ICLR 2026 Papers

Large Reasoning Models (LRMs) have shown remarkable capabilities in solving complex problems through reinforcement learning (RL), particularly by generating long reasoning traces. However, these extended outputs often exhibit substantial redundancy, which limits the efficiency of LRMs. In this paper, we investigate RL-based approaches to promote reasoning efficiency. Specifically, we first present a unified framework that formulates various efficient reasoning methods through the lens of length-based reward shaping. Building on this perspective, we propose a novel **L**ength-b**A**sed **S**t**E**p **R**eward shaping method (LASER), which employs a step function as the reward based on target length. LASER surpasses previous methods, achieving a superior trade-off between performance and efficiency. Next, we further extend LASER based on two key intuitions: (1) The reasoning behavior of the model evolves dynamically during training, necessitating reward specifications that are also adaptive and dynamic; (2) Rather than uniformly encouraging shorter or longer chains of thought (CoT), we posit that length-based reward shaping should be difficulty-aware i.e., it should penalize lengthy CoTs more for easy queries. This approach is expected to facilitate a combination of fast and slow thinking, leading to a better overall tradeoff. The resulting method is termed LASER-D (**D**ynamic and **D**ifficulty-aware). Experiments on five open-weight models from 1.5B to 32B demonstrate that our approach significantly enhances both reasoning performance and response length efficiency. For instance, LASER-D achieves a **5.3** improvement on AIME2024 while reducing token usage by **64**%. Further analysis reveals that our RL-based compression produces more concise reasoning patterns with less redundant ``self-reflections''.

Optimistic exploration is central to improving sample efficiency in reinforcement learning with human feedback, yet existing exploratory bonus methods often fail to realize true optimism. We provide a theoretical analysis showing that current formulations, under KL or $\alpha$-divergence regularization, unintentionally bias exploration toward high-probability regions of the reference model, thereby reinforcing conservative behavior instead of promoting discovery of uncertain regions. To address this pitfall, we introduce the General Exploratory Bonus (GEB), a novel theoretical framework that provably satisfies the optimism principle. GEB counteracts divergence-induced bias via reference-dependent reward regulation and unifies prior heuristic bonuses as special cases, while extending naturally across the full $\alpha$-divergence family. Empirically, GEB consistently outperforms baselines on alignment tasks across multiple divergence settings and large language model backbones. These results demonstrate that GEB offers both a principled and practical solution for optimistic exploration in RLHF.

Current online reinforcement learning (RL) algorithms like GRPO share a key limitation in LLM reasoning: they cannot learn from problems that are "unsolvable" to the model. In other words, they can only improve performance on problems where the model is capable of exploring the correct answer. If a problem is too difficult -- such that even hundreds of attempts never produce a correct solution -- the model cannot learn from it. Consequently, the model's "upper limit" remains unchanged after RL training, even though the likelihood of solving easier, solvable problems may increase. These hard, unsolvable samples -- though potentially rich in learning signal -- cannot contribute to training, as no rollouts yield rewards and thus no gradients are produced. To unlock learning from these hard samples, we propose NuRL, a "nudging" method that aims to push the upper bound of LLM reasoning using self-generated hints, i.e., abstract cues that help reduce the problem difficulty for the model. Given a question and its gold answer, the model generates a Chain-of-Thought (CoT) and then produces a hint containing the core knowledge needed to solve the problem. During online RL training, we generate G rollouts from the base policy and use the pass rate to decide whether the hint should be injected. For hard samples with a 0% pass rate, we inject the offline-generated hint and regenerate a new batch of trajectories. This yields two benefits: (1) the hint boosts pass rates (from 0% to non-zero), thereby introducing training signals for previously unsolvable samples, and (2) the hints are self-generated (conditioned on the gold answer), avoiding distributional shift and do not rely on external models. Compared to standard GRPO, NuRL achieves consistent improvements across six diverse benchmarks and three models, while remaining complementary to test-time scaling. Notably, NuRL can raise the model's upper limit, whereas GRPO leaves pass@1024 unchanged from the base model. Furthermore, we present a systematic study of what makes an effective hint and when hints are most useful. Interestingly, the best hints are abstract and high-level -- as revealing gold answers actually hurt performance -- and are most beneficial when applied necessarily and after GRPO has converged.

