Reward Modeling

Follow this topic Ask about this topic

Momentum

24 papers in the last four weeks, up 118% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 197

Oct 7, 2026cs.CL

Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression

Reward modeling often requires jointly representing and reasoning over multiple evaluation criteria, yet verbalizing this process token by token can incur substantial inference cost. Recent work on latent reasoning suggests that continuous states may support this computation more compactly. We introduce LatentGRM, a latent evaluation framework built on semantic chunking, compression, and reconstruction. By using the structure of rubric-guided evaluations to guide compression, LatentGRM learns compact continuous trajectories that support autonomous pairwise judgments without generating textual assessments. A separate interpreter reconstructs evaluation text from these trajectories, providing an offline view of the information retained under compression. Under matched training data and backbones, LatentGRM achieves competitive aggregate preference accuracy relative to explicit Supervised Fine-Tuning (SFT) judges at both 4B and 8B scales. Across four benchmark domains, LatentGRM-8B compresses evaluation trajectories by 8.9--9.2x and reduces total judge inference time by 6.1--7.0x at vote@5. Controlled rubric interventions show that criterion-dependent preference information is carried through the latent sequence. Together, these results demonstrate that continuous latent evaluation can substantially reduce inference cost while preserving competitive judgment quality.

Mingqing Yuan, Xiaobo Liang, Junwei Yang +5

Soochow University · University of Cambridge · Chalmers University of Technology +3

Reward Modeling LLM-as-a-Judge Continuous Latent Reasoning Efficient Language Model Inference

Oct 7, 2026cs.CV

Visual Jev Rewards: Reference-Bound Verification for Multi-Subject Image Generation

Multi-subject image generation requires rewards that verify whether requested attributes, actions, and relations hold for the specified reference subjects. Subject presence alone does not establish that the correct subjects participate in a requested interaction. We present reference-bound Visual Jev rewards that turn these visual decisions into generator training signals. Each subject-related question receives a positive label only when the requested condition and the relevant reference identities hold jointly. We construct fixed questions offline, train a Qwen3.5-4B verifier with binary supervision, and directly read Yes probabilities from its language-model head. Their mean supplies a GRPO reward while retaining individual judgments for inspection. Using 200 MICo-150K training tasks and 30 updates, the framework raises a GPT-5.4 composite score from 41.78 to 52.50 on a manually selected 897-task MICo-Bench subset; direct 27B rewards yield 51.84. Each reward is tested in one GRPO run, and offline human evaluation does not establish a statistically significant advantage over direct scoring. The study provides an initial implementation and evaluation of Visual Jev as a reference-bound reward for multi-subject image generation.

Baoteng Li, Wenzhuo Wu, Kongming Liang +1

School of Artificial Intelligence, Beijing University of Posts and Telecommunications1 · Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance2

Reward Modeling Image Generation Evaluation Image Generation RL for Image Generation Vision-Language Model-as-a-Judge

Oct 6, 2026cs.CV

Personalize at Test Time: Learning User Preferences for Image Generation

Diffusion models can generate high-quality images, yet aligning their outputs with individual user preferences remains challenging. A key bottleneck is accurately modeling diverse user preferences from limited feedback. Existing approaches often rely on labor-intensive manual preference annotations or vision-language models (VLM) to extract preference information from user interaction histories, introducing substantial annotation or computational costs that limit scalability. We propose an approach that learns personalized reward models directly from users' historical image preference pairs. First, we use an autoencoder to compress hundreds of visual attributes into 50 attribute-anchored preference dimensions and train an evaluator to score images along these dimensions. We then represent each user's preferences as a linear combination of the shared dimension scores, estimating the user-specific weights by maximizing the likelihood of their observed pairwise preferences under the Bradley-Terry model. This formulation reduces per-user adaptation to optimizing a low-dimensional weight vector, simplifying optimization and enabling data-efficient personalization from sparse feedback. The learned personalized rewards guide image generation at inference time while keeping the diffusion model frozen. Experiments on real-user preference data show that our approach achieves approximately 77% held-out pairwise preference prediction accuracy and improves the alignment of generated images with individual user preferences.

Jiamu Bai, Jiaming Hu, Yanhong Wu +1

Penn State University · Meta · Boston University +1

User Preference Modeling Diffusion Model Alignment Image Generation Reward Modeling Diffusion Model Guidance

Oct 6, 2026cs.LG

Reinforcement Learning for Hierarchical Reasoning Rewards: Minimax-Optimal Rates with Transformers

Reinforcement learning (RL) has become a standard tool for post-training language models on reasoning tasks, where the policy is updated by reward feedback while exploring the space of responses. Despite its empirical success, theoretical understanding of RL post-training remains limited, in particular of why on-policy exploration combined with a neural reward model is effective. In this paper, we address this question by modeling the reward as a hierarchical function on the response space: the reward consists of infinitely many local components, each of which becomes relevant only after the preceding ones have been resolved. We show that a natural Transformer-based actor--critic algorithm, which alternates between sampling from the current KL-regularized policy, fitting a Transformer critic to the observed rewards, and updating the policy, achieves the minimax optimal rates in the query budget and in the regularization strength up to logarithmic factors, and is minimax optimal for a fixed number of prompts. In contrast, we prove that sampling from the fixed reference distribution, as in offline reward modeling, can limit regret decay to a logarithmic rate. These results show that on-policy exploration progressively zooms in on the region where the reward is concentrated, and quantify its benefit for RL post-training.

Naoki Nishikawa, Taiji Suzuki

The University of Tokyo, RIKEN AIP

Reward Modeling Transformer-Based RL RL for Language Model Reasoning RL Post-Training

Oct 6, 2026cs.CV

Revisiting Numerical Forecasting Models for Language-Based Trajectory Prediction

Language-based trajectory predictors represent coordinates as discrete tokens and learn auxiliary tasks such as destination and group reasoning. This formulation enables the model to capture behavioral intent and social context beyond coordinate dynamics alone. However, token-level objectives provide only indirect guidance for continuous coordinate-space dynamics. To address this limitation, we introduce MoRE (Mixture of Reward Experts), a refinement framework that transfers numerical forecasting priors into a pretrained language-based predictor through reinforcement learning. Five frozen numerical predictors provide complementary coordinate-level knowledge of motion and interactions. Their predictions are converted into expert rewards and combined through an uncertainty-weighted consensus that penalizes disagreement. A ground-truth reward anchors the prediction to the target trajectory. To focus refinement on difficult cases, MoRE refines the policy using the top 1% of training samples ranked by predictive entropy. Expert predictions are computed once and cached before PPO training, so the experts are not run during policy updates or inference. In this way, MoRE combines the contextual modeling of the language-based predictor with coordinate-level feedback from numerical experts. On ETH-UCY, MoRE reduces ADE from 0.22 to 0.20 m and FDE from 0.32 to 0.29 m. Relative to the base policy, ADE decreases by 17.9% on SDD and 12.7% on NBA. On ETH-UCY, MoRE also reduces collision rates and better matches ground-truth pedestrian spacing, without increasing measured inference memory or latency. The project page is available at https://jungyu0413.github.io/MoRE/.

JunGyu Lee, Inhwan Bae, Hae-Gon Jeon

Yonsei University · DGIST

Reward Modeling RL for Language Models Trajectory Generation Pedestrian Trajectory Prediction Trajectory Prediction

Oct 5, 2026cs.CL

Ontology Concept Overlap as a Training Signal: Knowledge-Grounded Reinforcement Learning for Clinical Question Answering

Reinforcement learning post-training for language models relies on two reward designs: human preferences (RLHF, DPO) and binary verifiers (RLVR). Clinical question answering fits neither. Near-correct answers differ by a single substituted entity, and no executable check decides clinical correctness. We instantiate a soft verifier from a maintained controlled vocabulary: UMLS Concept Unique Identifier overlap (via scispaCy, set-level F1) gives a graded, externally specified reward computed without a model in the loop. We combine it inside GRPO with an entropy-normalised LLM judge, which covers the safety and evidence axes overlap cannot see, and a small consistency penalty on padding and repetition that keeps early-training samples scorable. This three-term composite improves over SFT on Phi-3-mini (3.8B) over MedQA by 2.9% on EM (0.700 vs 0.680) and 39% on Token-F1 (0.202 vs 0.145); on Llama-3.2-3B the corresponding gains are 14% on EM and 35% on Token-F1. We report Token-F1 as the primary metric because it credits partially-correct clinical content that EM discards at this open-generation scale. Main-table results are means over 3 seeds with standard deviations below 0.005. The method transfers to PubMedQA, where training on the PubMedQA train set with the same composite reward improves Token-F1 over SFT by 22% on Phi-3-mini and 17% on Llama-3.2-3B without retuning. A reward ablation on Phi-3, varying the judge-ontology split at a fixed consistency weight, attributes 3 EM points to the ontology term, the contribution that catches entity substitutions the judge cannot. Three negative findings constrain the design: DPO under random negatives underperforms SFT for strong-prior models but helps the weakest-prior one; PPO under a sparse neural reward diverges; GRPO with KL-in-loss collapses at 7B.

Aditya Tanna, Abhishek Jindal

Dhirubhai Ambani University Gandhinagar, Gujarat, India

Reward Modeling RL for Language Model Reasoning Question Answering Clinical QA Medical LLMs

Oct 4, 2026cs.AI

EnGRICH: Enhancing Generative Reward Modeling with Critiques from Humans

Generative reward models (GRMs) are important for LLM optimization. Unlike scalar reward models, GRMs generate natural-language critiques alongside preference judgments, providing finer-grained evaluation signals. Their effectiveness depends heavily on critique reliability. However, existing GRM training typically uses final preference correctness as outcome supervision. Because the preference outcome space is highly constrained, unreliable critiques can still yield correct outcomes and thus be reinforced. Recent work leverages human critiques for process supervision, but such critiques are scarce and are often reduced to scalar rewards, leaving their fine-grained evaluative information underutilized. We argue that evaluative criteria learned from human critiques can be generalized to broader outcome-only preference data. To this end, we propose \textbf{EnGRICH}, a GRM training framework that pairs the GRM with a training-time MetaCritic learned from a small set of human critiques. MetaCritic constructs response-specific rubrics and uses them to evaluate the evidence coverage and correctness of generated critiques. The resulting signals provide both process rewards for fine-grained credit assignment and structured guidance for exploring better critiques. During GRM training, MetaCritic is further optimized to generalize human-grounded evaluative criteria to outcome-only data. At inference, the trained GRM operates independently. Experiments across seven reward-model benchmarks show that EnGRICH consistently improves over competitive baselines, while further analyses validate the effectiveness of its core mechanisms.

