reasoning. Crucially, we move beyond descriptive categorization to provide a rigorous algorithmic analysis of failure modes, mathematically framing the structural bottlenecks and stability trade-offs inherent in policy optimization. We also present a comparative taxonomy based on reward modeling, feedback mechanisms, and optimization strategies. Our evaluation highlights key trends. RLHF remains dominant for alignment, and outcome-based RL such as Reinforcement Learning with Verifiable Rewards (RLVR) significantly improves stepwise reasoning. However, persistent challenges such as reward hacking, computational costs, and scalable feedback collection underscore the need for continued innovation. We also explicate the causal factors behind recent benchmark performances, distinguishing between gains derived from architectural scaling versus those stemming from specific optimization objectives. We further discuss emerging directions, including hybrid RL algorithms, verifier-guided training, and multi-objective alignment frameworks. This survey serves as a roadmap for researchers advancing RL-driven LLM development, balancing capability enhancement with safety and scalability.

Monte Carlo tree search is attractive for robotic manipulation because it can improve action selection through simulation without requiring a fully differentiable policy. In uncertain domains, however, sparse terminal rewards and noisy transitions can make shallow search brittle: many candidate branches remain indistinguishable until late rollouts, and small simulation budgets amplify this ambiguity. This paper presents Reward-Centered ReST-MCTS, a decision-making framework that decomposes intermediate feedback into rule, heuristic, optional neural, and value-estimation channels, centers the resulting process signal against matched task contexts, and uses it to bias or repair search while preserving terminal-task evaluation. The primary evidence is intentionally tiered. Local tasks and matched ManiSkill diagnostics isolate reward-center mechanisms and ablations; matched option-level ManiSkill sweeps test robustness under primitive failure, observation noise, and initial-pose shifts while not claiming standard benchmark superiority; and an official same-backbone OpenVLA-OFT/LIBERO bridge tests bounded VLA action repair. The OpenVLA-OFT clean reproduction reaches 10/10 LIBERO-Spatial successes both with and without RCRM-Guard. A single-suite same-backbone action-channel stress artifact over ten paired LIBERO-Spatial action-channel stress episodes records 0/10 unguarded successes and 9/10 guarded successes. Additional observation-noise, language-perturbation, and visual-distractor probes are reported as coverage and negative-result context rather than superiority evidence. The resulting claim is bounded: Reward-Centered ReST-MCTS is an inspectable test-time verifier for same-backbone high-uncertainty manipulation, not a replacement VLA policy or a broad standard-benchmark superiority claim.

Existing LLM-based agents have achieved strong performance on held-in tasks, but their generalizability to unseen tasks remains poor. Hence, some recent work focus on fine-tuning the policy model with more diverse tasks to improve the generalizability. In this work, we find that finetuning a reward model to guide the policy model is more robust than directly finetuning the policy model. Based on this finding, we propose AgentRM, a generalizable reward model, to guide the policy model for effective test-time search. We comprehensively investigate three approaches to construct the reward model, including explicit reward modeling, implicit reward modeling and LLM-as-a-judge. We then use AgentRM to guide the answer generation with Best-of-N sampling and step-level beam search. On four types of nine agent tasks, AgentRM enhances the base policy model by $8.8$ points on average, surpassing the top general agent by $4.0$. Moreover, it demonstrates weak-to-strong generalization, yielding greater improvement of $12.6$ on LLaMA-3-70B policy model. As for the specializability, AgentRM can also boost a finetuned policy model and outperform the top specialized agent by $11.4$ on three held-in tasks. Further analysis verifies its effectiveness in test-time scaling. Codes will be released to facilitate the research in this area.