Enhancing the complex reasoning capabilities of Large Language Models (LLMs) attracts widespread attention. While reinforcement learning (RL) has shown superior performance for improving complex reasoning, its impact on cross-lingual generalization compared to Supervised Fine-Tuning (SFT) remains unexplored. We present the first systematic investigation into cross-lingual reasoning generalization of RL and SFT. Using Qwen2.5-3B-Base as our foundation model, we conduct experiments on diverse multilingual reasoning benchmarks, including math reasoning, commonsense reasoning, and scientific reasoning. Our investigation yields two significant findings: (1) Tuning with RL not only achieves higher accuracy but also demonstrates substantially stronger cross-lingual generalization capabilities compared to SFT. (2) RL training on non-English data yields better overall performance and generalization than training on English data, which is not observed with SFT. Furthermore, through comprehensive mechanistic analyses, we explore the underlying factors of RL's superiority and generalization across languages. Our results provide compelling evidence that RL enables the model with more robust reasoning strategies, offering crucial guidance for more equitable and effective multilingual reasoning.

We introduce GDPval, a benchmark evaluating AI model capabilities on real-world economically valuable knowledge-work tasks. GDPval covers the majority of Department of Labor O*NET Work Activities for 44 occupations across the top 9 sectors contributing to U.S. GDP (Gross Domestic Product). Tasks are constructed from the representative work of industry professionals with an average of 14 years of experience. We find that frontier model performance on GDPval is improving roughly linearly over time, and that the current best frontier models are approaching industry experts in deliverable quality. We analyze the potential for frontier models, when paired with human oversight, to perform GDPval tasks cheaper and faster than unaided experts. We also demonstrate that increased reasoning effort, increased task context, and increased scaffolding improves model performance on GDPval. Finally, we open-source a gold subset of 220 tasks and provide a public automated grading service to facilitate future research in understanding real-world model capabilities.

Masked diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive LLMs, offering competitive performance while supporting unique generation capabilities such as inpainting. We explore how inpainting can inform RL algorithm design for dLLMs. Aligning LLMs with reinforcement learning faces an exploration challenge: sparse reward signals and sample waste when models fail to discover correct solutions. While this inefficiency affects LLMs broadly, dLLMs offer a distinctive opportunity—their inpainting ability can guide exploration. We introduce IGPO (Inpainting Guided Policy Optimization), an RL framework that strategically inserts partial ground-truth reasoning traces during online sampling. Unlike providing full solutions, inpainting steers exploration toward promising trajectory spaces while preserving self-generated reasoning, bridging supervised fine-tuning and reinforcement learning. We apply IGPO to group-based optimization methods such as GRPO, where exploration failures cause zero advantages and gradients. IGPO restores meaningful gradients while improving sample efficiency. We also propose supervised fine-tuning on synthetically rewritten concise traces that better align with dLLM generation patterns. With additional techniques including entropy-based filtering, our training recipe yields substantial gains across four mathematical benchmarks—GSM8K, Math500, AMC and Minerva—achieving new state-of-the-art results for full-attention masked dLLMs.