Xuancheng Li, Beining Wang, Haitao Li +7

Department of Computer Science and Technology, Tsinghua University, Beijing, China · Tencent, Beijing, China

Reward Modeling Process Reward Models Rubric-Based RL RL from Human Feedback

Oct 1, 2026cs.LG

Range-GRPO: Policy Optimization via Pairwise Relations among Reward Intervals

As the use of large language models (LLMs) expands, post-training has become increasingly important for adapting them to downstream tasks. However, obtaining reliable supervision remains costly, especially in domains without reference answers or executable verifiers. LLM-as-a-Judge provides scalable pseudo-rewards for unlabeled responses, but a single point score does not explicitly represent reward uncertainty. This motivates representing pseudo-rewards as conformally calibrated reward ranges. We propose Range-GRPO, a semi-supervised post-training framework that combines limited labeled data with unlabeled prompts. In Group Relative Policy Optimization (GRPO), learning signals depend on relative reward comparisons within each rollout group. The proposed objective compares reward ranges pairwise rather than reducing them to point rewards, allowing interval uncertainty to affect both the magnitude and direction of these signals. Our theoretical analysis characterizes this distinction and shows that the proposed objective recovers the Dr.GRPO advantage when all reward ranges collapse to points. Empirically, Range-GRPO achieves the highest in-distribution and out-of-distribution average performance among the evaluated semi-supervised methods while requiring fewer training resources.

Ryunyi Lee, Kangjun Noh, Somin Kim +2

Yonsei University

Reward Modeling LLM-as-a-Judge Group Relative Policy Optimization RL Post-Training Semi-Supervised Learning

Sep 30, 2026cs.LG

MatrixReward: Reward from Rubric Matrix for Open-Ended Generation

Open-ended query generation lacks standard answers, thus necessitating an effective reward mechanism. Pointwise scoring rubrics provide limited information about the relative quality of sample answers under the same prompt; merging multiple rubric judgments into a single score may also mask the differences between these answers. We propose MatrixReward, which constructs rewards from a rollout-by-rubric win-rate matrix obtained by comparing every pair of sampled responses under each rubric. The spread of each matrix column captures how strongly that rubric distinguishes the current rollouts, while correlations between columns reveal rubric repetition; together, these statistics yield data-dependent rubric weights. We combine these weights with the prior weights of rubrics. After column normalization and weighting, the observed per-rubric maxima and minima define positive and negative ideal profiles. Each rollout's distances to these two ideals determine its relative-closeness quality reward. Evaluated using Qwen3-8B on four open-ended query-answering benchmarks, MatrixReward achieves an average score of 63.02, outperforming the strongest baseline by approximately 2.0%. These results support the idea that matrices derived from relative comparisons can be used to construct rewards more reasonably for open-ended generative reinforcement learning.

Zihan Shen, Qi Liu, Zixuan Yang +4

Zhejiang University · Qwen Business Unit of Alibaba · Renmin University of China

Open-Ended Generation Reward Modeling Rubric-Based RL Rubric-Based Evaluation

Sep 29, 2026cs.LG

Revisiting scaling laws for reward optimization

Scaling laws for optimization against reward models in AI alignment have pinned down how performance depends on optimization effort---measured by a KL-divergence budget relative to a reference policy. Beyond a certain budget, over-optimization (or reward hacking) can arise: because we optimize against a proxy reward model (distinct from true rewards), performance can plateau or degrade. Naturally, the proxy reward's accuracy depends on how much preference data (often in the form of pairwise comparisons) was used to train it. However, existing research does not cleanly identify how performance jointly scales with the amount of training data and the divergence budget. Our main contribution is to provide an empirically accurate and theoretically grounded scaling law in such context. Performance roughly scales as

Θ(\sqrt{\min\{\log(M),K\}})

, where

M

is the number of comparisons in training data and

K

is the policy's divergence budget. We develop an information-theoretic model to establish this upper bound and prove it is tightly achievable through a constructive procedure. Informed by this, we conduct extensive empirical evaluations using a real-world annotation setup, whereby a large 70B gold reward model generates feedback data and proxy reward models are trained from less capable models (0.6B to 4B). Our scaling law provides an excellent fit (R2 from 97% to 99%), outperforms alternative specifications, and remains robust across model sizes, noise, and optimization procedures (best-of-

N

or policy tilting). Our evidence suggests that reward optimization is analogous to a surprisingly simple selection task: choosing from a sequence of IID Gaussian random variables using noisy preference feedback.

Ali Aouad, Aymane El Gadarri, Vivek F. Farias

MIT

Reward Modeling Reinforcement Learning Preference-Based RL

Sep 29, 2026cs.CV

Think Before You Score: Thinking Reward Model for Visual Generation

Visual reward models are essential for evaluating and improving visual generation models, yet existing approaches typically map task conditions and candidate outputs directly to scalar rewards, leaving implicit what should be evaluated for each individual case. We introduce Think Before You Score, a paradigm that explicitly determines what matters for each case before judging how well the candidate performs. Following this principle, we propose the Thinking Reward Model (TRM), which formulates case-adaptive rubrics, performs rubric-guided assessment, and produces fine-grained pointwise rewards. We further observe that conventional pairwise preference optimization can induce score polarization, and introduce Pairwise Dual-Group Relative Policy Optimization (PD-GRPO), which leverages pairwise supervision to improve reward discrimination while preserving fine-grained pointwise scoring. Extensive experiments on image generation and editing reward-modeling benchmarks demonstrate that TRM achieves state-of-the-art performance among open-source reward models while remaining highly competitive with proprietary alternatives. Moreover, using TRM as a reward for reinforcement learning consistently improves diverse visual generation models, demonstrating that its fine-grained, case-adaptive rewards translate into effective optimization signals for visual generation.

Xuehai Bai, Zhenchen Tang, Yang Shi +9

HDU · SenseTime · CASIA +5

Reward Modeling Multimodal Reward Modeling

Sep 29, 2026cs.AI

RankBuffer: Efficient Ranking-Based Rewards for Open-Ended Generation

Open-ended generation lacks canonical answers, making pointwise rewards difficult to calibrate for group-based reinforcement learning. Directly ranking same-query rollouts provides a more suitable relative reward signal, but existing ranking-based reward methods can incur substantial judging cost. We introduce RankBuffer, which maintains an ordered, query-specific buffer of previously judged responses as a reusable quality scale. Each rollout is first inserted into an anchor interval through an independent coarse judgment, after which only rollouts assigned to the same interval undergo local fine ranking. The resulting complete order is converted into bounded rank rewards, while boundary expansion, local refinement, and inactive-anchor pruning adapt the buffer as the policy evolves. Across four open-ended benchmarks, RankBuffer consistently outperforms all pointwise baselines. It also achieves nearly on-par performance with the strongest ranking-based reward baseline while substantially reducing judging cost. Ablations demonstrate the importance of both local fine ranking and anchor response content, while buffer analyses show that rollout-derived anchors progressively extend and refine the covered quality scale. These results establish response reuse as an effective approach to efficient relative reward construction.

Zixuan Yang, Yiqun Chen, Qi Liu +6

Renmin University of China · University of Southern California · Xiaohongshu Inc.

Open-Ended Generation Reward Modeling Learning to Rank RL for Generative Models

Sep 28, 2026cs.AI

CoRe: Co-Evolving Reward Models for Mitigating Latent Reward Hacking in Video Diffusion Models

Latent reward models (LRMs) enable efficient alignment of video diffusion models by scoring intermediate states directly in latent space. However, we find that optimizing against a fixed latent reward rapidly leads to latent reward hacking: the predicted reward stays high while perceptual and motion quality deteriorate. Our analysis identifies distributional escape as the central cause: within a few hundred updates, the generator moves beyond the reward model's training support, where its scores no longer reflect video quality. Based on this insight, we introduce CoRe, a co-evolving reward framework that treats latent-space alignment as a dynamic interaction between the generator and the reward model. Rather than optimizing against a stationary proxy, CoRe continually refits the reward model on the generator's current samples while anchoring it to real-video preferences, so the generator cannot gain reward by drifting away from the data. On Wan2.1-T2V-1.3B, experiments show that CoRe consistently improves generation quality over both the pretrained model and prior alignment methods, while avoiding the quality collapse of fixed-reward optimization.

Zhaolong Su, Yujin Han, Feng Wang +3

Cornell University · The University of Hong Kong · Johns Hopkins University

Diffusion Model Alignment Reward Modeling Reward Hacking Video Diffusion Models

Sep 28, 2026cs.CL

Rubric Rewards from Item Response Theory

Many language tasks have no single answer that can be checked automatically. Rubrics provide criteria for judging responses to these tasks. For reinforcement learning, the resulting verdicts must be combined into a scalar reward. A common approach sums the points assigned to satisfied criteria. Distinct verdict patterns can thus receive the same reward, and the fixed points encode how much each criterion should count, not how strongly its verdict distinguishes the current rollouts. Beyond this aggregation problem, judging the full rubric needs more judge requests as the criterion count grows. To address these limitations, Rubric Response Theory (RRT) measures quality and selects criteria when rubric criteria are monotone indicators of a shared target. Rather than adding assigned points, RRT uses a two parameter item response model that treats the verdict pattern as evidence about scalar quality specific to the rubric. Under this model, its likelihood score maximizes the local signal-to-noise ratio for quality. Its Response Parameter Network (RPN) reads the prompt and criterion text to predict criterion difficulty and discrimination. As the policy distribution changes during training, RRT uses online expectation maximization to update the RPN from current rollout verdicts. With Qwen3.5-4B as the policy, RRT's macro criterion score across Medical, Science, Rubrics as Rewards Science, and RubricBench is 1.7 points above that of group relative policy optimization (GRPO). On hard and very hard criteria in Medical and Science, RRT gains 2.8 to 5.6 points over GRPO. At half the criterion budget, adaptive Fisher selection with a frozen RPN keeps the macro criterion score across four datasets within 0.1 points of GRPO with full judging. These results show RRT can reduce judge requests while remaining competitive with GRPO.

Milad Yazdani, Yaser Souri, Xiren Zhou +4

Department of Electrical and Computer Engineering, University of British Columbia · Microsoft · School of Biomedical Engineering, University of British Columbia

Reward Modeling Rubric-Based RL Reward Design for RL Item Response Theory

Sep 28, 2026cs.AI

Using Context Is Not Enough: Test-Time Training for Personalized Reward Modeling

Reinforcement learning from human feedback (RLHF) aligns large language models (LLMs) with human preferences, yet most pipelines learn a single reward model that overlooks individual differences in preferences. Personalized reward models (PRMs) address this by conditioning rewards on user-specific feedback, most commonly through in-context learning (ICL), where a user's historical comparisons are supplied as contextual preference pairs. However, we identify a key limitation of ICL-based PRMs: they fail to capture the preference relations conveyed by contextual pairs. To address this, we propose Preference-Aligned Test-Time Training (P-TTT), which explicitly encodes these relations into user-specific fast weights for personalized reward prediction. P-TTT introduces sequence-level update and apply operations to match the response-level granularity of preference feedback, together with a preference-aligned objective that directly uses pairwise preference relations to guide fast-weight adaptation. Notably, P-TTT is simple to implement and computationally efficient, updating fast weights within a single forward pass without inference-time backpropagation. Extensive experiments show that P-TTT more effectively captures historical preference relations and outperforms state-of-the-art methods by a large margin.

Bohao Wang, Xiaoyan Zhao, Yang Zhang +4

Zhejiang University · National University of Singapore

Pairwise Preference Learning Reward Modeling Test-Time Training User Preference Modeling

Sep 28, 2026cs.AI

From Soft Targets to Reward Signals: How Assignment and Reward Objectives Interact

Soft preference targets specify supervision strength, and reward objectives convert that strength into learned reward signals. A central design question remains: how does assigning a fixed set of preference strengths to different response pairs change the rewards produced by different objectives? We introduce assignment geometry to study this interaction. Mean-matched smoothing controls target dispersion, while within-stratum reassignment changes correspondence and preserves the complete target distribution. Across five reward objectives, intact correspondence retains the largest clean preference margins among the compared soft targets within a common accuracy-equivalence budget. Attenuation orderings change with the reward objective, revealing different responses to the same target assignments. Independent reassignments and a related source construction reproduce the retention direction. An attenuation-retention profile compares these combinations through margin magnitude, edit response, and accuracy. Against independently calibrated scaling, APLOT uniform targets deliver additional attenuation on both aggregate and presentation edits. These findings establish a joint design space in which target placement and reward objective shape reward properties beyond preference accuracy.

Jiangtao Lin, Bangyang Wei, Siyi Liu +2

Tsinghua Shenzhen International Graduate School, Tsinghua University · School of Vehicle and Mobility, Tsinghua University · Tencent Holdings Limited +1

Pairwise Preference Learning Reward Modeling Preference Learning

Sep 28, 2026cs.CL

CRISP: Cultural Reward Modeling for Implicit Situated Propriety

As large language models (LLMs) are increasingly deployed across countries and regions, the ability to recognize and respond appropriately to diverse cultural contexts becomes increasingly important. However, existing research has largely focused on cultural knowledge or tasks with predefined response spaces, while open-ended culturally situated behavior remains comparatively underexplored. In this work, we introduce CRISP-RM, a culturally situated reward model that assigns rewards according to cultural appropriateness in open-ended social scenarios. During policy optimization, we further introduce Norm Grounding Supervision (NGS), providing guidance that enhances the policy's sensitivity to relevant cultural norms. To construct culturally situated data, we employ a collaborative multi-agent framework that instantiates implicit cultural norms into diverse social scenarios and further curate NormCompass as a dedicated testbed. We conduct comprehensive experiments to evaluate the effectiveness of CRISP-RM in both reward modeling and policy optimization. Best-of-

N

experiments show that CRISP-RM consistently outperforms strong general reward models. During GRPO policy optimization, CRISP-RM generally improves culturally situated behavior, while incorporating NGS yields further gains. Further analyses demonstrate the advantages of CRISP-RM in distinguishing culturally appropriate behavior beyond superficial fluency and politeness, while NGS provides complementary gains during policy optimization by improving norm grounding.

Zekun Yuan, Yangfan Ye, Baohang Li +6

Harbin Institute of Technology · Huawei Technologies Co., Ltd · Peng Cheng Laboratory

Reward Modeling RL for Language Models Cultural Alignment Cultural Knowledge in Language Models Reward Design for RL

Sep 28, 2026cs.AI

Evolving Support Priorities in Empathetic Reinforcement Learning

We identify a fundamental mismatch in empathetic reinforcement learning: support priorities evolve with the dialogue state, yet existing methods typically optimize predefined reward specifications that remain fixed across turns. To model these evolving support priorities, we organize empathetic support along cognitive, affective, and proactive empathy, and propose Context-Adaptive Rubric Evolution (CARE). At each turn, CARE generates a context-adaptive rubric by adjusting both the weights of these three empathy dimensions and their fine-grained evaluation criteria. The rubric generator is trained with turn-level rubric supervision and human preference data through supervised fine-tuning followed by preference-based reinforcement learning, and then serves as an adaptive reward interface for online empathetic RL. Integrated with both RLVER and MICA, CARE achieves state-of-the-art performance across SentientBench, EQBench3, and EMPA under three independent LLM judges. Notably, on EMPA, CARE improves EPM-Idx over the strongest baseline by at least 13 points under all three judges, including an increase from 28.11 to 83.54 under Gemini-2.5-Pro. Further analyses show that learned rubric priorities systematically vary across dialogue stages and user emotions, demonstrating that CARE adapts what is rewarded as support needs evolve.

Pengyu Huang, Zhiyuan Han, Wenwen Tong +6

University of Science and Technology of China, Hefei, China · SenseTime Research, Shanghai, China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center

Reward Modeling RL for Language Models Rubric-Based RL Reward Design for RL Emotion-Aware Dialogue Generation

Sep 27, 2026cs.CL

RewardExplainer: Learning Reward Model Explanations from Counterfactual Preference Feedback

Reward models (RMs) are a key component of large language model post-training, providing reward signals for subsequent reinforcement learning. However, conventional discriminative RMs typically output only scalar scores, making it difficult to identify the response behaviors associated with their scoring decisions. Existing interpretation methods often rely on predefined high-level attributes and require repeated counterfactual interventions for each response pair to validate candidate explanations, lacking a closed-loop mechanism that uses RMs' feedback to train a reusable explainer. To address this, we propose RewardExplainer, a framework that obtains feedback from the target reward model through counterfactual rewriting and uses this feedback to further optimize the explainer. RewardExplainer generates open-ended, atomic, and intervenable natural-language scoring mechanisms, making explanations more concrete, readable, and actionable. It further converts counterfactual feedback into preference supervision, enabling the explainer to more faithfully capture the target RM's scoring preferences and sensitive behaviors than single-pass generation. Extensive experiments across multiple target RMs and explainer backbones show consistent improvements. Beyond interpretation, we use the generated mechanisms to identify potential bias patterns and construct targeted debiasing data for fine-tuning the reward model, improving robustness on reward-hacking benchmarks.

Jingyi He, Nier Wu, Shuang Liu +3

The Chinese University of Hong Kong, Shenzhen · Shanghai Jiao Tong University · Carnegie Mellon University +2

Reward Modeling Counterfactual Explanations

Sep 27, 2026cs.LG

Diffusion Reward Models

Reward models underpin the alignment of large language models, yet the dominant designs reduce each prompt--response pair to a point estimate or to a distribution from a fixed parametric family. This is at odds with human preference, which is inherently multimodal: the same response can be reasonably judged in many ways, and no single family covers all of them. To better fit this structure, we introduce DRM, a Diffusion Reward Model that recasts reward modeling as conditional density estimation over

p(\mathbf{r}\mid x,y)

. Conditioned on a frozen LLM encoder, a lightweight Diffusion Transformer denoises Gaussian noise into a reward vector, placing no parametric assumption on the output distribution and naturally representing its multimodal structure. A single architecture handles both multi-attribute regression and pairwise preference data, and at inference

N

samples form an empirical reward distribution that can be aggregated into a scalar, a variance, or quantiles. Across five benchmarks, DRM matches or surpasses baselines under matched data and backbone, stays competitive with much larger discriminative, distributional, and generative RMs despite its modest training scale, and recovers multimodal reward structure where conventional heads collapse to a point. Uncertainty-aware rejection and lower-confidence-bound (LCB) aggregation further demonstrate that DRM can exploit distributional information beyond a scalar reward to improve reward-model decisions. Downstream RLHF experiments additionally show that using DRM as the training-time reward leads to improved policy performance, directly validating the practical benefit of diffusion-based reward modeling for RLHF training.

Xiangyang Wang, Bingxiang He, Zeyuan Liu +13

Tsinghua University · University of Illinois Urbana-Champaign

Reward Modeling Multimodal Reward Modeling Diffusion Models RL from Human Feedback

Sep 27, 2026cs.LG

A Cheap Verifier is Good Enough: LLM Post-training is Robust to Erroneous Rewards

When post-training large language models on tasks with semi-verifiable rewards, there are many factors (training steps, base model size, training order, data quality, verifier accuracy, etc.) that practitioners must contend with to maximize model performance. Yet, it remains unclear how well verifier agreement predicts post-training performance on such tasks. In this paper, we explore this question with over 11k H100 GPU-hours, across HealthBench and PRBench tasks in medical, legal, and finance domains. Across the tested domains, Qwen3 trainees (1.7B-8B on HealthBench; 8B on PRBench), evaluation splits, and frontier LLM reference judges (which we call golden verifiers), higher verifier agreement does not consistently identify the best training verifier. Expensive verifiers need not outperform inexpensive ones, and open-weight Gemma verifiers produce strong training outcomes. We compare two low-cost choices retrospectively -- a cost-reducing choice and a balanced choice -- with estimated grading cost reductions of 98.8%-99.7% relative to the golden grading protocols and average post-training score gaps of 1-3 points from the best evaluated training verifier. These averages include larger losses in individual settings; they do not establish that verifier choices are interchangeable.

Andreas Plesner, Curtis Northcutt, Francisco Guzmán +1

ETH Zurich · Handshake AI

Reward Modeling LLM Reliability Reinforcement Learning with Verifiable Rewards LLM Post-Training

Sep 20, 2026cs.CL

FLARE: A Full-Lifecycle Dense Supervision Paradigm for Long-Horizon Coding Agents via Generative Reward Model

While test-time scaling enhances Large Language Model (LLM) agents in long-horizon software engineering (SWE), sparse binary rewards (Pass/Fail) create a severe credit assignment crisis and waste failed exploratory trajectories. Current trajectory optimization and scaling methods are costly and structurally limited, relying on heuristic state reuse without causal diagnosis or delayed scalar scoring without actionable online guidance. We propose FLARE (Full-Lifecycle Alignment and Reward Engine), a novel dense supervision paradigm driven by a lightweight Generative Reward Model (GRM). First, RADAR, an offline causal-aware diagnostic framework, extracts high-fidelity, hindsight-free supervision through causal-chain backtracking to distill a GRM providing real-time, step-level risk feedback. Second, FLARE uses this GRM to continuously optimize the agent across its entire lifecycle. During inference, FLARE acts as an Active Scaffold, autonomously intercepting high-risk generation steps for localized breakpoint re-execution, drastically reducing compute overhead. During post-training, the GRM's structured signals serve as process-supervised reranking scores for Supervised Fine-Tuning (SFT) and step-level dense rewards for Reinforcement Learning (RL), mitigating policy collapse in sparse environments. Extensive evaluations show that FLARE establishes a new Pareto frontier across the agent lifecycle: FLARE (N=1) outperforms Global Rollout (N=5) with a 5x reduction in token consumption. Extending FLARE to training overcomes the sparse reward problem in long-horizon interactive tasks, delivering relative performance gains of 19.13% in SFT through process-aware data curation and a consistent 9.19% improvement in RL.