Recent studies have extended Reinforcement Learning with Verifiable Rewards (RLVR) to autoregressive (AR) visual generation and achieved promising progress. However, existing methods typically apply uniform optimization across all image tokens, while the varying contributions of different image tokens for RLVR's training remain unexplored. In fact, the key obstacle lies in how to identify more critical image tokens during AR generation and implement effective token-wise optimization for them. To tackle this challenge, we propose $\textbf{G}$roup $\textbf{C}$ritical-token $\textbf{P}$olicy $\textbf{O}$ptimization ($\textbf{GCPO}$), which facilitates effective policy optimization on critical tokens. We identify the critical tokens in RLVR-based AR generation from three perspectives, specifically: $\textbf{(1)}$ Causal dependency: early tokens fundamentally determine the later tokens and final image effect due to unidirectional dependency; $\textbf{(2)}$ Entropy-induced spatial structure: tokens with high entropy gradients correspond to image structure and bridges distinct visual regions; $\textbf{(3)}$ RLVR-focused token diversity: tokens with low visual similarity across a group of sampled images contribute to richer token-level diversity. For these identified critical tokens, we further introduce a dynamic token-wise advantage weight to encourage exploration, based on confidence divergence between the policy model and reference model. By leveraging 30\% of the image tokens, GCPO achieves better performance than GRPO with full tokens. Extensive experiments on multiple text-to-image benchmarks for both AR models and unified multimodal models demonstrate the effectiveness of GCPO for AR visual generation.

Personalized alignment of large language models seeks to adapt responses to individual user preferences, typically via reinforcement learning. A key challenge is obtaining accurate, user-specific reward signals in open-ended scenarios. Existing personalized reward models face two persistent limitations: (1) oversimplifying diverse, scenario-specific preferences into a small, fixed set of evaluation principles, and (2) struggling with generalization to new users with limited feedback. To this end, we propose **P-GenRM**, the first **P**ersonalized **Gen**erative **R**eward **M**odel with test-time user-based scaling. P-GenRM transforms preference signals into structured evaluation chains that derive adaptive personas and scoring rubrics across various scenarios. It further clusters users into User Prototypes and introduces a dual-granularity scaling mechanism: at the individual level, it adaptively scales and aggregates each user’s scoring scheme; at the prototype level, it incorporates preferences from similar users. This design mitigates noise in inferred preferences and enhances generalization to unseen users through prototype-based transfer. Empirical results show that P-GenRM achieves state-of-the-art results on widely-used personalized reward model benchmarks, with an average improvement of ~2.31\%, and demonstrates strong generalization on an out-of-distribution dataset. Notably, Test-time User-based scaling provides an additional ~3\% boost, demonstrating stronger personalized alignment with test-time scalability.

Active perception is a fundamental skill that enables us humans to deal with uncertainty in our inherently partially observable environment. For senses such as touch, where the information is sparse and local, active perception becomes crucial. In recent years, active perception has emerged as an important research domain in robotics. However, current methods are often bound to specific tasks or make strong assumptions, which limit their generality. To address this gap, this work introduces APPLE (Active Perception Policy Learning) - a novel framework that leverages reinforcement learning (RL) to address a range of different active perception problems. APPLE jointly trains a transformer-based perception module and decision-making policy with a unified optimization objective, learning how to actively gather information. By design, APPLE is not limited to a specific task and can, in principle, be applied to a wide range of active perception problems. We evaluate two variants of APPLE across different tasks, including tactile exploration problems from the Tactile MNIST benchmark. Experiments demonstrate the efficacy of APPLE, achieving high accuracies on both regression and classification tasks. These findings underscore the potential of APPLE as a versatile and general framework for advancing active perception in robotics.

Although diffusion models have achieved strong results in decision-making tasks, their slow inference speed remains a key limitation. While consistency models offer a potential solution, existing applications to decision-making either struggle with suboptimal demonstrations under behavior cloning or rely on complex concurrent training of multiple networks under the actor-critic framework. In this work, we propose a novel approach to consistency distillation for offline reinforcement learning that directly incorporates reward optimization into the distillation process. Our method achieves single-step sampling while generating higher-reward action trajectories through decoupled training and noise-free reward signals. Empirical evaluations on the Gym MuJoCo, FrankaKitchen, and long horizon planning benchmarks demonstrate that our approach can achieve a $9.7$% improvement over previous state-of-the-art while offering up to $142\times$ speedup over diffusion counterparts in inference time.