Jingxuan Xu, Gang Wu, Yanan Wu +13

Independent Researcher · Nanjing University · Peking University +1

RL for Code Generation Reward Modeling Credit Assignment in RL Process Supervision Sparse-Reward RL Long-Horizon LLM Agents

Sep 19, 2026cs.CV

RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling

Reinforcement learning (RL) is vital for optimizing video generation models, with a robust reward model (RM) serving as the cornerstone. However, existing video reward models often produce unstable scalar scores because they directly map complex, subjective video quality into a single score without explicit evaluation criteria. This leads to scalar drift, where the scoring scale collapses or shifts across different prompts, making the reward unreliable for RL. Drawing inspiration from professional human annotation engineering, we address this problem with RewardVerse, a rubric-based video reward framework that introduces a dynamic rubric as an intermediate representation between the evaluation query and the scorer. Instead of unconstrained direct scoring, RewardVerse first generates explicit evaluation criteria and then performs rubric-guided scoring, providing a stable semantic anchor that mitigates scalar drift. To efficiently optimize this collaborative pipeline, we propose Rubric-Guided Policy Optimization (RGPO), a two-stage training algorithm. RGPO first warms up the scorer using self-evolving seed rubrics and then jointly optimizes the rubric generator to produce query-adaptive evaluation criteria while continuously aligning the scorer with human ratings. Extensive experiments on the 16-dimensional EvalVerse benchmark and external datasets demonstrate that RewardVerse mitigates scalar drift, achieves state-of-the-art performance on both pointwise and pairwise evaluation, and provides a robust and interpretable reward signal for RL in video generation.

Zhenchen Tang, Yang Li, Songlin Yang +6

New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · Tencent +1

Reward Modeling Multimodal Reward Modeling Rubric-Based RL Rubric-Based Evaluation Video Generation Evaluation

Sep 17, 2026cs.LG

MATCH: Model-Aware Tool Learning with Curriculum Scheduling and Hierarchically Gated Rewards

Tool learning enables large language models (LLMs) to use external tools for tasks beyond parametric knowledge. Reinforcement learning can optimize tool-call behavior from feedback, but current methods still face two problems: fixed-threshold curricula can become misaligned with the policy's evolving capability boundary, and additive rewards can leak argument-level credit when the predicted tool is wrong. To address these problems, we propose MATCH, a closed-loop framework for model-aware tool learning with curriculum scheduling and hierarchically gated rewards. Model-Aware Curriculum Learning (MACL) maintains reward-derived sample difficulty that co-evolves with the policy, and each epoch selects samples near the current capability boundary together with a top-k pool of harder cases. Hierarchical Tool-call Gated Reward (HTGR) scores tool name, argument key, and argument value as a gated chain, granting credit at each level only when prerequisites hold. The same HTGR rewards drive both GRPO updates and MACL's difficulty refresh, closing the loop between policy optimization and sample scheduling. On API-Bank and BFCL V3, MATCH reaches 72.19% and 62.87% overall accuracy, outperforming the main supervised and RL-based baselines. Backbone experiments further show consistent improvements across four backbones from two model families.

Shihao Liu, Hao Yin, Lijun Liu +3

School of Cyber Security, University of the Chinese Academy of Sciences · Honor Device Co., Ltd · University of the Chinese Academy of Sciences

Reward Modeling Curriculum RL Policy Learning Tool Use RL for Tool Use

Sep 17, 2026cs.CL

F $^{2}$ DR: A Fine-Grained Full-Pipeline Reward Framework for DeepSearch Workflows

With the widespread industrial deployment of Large Language Models (LLMs), DeepSearch has emerged as the dominant paradigm for resolving complex user queries. It typically operates through an iterative closed-loop workflow consisting of planning and reflection, information retrieval, and answer generation. However, existing reward models (RMs) and evaluation benchmarks are primarily designed for static single-turn tasks, failing to capture the full-pipeline complexity of DeepSearch workflows. To address this limitation, we propose F2DR, a fine-grained full-pipeline DeepSearch reward framework. F2DR evaluates DeepSearch workflows across three dimensions: Content, Trajectory, and Answer, enabling comprehensive process-level assessment. We further construct DeepSearch RM-Bench, a dedicated benchmark for evaluating RMs in DeepSearch scenarios. Extensive experiments demonstrate that F2DR achieves significantly higher evaluation consistency than self-evaluation-based baselines, while DeepSearch RM-Bench exhibits strong discriminative capability across existing open-source RMs. We will publicly release the complete DeepSearch RM-Bench dataset soon.

Bojian Xiong, Wentao Ding, Yujing Lu +11

Tianjin University · TJUNLP Lab, Tianjin University, Tianjin, China · Baidu Inc. +1

Reward Modeling LLM Evaluation AI Agent Benchmarks Reward Model Evaluation

Sep 16, 2026cs.RO

FIERCE: From Generalist Robot Policies to Fast Specialists via Progress-Failure Feedback

Generalist robot policies offer useful initialization, but refining compact specialists through limited physical interaction requires informative learning feedback. We present FIERCE, a generalist-initialized reinforcement learning framework centered on a unified, task-adaptive progress-failure evaluator. Its architecture shares an observation-language representation between an observed-progress head and an action-conditioned latent predictor whose past and current predictions feed a causal sequence head for task-failure estimation. Joint supervision from progress and preference labels, synchronized commands and observations, and terminal outcomes trains the evaluator; target-task rollouts support adaptation and calibration. Fixed evaluator snapshots provide progress shaping and failure-risk penalties alongside independently verified terminal rewards, while evaluator and policy updates alternate as new experience is collected. Refinement requires neither continued generalist action queries nor a dedicated target-task simulator or manually annotated dense rewards. Only the compact specialist is retained at deployment. The evaluation separates feedback quality, policy-learning efficiency, and deployment cost across simulation and two contact-rich real tasks. Code, model weights, and data-restoration tools are released at https://github.com/ar-mine/FIERCE.

Runjia Tan, Yuang Tu, Yujie Yan +3

Nanyang Technological University. · Guangzhou Cloudbutterfly Technology Co., Ltd.

Reward Modeling Robot Policy Learning Robot Policy Adaptation Reward Shaping Robotic RL

Sep 14, 2026cs.CL

Don't Count the Edits, Judge by the Outcome Alone: Reward-Based Evaluation for Grammatical Error Correction

Grammatical error correction (GEC) evaluation has traditionally relied on reference or edit overlap, which can penalize valid rewrites that differ from gold corrections. Reference-free metrics reduce this dependence, but evaluating whether a fluent output is a valid correction of the source remains challenging. We propose SURE, a source-conditioned reward evaluator trained on within-source preferences spanning minimal-edit and rewrite-oriented corrections. SURE jointly learns an overall reward with criteria-level supervision for grammaticality, faithfulness, and fluency, together with span-level grounding for source-side error resolution. Experiments on SEEDA show that SURE performs competitively against strong baselines, with particular gains on rewrite-style corrections and more disentangled criteria-level diagnostics. Our code is available at https://github.com/hayeonggg/SURE.

Hayeong Ryu, Sunhee Jo, Seunguk Yu +1

Department of Artificial Intelligence, Chung-Ang University · Graduate School of Advanced Imaging Sciences, Multimedia and Film, Chung-Ang University

Reward Modeling Reference-Free Evaluation Rubric-Based Evaluation Automated Evaluation

Sep 10, 2026cs.CV

AgenticGen: Reward-Guided Agentic Video Generation for Advertising

Advertising video generation is not only a video synthesis task, but also a product-conditioned reasoning problem whose success is measured by online business metrics. Recent video foundation models can generate realistic clips from multimodal conditions, yet they do not optimize how a product should be transformed into an effective advertisement or how future generation should be improved from online business feedback. To close this loop, we propose AgenticGen, a reward-guided agentic framework that decomposes advertising video generation into two trainable reasoning stages, strategy selection and draft generation, thereby exposing optimization targets that online business feedback can supervise. AgenticGen learns a performance-based reward from accumulated online feedback and a complementary rubric-based reward aligned with human quality standards, then uses them to supervise policy optimization. DPO first moves the agentic policies toward online preferences, and GRPO further refines both stages with process and outcome rewards. Offline experiments validate the reward models and successive policy optimization. Online A/B experiments in the TikTok advertising system show that AgenticGen after DPO and GRPO improves CTR by 2.72%, CVR by 2.63%, and Advv by 9.61% over the SFT baseline.

Xingyuan Bu, Chengru Song, Hao Zhou +9

ByteDance · Tsinghua University · The Chinese University of Hong Kong

Reward Modeling Agentic RL RL for Video Generation Agentic Video Generation Video Generation

Sep 9, 2026cs.AI

Proof-Carrying Cognition: Closing the Verification Gap with Reality-Settled Reward

Frontier gains in language-model reasoning come from reinforcement learning on reasoning traces and are concentrated in domains with a cheap, sound verifier. We argue the field's binding constraint is the verification gap: no scalable, incorruptible reward for reasoning outside formal domains. We make four contributions. (1) Theory: in a joint-Gaussian model of best-of-N selection, verifier-gold correlation rho is the exact exchange rate between test-time compute and capability, and an unsound verifier pays a polynomial penalty N^(1/rho^2); a margin-free copula form predicts realized soundness of real LLM judges to 4% median error. (2) Demonstration: in program-synthesis testbeds with executable ground truth, including a pre-registered scaled replication, unsound verifiers lose Soundness-under-Pressure as optimization grows (0.94 to 0.32 at N=4096) while a sound verifier improves monotonically; reality-anchored settlement beats a frozen verifier under i.i.d. and adversarial pressure, driving the hacking gap from ~0.27 to ~0; soundness scales log-linearly with settled labels, with on-policy settlement ~10x more label-efficient than random labeling. With real LLM judges and unit-test execution as gold, a weak judge loses soundness under best-of-N (p<0.001), a stronger judge is more robust, and selection alone manufactures +0.53 hacking gaps from honest samples. Under real GRPO training, a frozen reward model traces the full overoptimization curve (executed reward collapses 90%) while the same model refit on a 10% settlement stream preserves 6x the executed reward. (3) Paradigm: proof-carrying cognition, where reasoning steps are typed probabilistic claims priced by a self-built world model trained only on held-out reality and settled by proper scoring rules. (4) Benchmark: we specify Soundness-under-Pressure as the headline metric for a reality-settled reasoning benchmark.

Eshwar Reddy M, Sourav Karmakar

AI Engineer, Testsigma University of San Diego · Senior AI Scientist, Intuit India

Reward Modeling Reward Hacking LLM Reliability Reinforcement Learning with Verifiable Rewards

Sep 9, 2026cs.LG

ALIGN-HOLD: Experience Alignment for Real-Time Hold Control in Large-Scale Ride-Hailing Matching at DiDi

Real-time hold control is a high-leverage mechanism in large-scale ride-hailing systems: by selectively deferring driver-order pairs, the platform can wait for better matching opportunities and improve end-to-end passenger-driver experience. Existing production systems such as EXHOLD learn bandit-based hold policies from handcrafted combinations of trip completion, cancellations, waiting time, and driver effort. However, designing such rewards becomes increasingly difficult as marketplace preferences are heterogeneous and observed passenger-driver behavior can be sparse, noisy, and affected by dynamic supply-demand conditions. We present ALIGN-HOLD, a production-scale experience alignment framework that learns hold policy from implicit marketplace preferences. ALIGN-HOLD constructs complementary preference pairs from order trajectories, driver trajectories, and contemporaneous local matching graphs, and trains an experience Reward Model (RM) using balanced multi-view sampling and model-adaptive hard preference sampling. During simulator-based policy learning, the frozen RM provides a dense, context-dependent reward and supports label-free filtering of low-identifiability interactions whose behavioral feedback is difficult to attribute to matching quality. We deploy ALIGN-HOLD on DiDi's ride-hailing platform and evaluate it in a 28-day randomized A/B experiment, covering approximately 100,000 passenger requests per day. Compared with the deployed production policy, ALIGN-HOLD achieves statistically significant improvements in trip completion rate and driver income, while significantly reducing passenger cancellations before and after driver acceptance. Complementary ablations, RM diagnostics, and behavioral analyses validate the contributions of the proposed components. ALIGN-HOLD has been fully ramped up and is currently serving DiDi's Brazil marketplace.

Zuhao Zhang, Xu Liu, Kai Wan +3

Didichuxing Co. Ltd Beijing, China · Shanghai Jiao Tong University Shanghai, China

RL Control Reward Modeling Preference-Based RL

Sep 3, 2026cs.CV

WorldReward: Reward Modeling for Camera-Conditioned World Models

Camera-conditioned world models generate interactive videos in which commanded actions should induce the expected scene changes while appearance, geometry, and temporal dynamics remain coherent. Existing rewards assess these requirements separately: geometry-based rewards estimate trajectory execution but cannot judge the visual quality of the executed motion, whereas image-based rewards measure frame quality without capturing action execution or temporal dynamics. We posit that a vision-language model (VLM) offers a shared reasoning space for relating actions to their visual outcomes. However, judging a complete long video against its full action sequence creates a lengthy, noisy context in which short-lived local action evidence can be missed or diluted. We present WorldReward, a VLM-based pairwise preference reward model that unifies action-consistency and visual-quality evaluation for camera-conditioned world models. WorldReward decomposes paired videos into action-aligned chunks, organizes each chunk into structured visual evidence, and aggregates chunk-level decisions by voting into separate video-level action and visual-quality preferences. To train it, we construct a large-scale reasoning-augmented preference dataset using structured judgments generated by a frontier VLM and refined through tool-based agent auditing and targeted human review. We further introduce WorldReward-Bench, a human-annotated benchmark measuring reward-model agreement with human preferences across action consistency, appearance quality, and motion quality. WorldReward achieves the highest agreement on all three dimensions, exceeding GPT-5.5 by 3.42, 1.45, and 3.56 percentage points, respectively. When used for RL post-training of HY-WorldPlay 1.5, it consistently improves both action execution and visual quality across short- to long-term horizons.

Yibin Wang, Zehan Wang, Junshu Tang +13

Fudan University · Tencent Hunyuan · Shanghai Innovation Institute +3

Reward Modeling Camera-Conditioned Video Generation RL for Video Generation Multimodal Reward Modeling World Model Evaluation

Sep 1, 2026cs.LG

Patterning in Practice: Debiasing Reward Models with Susceptibilities

Reward models trained on human preferences are known to suffer from length, formatting, and other stylistic biases. In this paper we use patterning, which reweights each preference pair according to its measured effect on posterior expectation values of benchmark losses (its susceptibility), to debias a Gemma 2 9B Instruct reward model trained on Skywork-Reward-Preference v0.2. We obtain

+14.2 \pm 1.2

pp on RM-Bench Hard, the split where style cues point against correctness (mean

\pm

s.e.\ over 5 seeds), with overall RM-Bench accuracy preserved, comparable to the strongest Hard-split gain reported by the closest published comparator (SteerRM,

+13.2

pp). We demonstrate in a simple case that the reweighting is interpretable by tracing a side effect of the intervention (a regression on a safety subset of RM-Bench) to a small class of training pairs, which we confirm by ablation. The weights also transfer: those computed on Gemma 2 9B debias Gemma 2 2B and 27B with no recomputation, and transfer partially to Llama 3.1 8B. This is the first application of patterning, a program grounded in singular learning theory, beyond small models and synthetic tasks.

George Wang, Elizabeth Donoway, Daniel Murfet

Resolution

Reward Modeling Debiased ML Singular Learning Theory

Aug 31, 2026cs.CL

When Does Predictor-Based RL Align with Human Perception? A Study of Subjective Rewards in Codec-Based Speech Language Models

Codec-based text-to-speech (TTS) models make language-model post-training applicable to speech generation, but it remains unclear when learned perceptual predictors can serve as reinforcement learning rewards without losing alignment with human listeners. We study this question with Group Relative Policy Optimization (GRPO) using learned rewards for anime-like speaking style, naturalness, likability, and arousal. To prevent perceptual rewards from being optimized through transcript drift, we introduce a character error rate (CER) zone constraint and compare policy optimization with Best-of-

N

reranking under the same reward gate. Across single-reward runs, each reward primarily improves its own target metric, showing that subjective predictors are not interchangeable quality surrogates. Multi-rater A/B tests further show uneven human transfer, while a reward-gap analysis separates average transfer from within-axis calibration: signed reward gaps significantly predict listener choices in the pooled analysis, whereas residual CER gaps do not, but per-axis calibration remains heterogeneous. Best-of-8 is a strong human-level baseline and is not clearly worse than GRPO perceptually, suggesting that GRPO should be viewed as amortizing reward-selected behavior into the policy rather than uniformly outperforming reranking. These results support analyzing subjective speech rewards as predictor-axis-base tuples and provide practical diagnostics for selecting rewards before multi-reward speech post-training.

Joonyong Park, Jerry Li

Spellbrush

Reward Modeling RL for Language Models Speech Generation Evaluation TTS Evaluation Speech Language Models

Aug 30, 2026cs.AI

Beyond Uncertainty: Multi-Solver Disagreement Rewards for Self-Evolving Reasoning Curricula

Self-evolving reasoning frameworks train a Challenger to generate questions exposing a Solver's weaknesses, creating adaptive curricula without human data. However, existing approaches use a single solver's sampling uncertainty as the Challenger's reward. This creates a fundamental bottleneck: as the solver grows confident on the Challenger's question distribution, all sampled answers converge identically, collapsing the reward to zero and starving the Challenger of learning signal. Critically, this single-model reward cannot distinguish genuinely easy questions from those that merely align with one solver's learned biases. We propose a multi-solver disagreement reward using a heterogeneous ensemble varying in model capacity and sampling temperature. A normalized Shannon entropy over the ensemble's per-question plurality answers explicitly rewards questions where solvers produce conflicting solutions---capturing difficulty as inter-model divergence rather than intra-model sampling variance. This richer gradient enables the Challenger to discover questions targeting true capability boundaries, producing a curriculum that forces downstream Solvers to develop robust reasoning strategies generalizing across problem types. Our approach is a drop-in reward function replacement requiring no framework modifications or additional data. Experiments with Qwen3-4B show that Solvers trained on disagreement-Challenger questions achieve +1.34 points average improvement on competition-math benchmarks (MATH-500, AMC, Olympiad), suggesting that multi-solver disagreement provides a complementary and scalable signal for curriculum generation in self-play reasoning systems.

Vinoth Selvendran, Zhanming Zhang

Independent Researcher · Palo Alto, CA, USA · New York, NY, USA

Reward Modeling RL for Language Model Reasoning Curriculum RL Reward Design for RL Algorithmic Reasoning Self-Evolving Agents

Aug 19, 2026cs.CV

VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation

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.

Yinming Huang, Shuyuan Tu, Xi Yan +6

Fudan University · Shanghai Innovation Institution · Yinwang Intelligent Technology Co., Ltd +1

Reward Modeling Audio-Video Generation RL for Video Generation Human Preference Modeling Video Generation Evaluation

Aug 12, 2026cs.LG

A Framework for Designing Reward Functions: From Objectives to Features to Human-Aligned Reward Functions

We present a formal process to enable non-experts to instantiate and iterate on human-aligned reward functions, i.e. reward functions that adhere to a given preference ordering over trajectories. Given a task described in natural language, our process produces a linear reward function in three steps: distill the task's objectives into a set of fundamental objectives and derive measurable outcome variables that capture those fundamental objectives, select a causally representative subset of outcome variables as the reward terms, and fit weights to those reward terms via preference elicitation. Our contributions describe the first step and formalize the latter two steps. The first is a guided workflow for deriving outcome variables. The second is a reduction of reward term selection to minimum-cost partial cover on a causal DAG, solved in polynomial time via max-flow. The third is a geometric framing of weight fitting as a convex feasibility problem iteratively narrowed by preference queries, solved by existing separation oracle methods. To the best of our knowledge, this is the first reward-design method that maintains a deterministically conflict-free feasible weight region, narrowed to a desired tolerance via a separation oracle with O(n log κ) preference queries.

Di Yang Shi, W. Bradley Knox

University of Texas at Austin

Reward Modeling Reward Design for RL

Aug 12, 2026cs.SD

MuseCritic: Learning Multi-Aspect Song Rewards through Natural-Language Aesthetic Critiques

Long-form song generation models continue to improve in duration, structural coherence, and acoustic complexity, increasing the need for reliable aesthetic rewards aligned with human preferences. However, reward models for complete songs remain limited, and existing evaluators typically predict scores in a single forward pass without readable explanations. To this end, we introduce MuseCritic, a semi-scalar reward model that generates a natural-language critique covering five aesthetic dimensions and uses it as an intermediate representation to predict continuous reward scores. MuseCritic follows a two-stage training pipeline: a teacher model first provides high-quality critiques for supervised fine-tuning, then the fine-tuned model generates its own critiques for reward learning, mitigating training-inference distribution shift. On an in-domain test set of 200 SongEval songs, MuseCritic reduces macro-averaged mean squared error from 0.2875 to 0.2316 and improves macro-averaged LCC, SRCC, and Kendall's tau to 0.9068, 0.8838, and 0.7178, respectively. On the out-of-domain Music Arena benchmark with 733 preference pairs, it achieves 71.35% accuracy and remains competitive with strong music-specific reward models. Using MuseCritic with GRPO also improves Muse-0.6B on all nine aesthetic metrics from SongEval and Audiobox Aesthetics. These results show that critique-conditioned reward modeling reduces scoring error and provides an effective optimization signal for song generation. The project repository is available at https://github.com/WuqnEl/MuseCritic.

Jiabao Zhuang, Changhao Jiang, Hanchen Wang +11

Fudan NLP Group, Fudan University

Music Generation Evaluation Reward Modeling Music Generation

Aug 10, 2026cs.LG

Procedural Fairness Failures in RLHF from Preference Averaging

Reinforcement Learning from Human Feedback (RLHF) aggregates heterogeneous preferences into a single reward model, assuming preference homogeneity. When preferences are heterogeneous, this aggregation induces a procedural fairness failure where majority preference groups dominate reward learning while minority preferences are systematically under-represented. This work defines procedural fairness in alignment as preserving distinct preference signals during reward modeling and shows that standard RLHF violates this via preference averaging. Preference-Aware RLHF (PA-RLHF) is introduced, separating optimization across preference modes at the reward learning stage. In a controlled setting, PA-RLHF improves overall alignment accuracy from 46.9% to 67.9% and reduces the fairness gap between best and worst aligned groups from 15.9 to 9.6 percentage points. These results show that procedural fairness failures in alignment can arise from structural design choices in reward learning, even in controlled, noise-free settings, with direct implications for large language models and agentic systems, where biased reward models can compound inequities across sequential decisions.

M P V S Gopinadh, Karthik Kamuju, Kummari Avinash +2

Vishnu Institute of Technology

Reward Modeling Algorithmic Fairness Group Fairness Multi-Objective Language Model Alignment RL from Human Feedback

Aug 10, 2026cs.RO

RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance

General-purpose reward models are increasingly the bottleneck for scaling robot learning, yet the recipe for learning value-related capabilities from large-scale heterogeneous corpora remains underexplored. Existing approaches tie supervision to task-internal anchors such as preferences or normalized progress, none of which transfer cleanly across embodiments and data sources. We introduce RynnValue, an open-source value foundation model for robotic manipulation that replaces these anchors with temporal distance, the directed cost-to-go from an observation to the language-specified goal. Because temporal-distance labels can be derived directly from timestamps, RynnValue scales to over 7,000 hours and roughly 3M instruction-conditioned clips without preference or progress annotations. To make temporal-value learning reliable at scale, we combine random temporal sampling, temporal-order shuffling, and value-isolation attention, suppressing shortcuts that would leave predictions insensitive to failures and regressions. Trained without preference labels, RynnValue attains an average Kendall's

τ_a

of 0.704 on RBM-EVAL-OOD, surpassing the fully preference-supervised state of the art (0.655) and more than doubling a progress-only counterpart (0.292), while generalizing zero-shot to unseen tasks, embodiments, and viewpoints. As a zero-shot reward model, RynnValue serves a range of downstream applications. Converted into dense rewards via potential-based shaping, it raises real-world policy success from 52.5% to 72.5% online and from 63.8% to 82.5% offline; used for data filtering, it improves multi-task behavior cloning success from 35.0% to 42.5%; and applied as inference-time value guidance, it lifts a frozen policy's success from 67.5% to 80.0%. These results establish temporal distance as a scalable supervision target and practical reward interface for generalist robot policies.

Dongchi Huang, Hongyin Zhang, Bohan Hou +11

DAMO Academy, Alibaba Group · Hupan Lab

Reward Modeling Robot Foundation Models Multimodal Reward Modeling

Aug 10, 2026cs.LG

Finding the Signal in the Spam: Jointly Learning Rewards and Worker Reliability from Pairwise Comparisons

The problem of learning from pairwise comparisons has been widely studied across many domains such as recommendation systems, social choice, and more recently, fine-tuning large language models. In this problem, the goal is to learn item rewards based on pairwise comparisons between them. In many scenarios, these comparisons are elicited from crowdworkers using platforms such as Amazon Mechanical Turk, Scale AI, etc. However, crowdworkers are often unreliable due to limited domain knowledge or revenue-maximizing (spamming) behavior. In this work, our goal is to understand whether worker reliability (competency) can be learned jointly with item rewards. To this end, we adopt the Boltzmann-rational model for pairwise comparisons, which extends the Bradley-Terry-Luce model by incorporating worker competencies. We derive an EM-based algorithm for learning under this model by introducing Polya-Gamma latent variables to transform the logistic likelihood into a conditionally Gaussian form, enabling tractable optimization and leading to a simplified

Q

function in the E-step of the algorithm. This technique allows us to reduce our formulation to a matrix sensing problem, using which we establish theoretical convergence guarantees for our algorithm. We conduct extensive experiments on real-world and synthetic datasets. These experiments demonstrate the advantages of using our algorithm over several baselines and confirm its strong robustness to both spammers and adversarial workers, highlighting its practical effectiveness in realistic crowdsourcing and reward learning settings. The code and data is publicly available at https://github.com/KaustubhShejole/BoRa_EM.

Kaustubh Shivshankar Shejole, Tanish Agarwal, Arpit Agarwal +1

IIT Bombay, Mumbai, India – 400076

Pairwise Preference Learning Reward Modeling Inter-Rater Reliability Pairwise Preference Evaluation Learning with Noisy Labels

Aug 10, 2026cs.AI

CoRE: Consensus Rewards via Equilibrium for Test-Time Reinforcement Learning

On unlabeled test data, reinforcement learning lacks a ground-truth reward; test-time RL methods derive one from the model's own roll-outs, rewarding those that match the majority vote over

N

sampled answers. That vote discards a correct answer whenever it is a minority and scores every majority-matching roll-out identically. We replace it with \emph{CoRE} (Consensus Rewards via Equilibrium): the

N

roll-outs form a graph whose edges combine answer agreement, reasoning similarity, and generation confidence, and replicator dynamics extract its dominant set, yielding a refined pseudo-label, a graded per-roll-out reward, and a per-question cohesiveness gate. CoRE strictly generalizes voting: majority voting is recovered as a special case; a block-value analysis gives a sharp threshold for when consensus recovers a correct minority against a larger wrong plurality; and confidence calibration provably lowers that threshold multiplicatively. Across seven backbones and five benchmarks (42 model--benchmark cells, three seeds each), \emph{CoRE} improves the untrained base by

+21.7

points on average versus

+20.4

for majority-vote TTRL, wins wherever agreement is contestable with margins over the vote of up to

+7.5

points, and reaches the voting baseline's plateau accuracy in

54

--

70

% fewer steps. Consensus, not counting: treating the roll-out group as a graph rather than a ballot box turns a brittle vote into a calibrated, graded, self-supervised reward at no extra roll-out cost.

Ambuj Mehrish, Sebastiano Vascon

CVML Lab Ca’ Foscari University of Venice

Reward Modeling RL for Language Models RL for Language Model Reasoning Test-Time RL Reward Design for RL

Aug 9, 2026cs.AI

TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models

Reward models are a bottleneck for reinforcement learning in embodied AI. Long-horizon robotic manipulation requires scalable vision feedback beyond handcrafted rewards or task-specific annotations. Existing open-source VLM reward judges like RoboReward adopt simple 1--5 trajectory progress scoring, lacking pairwise preferences for RLHF, DPO and Bradley-Terry frameworks, while failing to optimize video scene understanding. Augmenting RoboReward with pairwise comparison and video-QA supervision causes inconsistency between pairwise preferences and pointwise scores, introducing training noise and hurting downstream performance---an issue aggregation methods such as TrustJudge cannot resolve. To address this, we propose TrustRoboReward, a multi-paradigm reward modeling framework equipped with Preference-Ordered Isotonic Score Editing (POISE). We construct a unified four-paradigm dataset with trajectory progress scoring (Score-A), video-QA answer quality scoring (Score-B), and their pairwise counterparts (Pair-A, Pair-B). Pairwise labels align better with human judgment than pointwise scores, inspiring us to calibrate pointwise scores to avoid score-pair reversals against pairwise preferences. POISE rectifies pointwise scores and eliminates cross-paradigm reversal conflicts unresolved by TrustJudge. Theoretically, POISE reduces score-pair reversal conflicts from 20.15% to 0%, whereas TrustJudge retains 20.46% conflicts on the same corpus. Evaluated on our benchmark, Qwen3-VL-4B trained with POISE achieves an overall reward score of 77.96%, nearly matching GPT-5-mini (78.09%, gap 0.13%) and outperforming the strongest RoboReward-4B baseline by 10.13%. It also lifts test-time score-pair consistency to 71.90%, exceeding RoboReward-4B (57.26%) and GPT-5-mini (68.09%). Integrating TrustJudge aggregation during inference boosts the overall score to 78.57%, surpassing the GPT-5-mini teacher model.

Yidong Wang, Yan Zhan, Ziteng Feng +16

Peking University · University of Science and Technology of China · Southeast University +6

Reward Modeling Pairwise Preference Evaluation Multimodal Reward Modeling Isotonic Regression

Aug 6, 2026cs.LG

RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction

Recent advances in reward modeling show a paradigm shift from discriminative reward models to generative reward models. However, despite their strong capabilities in response ranking, generative reward models have not realized their potential in reinforcement learning (RL). Our analysis reveals that this limitation arises from a mismatch between the comparative nature of generative reward modeling and the scalar scoring paradigm adopted by existing RL algorithms. To bridge this gap, we propose a Ranking-based Reward Construction (RRC) approach, which enables generative reward models to provide more effective RL learning signals by deriving rewards from relative preference rankings. RRC introduces two complementary strategies: self-competitive ranking, which exploits comparisons among sampled responses, and anchor-guided ranking, which enables scalable ranking-based reward construction with a small set of reference responses. Experiments across open-ended chat and reasoning benchmarks demonstrate that RRC substantially improves RL training with generative reward models, achieving consistent gains over existing reward construction approaches. Our code can be found at https://github.com/wangclnlp/RRC.

Chenglong Wang, Ziming Zhu, Yifu Huo +9

School of Computer Science and Engineering, Northeastern University, Shenyang, China · 2NiuTrans Research, Shenyang, China · 3Independent Researcher, Beijing, China +1

Reward Modeling RL for Language Models Reward Design for RL

Aug 4, 2026cs.RO

EvoHIL: Self-Evolving Reward and Flow-Matched Policy Optimization for Robust Human-in-the-Loop Reinforcement Learning

Human-in-the-loop reinforcement learning (HIL-RL) enables robots to learn contact-rich manipulation from limited real-world interaction, but deployment exposes three coupled limitations: static visual reward models fail under scene changes; independently sampled actions cause temporally inconsistent motion; and vision-based policies remain sensitive to appearance shifts. We present EvoHIL, a unified framework that adapts the reward model, action generator, and visual do main within a staged human-in-the-loop learning process. First, self-evolving reward (SER) adapts the success classifier from human-confirmed positives and provisional weak negatives. Second, Action Flow Stabilization (AFS) generates temporally coherent action chunks through flow matching, grounding policy updates in executed action prefixes and demonstrated behavior. Third, retention-aware offline fine-tuning replays relit interaction data while anchoring the AFS actor-critic to prior behavior, adapting the visual domain without additional robot interaction. Across six manipulation tasks on Franka FR3 and SO-101 arms under a controlled lighting shift, EvoHIL improves task success, agreement with human-confirmation labels, motion smoothness, and completion time relative to human-in-the-loop and imitation baselines.Project page: https://anonymous4366.github.io/EvoHIL/

Shuoqin Zhang, Tongtong Cheng, Xiru Gao +7

Reward Modeling Robot Policy Learning Human-in-the-Loop AI Robust RL

Aug 3, 2026cs.LG

Rethinking Personalized Reward Modeling for LLMs under Preference Heterogeneity via Group-Debiased Federated Learning

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.

Seongyoon Kim, Boryeong Cho, Jihwan Oh +2

Institute of Engineering Research, Korea University Seoul, Republic of Korea · Kim Jaechul Graduate School of AI, KAIST Seoul, Republic of Korea · Industrial Management Engineering, Korea University Seoul, Republic of Korea

Pairwise Preference Learning Reward Modeling LLM Alignment Federated Learning Aggregation Federated Learning Heterogeneous Federated Learning

Jul 31, 2026cs.AI

Beyond Routing Weights: Faithful Response-Level Interpretation of Mixture-of-Experts Reward Models via Contribution Contrast

Reward models are central to learning from human preferences, yet identifying what drives their predictions remains challenging. Recent sparse Mixture-of-Experts (MoE) reward models seek to improve interpretability by routing prompts to specialized experts and characterizing experts through examples with high routing weights. However, routing weights only reveal which prompts an expert

\textit{receives}

, not how it

\textit{judges}

responses, providing only a partial account of expert behavior. We therefore propose

\textbf{Co}

ntribution-

\textbf{Co}

ntrast (

\textbf{CoCo}

) response-level interpretation, which faithfully characterizes experts' roles using chosen-rejected response pairs with the largest contribution contrasts, jointly capturing routing and preference behavior. Across automatic and human evaluations, CoCo yields more coherent, faithful, and specialized interpretations than router-based, score-based, and sparse autoencoder-based alternatives while maintaining competitive reward modeling accuracy. To the best of our knowledge, this is the first systematic study of interpretation methods for MoE reward models.

Yifan Wang, Jinyi Mu, Mayank Jobanputra +4

Saarland University · University of California San Diego · Bielefeld University +2

Reward Modeling Neural Network Interpretability Mixture-of-Experts Models

Jul 31, 2026cs.CL

Learning Latent Reasoning Traces for Scalar Reward Models End-to-End

Reward models (RMs) are central to aligning large language models with human preferences via reinforcement learning. Although traditional scalar RMs enable efficient and probabilistic reward modeling, they rely on superficial cues that fail to generalize to complex or out-of-distribution (OOD) tasks. Conversely, generative RMs leverage extensive reasoning to improve robustness on challenging tasks, but their natural language-based scores lack the numerical flexibility and probabilistic interpretability that scalar RMs offer. While recent approaches combine both paradigms through off-policy multi-task learning, such parallel optimization does not guarantee that generated reasoning traces actively align with or benefit downstream scalar reward prediction. To address this mismatch, we propose LatentRM, a reward modeling framework that learns intermediate reasoning traces as discrete latent variables to explicitly maximize the likelihood of downstream scalar rewards. Through on-policy optimization of the latent reasoning space end-to-end, LatentRM tightly couples deep reasoning-based evaluation with precise scoring. Extensive validations on in-distribution and OOD datasets and RLHF show that LatentRM outperforms scalar, generative, and hybrid RMs on preference modeling and policy alignment across tasks ranging from open-ended conversation to complex reasoning.

Sanwoo Lee, Clive Bai, Hsiu-Yuan Huang +3

National Key Laboratory for Multimedia Information Processing, Peking University · School of Computer Science, Peking University · LLM Department, Tencent

Reward Modeling LLM Alignment Latent Variable Models Process Reward Models Preference-Based RL

Jul 30, 2026cs.AI

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

Computer-using agents (CUAs) are advancing rapidly across the digital world. A CUA trajectory records the agent's actions, states, and reasoning. Verifying whether it fulfilled the task instruction is central to CUA evaluation, data curation, and reinforcement learning. Neither human-written verifiers nor human annotators can provide such verification at scale, so the field increasingly turns to vision-language models (VLMs) as judges of CUA trajectories. But a fundamental question has long gone unexamined: are these VLM judges reliable enough? To study it systematically, we introduce OSReward, a realistic, high-quality benchmark that evaluates VLM judges on CUA trajectories. The trajectories come from diverse agent backbones executing human-verified instructions across platforms, and are then rigorously labeled with ground-truth verdicts through multi-stage human annotation. Building on it, we derive OSReward-Hard, a challenge set concentrating genuinely hard cases, and OSReward-Multi for fine-grained efficiency and alignment scoring. The most comprehensive evaluation of VLM judges to date finds even state-of-the-art models fall short of an ideal judge, sharing a systematic leniency bias that mislabels failed runs as successes. The few reliable enough to trust are too expensive to run at scale, while affordable open models trail far behind. To close this gap, we construct and release OS-Shepherd-100K, an open corpus of reasoning-annotated trajectory judgments for the CUA community. On it, we train OS-Shepherd (9B and 35B), open reward models that supply low-cost, stable, and reliable reward signals, matching commercial judges at 30-60x lower cost than the frontier. Extensive analyses further inform the design of reliable CUA reward at scale. Our code, benchmark, dataset, and model checkpoints are available at https://os-copilot.github.io/OSReward-Home/.

Qiushi Sun, Kanzhi Cheng, Yian Wang +20

The University of Hong Kong · Nanjing University · National University of Singapore +4

VLM Evaluation Computer-Use Agent Benchmarks Reward Modeling Computer-Use Agents Multimodal Reward Modeling Reward Model Evaluation

Jul 27, 2026cs.CL

DS@GT ARC at CheckThat! 2026: LLM-Based Trace Ranking and Grouped Reward Modeling for Multilingual Numerical Claim Verification

Automated verification of numerical claims is a challenging problem, as it requires both language understanding and quantitative reasoning. This paper describes our system for CLEF 2026 CheckThat! Task 2, which focuses on ranking reasoning traces generated by large language models (LLMs) and predicting a final verdict for numerical claims in English and Arabic. We explore two approaches. The first approach fine-tunes an LLM-based verifier using LoRA to score each reasoning trace independently as a binary classification problem, and selects the final verdict using Best-of-N selection. We further experiment with adaptive sub-claim decomposition to break complex claims into simpler parts before verification. The second approach uses a lightweight TF-IDF reward model with handcrafted numeric and temporal overlap features to score traces, and aggregates scores by verdict group to determine the final prediction. For Arabic, we compare a general multilingual model against AraBERT, a language-specific model pretrained on Arabic text. Our results show that the LLM-based approach outperforms the lightweight reward model on most metrics, particularly Recall@5, while the reward-based approach shows stronger performance on the Conflicting class. Sub-claim decomposition did not improve performance, suggesting that claim splitting introduces noise rather than aiding reasoning. For Arabic, AraBERT outperforms the multilingual baseline across most metrics.

Sagnik Sinha, Shreyas Shrestha

Georgia Institute of Technology, North Ave, Atlanta, GA 30332, United States

Numerical Reasoning in Language Models Reward Modeling Claim Verification

Jul 27, 2026cs.LG

What do Reward Models Memorize?

This paper studies what discriminatively trained reward models (RMs) memorize by measuring counterfactual memorization on two human preference datasets. We show that RMs 1) misallocate memorization to easy, high margin preference pairs, 2) memorize dataset-specific shortcuts (e.g., model identity, user sampling strategy), and 3) overgeneralize simple heuristic correlates of human preference (e.g., length, compliance) when confronted with unseen preference pairs. Overall, our findings indicate that discriminative training of RMs from human preference data results in biased RMs not yet capable of judging response quality in context-dependent scenarios.

Ivo Verhoeven, Pushkar Mishra, Ekaterina Shutova

ILLC, University of Amsterdam, The Netherlands · Google DeepMind, London, United Kingdom

Reward Modeling Pairwise Preference Evaluation Human Preference Modeling Shortcut Learning

Jul 25, 2026cs.AI

SeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents

Deciding whether a trajectory actually fulfills its instruction governs how we measure computer-use agents on long-horizon graphical-user-interface tasks and how we train them with reinforcement learning. This judgment has long relied on rule-based evaluation, which struggles to align with human intention and goes stale when an app updates or its online content drifts. Existing model-based judges attempt to address these problems but still leave a performance gap to the rule-based evaluation. We propose the \textbf{SeekJudge} framework, in which four role-specialized agents, a Condense, a Ground, a Seek and an Analyze agent, reach a verdict through a Seek--Analyze loop over the trajectory. A seed-calibrated distillation pipeline trains one specialized

9

B model to serve as the shared backbone for all four agents. Measured by downstream success rate on held-out RL test goals, SeekJudge is the first practical model-based reward to match or surpass native rule-based supervision in online RL. Beyond accuracy, SeekJudge provides step-level judgments, runs far cheaper than a closed-source large model, and keeps a small per-call context that scales to much longer trajectories. We further contribute a general architectural improvement to the reward server that speeds up judging in RL. Together these make model-based reward a practical drop-in for rule-based supervision in CUA reinforcement learning.

Yang Wan, Zhenhao Zhang, Jierui Wang +1

1Zhejiang University · University of Rochester

Reward Modeling LLM-as-a-Judge RL for GUI Agents Computer-Use Agents Long-Horizon Agent Evaluation Reward Model Evaluation+1

Jul 23, 2026cs.CL

CSPF: A Constrained Shared-Private Fusion Method for Non-Verifiable Preference Evaluation

At present, reliable evaluation of non-verifiable tasks remains challenging. Existing approaches often fail to adequately capture the diverse evaluative criteria underlying human preferences in such tasks. To this end, we propose Constrained Shared-Private Fusion (CSPF), a fusion method that treats heterogeneous frozen reward models as complementary evaluators and learns to integrate their hidden-state representations under pairwise human-preference supervision. CSPF decomposes each expert signal into shared and expert-private representations, encouraging cross-expert alignment while preserving complementary viewpoints. Across experiments on LM-Arena target-domain adaptation and PPE out-of-distribution preference evaluation, CSPF achieves the best performance on the primary metrics among the evaluated single-expert reward-model, scalar-score multi-expert, and rubric-judge baselines. Overall, CSPF suggests that fusing hidden-state representations provides a more expressive basis for preference assessment, offering a practical route toward integrated evaluative signals for non-verifiable preference tasks.

Hehao Zhang, Danli Wang, Xinyuan Wang +1

Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China

Pairwise Preference Learning Reward Modeling Pairwise Preference Evaluation

Jul 22, 2026cs.RO

Progress Reward Modeling for Robotic Learning: A Comprehensive Survey

Robotic learning takes place in dynamic environments with large behavior spaces. A terminal success signal only tells the robot whether the task is completed. It does not explain whether the current behavior is making progress, remaining unchanged, or undoing earlier progress. For this reason, recent studies have increasingly explored progress rewards that provide feedback during task execution. However, the current literature lacks a shared framework. Existing methods use different observations, goal specifications, output signals, supervision sources, and evaluation protocols. This makes it difficult to compare them and understand what their results actually validate. In this survey, we provide a unified view of progress reward modeling for robotic learning. We organize the field in three connected steps. We first study the interface of a progress model. This defines the problem from the outside by asking what information the model receives and what form of progress signal it produces. We then move inside the model and study the methods used to construct this signal. This reveals the different assumptions and mechanisms behind progress estimation and reward generation. Finally, we examine the data and benchmarks that support these methods. This shows how progress supervision is obtained and what different evaluations actually measure. Together, these three perspectives connect what a progress model is, how it is built, and how its quality is validated. We further summarize the main limitations of current approaches and discuss future research directions.

Jianshu Zhang, Keliang Wu, Haoran Lu +8

Northwestern University · Carnegie Mellon University · University of Wisconsin–Madison +2

Reward Modeling Process Reward Models Robotic RL Robot Learning

Jul 22, 2026cs.LG

How Fast Can Reward Models Score? A Systems Study of C++ and PyTorch Inference Runtimes for RLHF

In RLHF pipelines, reward scoring blocks policy updates. Slow scoring bottlenecks the entire loop, since no update runs until every rollout gets a score. And yet most setups just default to PyTorch eager mode or torch.compile, no one checks if that's actually fastest. Scoring itself is small. Rollout generation eats far more of a typical RLHF step. But scoring and generation fight over the same CPU and GPU resources, so a faster scoring engine doesn't shrink step time on its own. It mainly frees up capacity generation can use instead. We built a native C++ inference engine on ONNX Runtime. First step: confirm correctness. Output matched the PyTorch reference to 5.7 x 10^-6 on CPU and 4.2 x 10^-3 on GPU, close enough to trust. Then we tested it against PyTorch eager mode, torch.compile, and FastAPI, on both CPU and GPU. CPU was decisive. Our engine beat every baseline, confidence intervals didn't even overlap. GPU gave a different view: we beat PyTorch and FastAPI, but torch.compile came out ahead. Further testing traced the speedup to ONNX Runtime itself, not C++ as a language. And batching strategy mattered more than either the language or the runtime choice, more than we expected. The results are from repeated, independent runs, since single runs just aren't reliable enough to trust.

Venkata Naga Sai Vishnu Rohit Pulipaka, Anish Katta, Deva Rohit Reddy Peddireddy

Efficient Neural Network Inference Reward Modeling Inference Acceleration LLM Inference Acceleration

Jul 19, 2026cs.AI

Reward-Driven LLM Agent Workflows: Synthesizing POMDP Routing and Self-Correction for Autonomous Decision-Making

This paper addresses key technical challenges in current large language model (LLM) agent applications, including long-horizon planning, sparse reward attribution, and dynamic environmental interaction, by designing and optimizing an intelligent agent workflow. The proposed architecture is based on the synthesis of core AI paradigms: Visual, Language, Generative, Graph, Multimodal, Reinforcement, and Agent Intelligence. Unlike conventional baseline models that rely on static prompting and lack robust perception-action loops, our approach introduces a Partially Observable Markov Decision Process (POMDP) routing mechanism. This mechanism is augmented with an internal, self-correcting reward model that evaluates decision trajectories before execution. By integrating multimodal inputs and advanced reinforcement learning principles (such as proximal policy optimization and value function approximation), the agent maintains long-term structural memory and dynamically adapts its reasoning pathways to mitigate error accumulation. Empirical experiments on the ALFWorld embodied simulation environment and the WebShop online navigation benchmark demonstrate a 24.5% absolute improvement in task success rate and trajectory efficiency over mainstream baselines like the standard ReAct framework. Comprehensive ablation studies confirm the significant contribution of the reward-driven critique module in suppressing hallucination rates. This research bridges theoretical foundations of reinforcement learning and graph-based memory with autonomous agent workflows. Ultimately, the resulting architecture offers a practical, scalable reference framework for developing artificial intelligence technologies in complex, multi-step autonomous systems. Code is available at https://github.com/01Amez/RLAW_Implementation.

Amez Amanj Ali, Kuo-Kun Tseng

School of Computer Science and Technology Harbin Institute of Technology, Shenzhen

Reward Modeling LLM Self-Correction Partially Observable RL RL for LLM Agents

Jul 18, 2026cs.CY

A Method for Learning Value Systems in Generative AI

Value-aware AI systems require explicit computational representations of human values (groundings) and their aggregation into value systems in order to align their decisions with ours. As such representations are difficult to elicit, value learning seeks to infer them by observing human behaviour. This work addresses the lack of grounded value learning methods in generative AI: existing approaches typically replicate human preferences without awareness of the multidimensional structure of value alignment, or lack principled value system elicitation methods. To address these gaps, we adapt a previously validated value system learning method to the generative AI setting, which, based on pairwise prompt-response preference data, simultaneously learns: i) an implementation of a grounding for a set of values given by a multi-objective reward model, and ii) a value system representation in the form of a weighted linear scalarization of the previous grounding model. To ensure that the learned value systems are based on coherent value representations, our algorithm dynamically prioritizes the grounding learning process. We evaluate the method against baselines and a contemporary method on prompt-response preference datasets. Results show competitive performance and minimal trade-offs against the baselines, while improving explainability.

Andrés Holgado-Sánchez, Holger Billhardt, Sascha Ossowski

1CETINIA, University Rey Juan Carlos

Reward Modeling LLM Alignment Preference Learning

Jul 17, 2026cs.CV

Debiasing Text-to-Image Evaluation via Implicit Cultural Alignment Reward Modeling

As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synthesized content has become increasingly important for fair and trustworthy generative AI. Existing T2I evaluation metrics and multimodal judges often rely on visual-semantic representations that underrepresent implicit cultural norms, leading to biased preference judgments and the omission of fine-grained cultural cues. In addition, visual question answering (VQA)-based evaluators typically depend on autoregressive text generation, which limits their scalability for real-time reward modeling. To address these limitations, we introduce an Implicit Cultural Alignment Reward Model built upon a lightweight 4.2-billion-parameter Multimodal Large Language Model (MLLM). Our framework integrates an Implicit Cultural Probe with a Skip-connection Cross-Attention (SkipCA) mechanism, enabling late-stage semantic features to directly attend to early-stage visual representations and better preserve culturally salient details. Evaluations on 3,323 challenging and carefully curated image pairs from the CulturalFrames benchmark show that our approach achieves 83.49% pairwise accuracy, with Pearson and Kendall correlation coefficients of 0.5268 and 0.3749, respectively, outperforming representative vision-language metrics and MLLM-based evaluators. Moreover, by bypassing autoregressive text generation, our model processes each evaluation in 0.21 seconds under our local inference setup, achieving a

10\times

speedup over standard VQA-based evaluators. These results suggest that the proposed reward model can provide an efficient and culturally aware scalar signal for preference optimization pipelines such as Reinforcement Learning from Human Feedback and Direct Preference Optimization. Additional resources are available on our project page at https://bensonch1214.github.io/Implicit_Cultural_Alignment/.

Bo-An Chang, Yu-Chih Chen

National Tsing Hua University, Hsinchu 300044, Taiwan · National Yang Ming Chiao Tung University, Hsinchu 300093, Taiwan

VLM Evaluation Reward Modeling T2I Generation T2I Generation Evaluation

Jul 15, 2026cs.LG

Long-term User Engagement Optimization through Model-agnostic Downstream Rewards Learning

As recommender systems mature in the past few years, their optimization objectives have evolved from a primary focusing on short-term behavioral signals to a broader emphasis on long-term user engagement and retention. However, directly optimizing retention is difficult because return signals are sparse, delayed, and only partially attributable to earlier recommendations. Prior work has addressed this challenge with sequential modeling and reinforcement learning, but these approaches typically require task specific reward engineering, substantial computational overhead, and surface specific implementations that are difficult to generalize. In this paper, we present a unified, model-agnostic downstream reward framework for optimizing long-term user value in large-scale recommendation systems. First, we formulate the downstream reward learning problem and develop an offline screening framework to identify session level behaviors that are both observable early and predictive of future retention. We then propose several model-agnostic downstream rewards signals derived from observed user action patterns across multiple sources. We further discuss the engineering effort to productionize the proposed rewards derivations and challenges we faced when adding them to our ranking models. Online A/B experiments demonstrate consistent improvements in engagement and retention-related metrics, and the framework has been deployed across multiple Pinterest surfaces, including Homefeed, Related Pins, Search, and Notifications.

Dingsu Wang, Filip Ryzner, Kelly He +12

Pinterest San Francisco, CA, USA

Reward Modeling Learning to Rank Recommender Systems

Jul 14, 2026cs.RO

DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation

Reinforcement learning holds great promise for improving robot policies beyond the limits of imitation learning. However, its practical adoption remains bottlenecked by the lack of reliable vision-language reward models that provide dense and informative feedback. Two key challenges remain: acquiring diverse failure data at scale and obtaining fine-grained reward signals beyond sparse trajectory-level success labels. Collecting failure trajectories typically requires laborious human effort, while pseudo-failures constructed by relabeling successful demonstrations fail to capture the diverse physical failure modes that arise during robot execution. Meanwhile, existing reward models often predict sparse binary or trajectory-level rewards, which provide limited guidance for efficient policy optimization. We introduce DenseReward, a dense robotic reward model that addresses both challenges. To train DenseReward, we develop an automated failure data generation pipeline that synthesizes physically realistic failure trajectories in simulation without human labeling, covering diverse failure modes such as collisions, missed grasps, object drops, and recovery behaviors. DenseReward predicts dense frame-level reward scores from visual observations and language instructions, enabling fine-grained estimation of task progress throughout an episode. Experiments show that DenseReward outperforms general-purpose VLMs and existing robotic reward models in dense reward prediction across both simulated and real-world manipulation. We further demonstrate that DenseReward provides effective reward guidance for downstream model predictive control and reinforcement learning. We release the dataset, trained reward models, and evaluation suite to support the development of failure-aware dense reward modeling for robot learning.

Yu Fang, Wanxi Dong, Jiaqi Liu +7

University of North Carolina at Chapel Hill · Carnegie Mellon University · Shanghai Jiao Tong University +1

RL for Robotics Reward Modeling Multimodal Reward Modeling Robotic Manipulation

Jul 7, 2026cs.LG

Reward Valuation in Large Language Models: Causal Induction of Anhedonia

Recent frontier models mimic complex aspects of human cognition. Here we ask whether this alignment extends into reward valuation, which we assess in a mechanistic framework. Specifically, we use clinical tests that were developed to evaluate anhedonia in human subjects with major depressive disorders. Mechanistically, anhedonia is frequently associated with dysregulation in the Nucleus Accumbens (NAc) and the broader dopaminergic reward system. While neuroimaging has localized these deficits, establishing a causal link between NAc activity and specific behavioral symptoms remains a challenge. We use these ideas from neuroscience to functionally identify reward-anticipatory units in state-of-the-art AI models, and evaluate their causal involvement via targeted perturbations. We find that not only are such model units predictive of NAc brain recordings, their perturbation also induces behavioral effects mirroring human anhedonia: the model opts for low-effort, low-reward tasks in effort-based decision-making paradigms. Crucially, our results demonstrate that this represents a specific deficit in self-centered reward valuation and anticipation--rather than a loss of task capability, reward calculation, or effort avoidance. This induced vulnerability aligns with clinical measures of anhedonia and motivation in humans, such as DARS and MAP-SR, instruments that contain no reward-related vocabulary, ruling out a purely lexical account of the perturbation effect. Taken together, our results suggest reward valuation circuits in AI models that functionally mimic those in humans.

Melika Honarmand, Samin Mahdipour Aghabagher, Martin Schrimpf

NeuroAI Laboratory, EPFL

Reward Modeling Cognitive Modeling LLM Interpretability Causal Interventions in Language Models