Supervised fine-tuning (SFT) of foundation models often leads to poor generalization, where prior capabilities deteriorate after tuning on specific tasks. Inspired by trust-region policy optimization (TRPO) and proximal policy optimization (PPO) in reinforcement learning (RL), we propose Proximal SFT (PSFT), a fine-tuning objective that incorporates the benefits of trust-region, effectively constraining policy drift during SFT while maintaining competitive tuning. By viewing SFT as a special case of policy gradient methods with constant positive advantages, we derive PSFT that stabilizes optimization and leads to generalization, while leaving room for further optimization in subsequent post-training stages. Experiments across mathematical, human-value, and multimodal domains show that PSFT matches standard SFT in-domain, outperforms it in out-of-domain generalization, remains stable under prolonged training without causing entropy collapse, and provides a stronger foundation for the subsequent optimization.

Reinforcement-learning agents often struggle when deployed from simulation to the real-world. A dominant strategy for reducing the sim-to-real gap is domain randomization (DR) which trains the policy across many simulators produced by sampling dynamics parameters, but standard DR ignores offline data already available from the real system. We study offline domain randomization (ODR), which first fits a distribution over simulator parameters to an offline dataset. While a growing body of empirical work reports substantial gains with algorithms such as DROPO, the theoretical foundations of ODR remain largely unexplored. In this work, we cast ODR as a maximum-likelihood estimation over a parametric simulator family and provide statistical guarantees: under mild regularity and identifiability conditions, the estimator is weakly consistent (it converges in probability to the true dynamics as data grows), and it becomes strongly consistent (i.e., it converges almost surely to the true dynamics) when an additional uniform Lipschitz continuity assumption holds. We examine the practicality of these assumptions and outline relaxations that justify ODR’s applicability across a broader range of settings. Taken together, our results place ODR on a principled footing and clarify when offline data can soundly guide the choice of a randomization distribution for downstream offline RL.

Autoformulation is an emerging field that uses large language models (LLMs) to translate natural-language descriptions of decision-making problems into formal mathematical formulations. Existing works have focused on autoformulating mathematical optimization problems for $\textit{one-shot}$ decision-making. However, many real-world decision-making problems are $\textit{sequential}$, best modeled as $\textit{Markov decision processes}$ (MDPs). MDPs introduce unique challenges for autoformulation, including a significantly larger formulation search space, and for computing and interpreting the optimal policy. In this work, we address these challenges in the context of queueing problems---central to domains such as healthcare and logistics---which often require substantial technical expertise to formulate correctly. We propose a novel operator-theoretic autoformulation framework using LLMs. Our approach captures the underlying decision structure of queueing problems through constructing the Bellman equation as a graph of $\textit{operators}$, where each operator is an $\textit{interpretable}$ transformation of the value function corresponding to certain $\textit{event}$ (e.g., arrival, departure, routing). Theoretically, we prove a universal three-level operator-graph topology covering a broad class of MDPs, significantly shrinking the formulation search space. Algorithmically, we propose customized Monte Carlo tree search to build operator graphs while incorporating self-evaluation, solver feedback, and intermediate syntax checking for early assessment, and present a provably low-complexity algorithm that automatically identifies structures of the optimal policy (e.g., threshold-based), accelerating downstream solving. Numerical results demonstrate the effectiveness of our approach in formulating queueing problems and identifying structural results.

Large Language Models (LLMs) have achieved remarkable success through imitation learning on vast text corpora, but this paradigm creates a training-generation gap and limits robust reasoning. Reinforcement learning (RL) offers a more data-efficient solution capable of bridging this gap, yet its application has been constrained by a critical data bottleneck: existing RL datasets are orders of magnitude smaller and less diverse than web-scale pre-training corpora. To address this, we introduce the \textbf{\texttt{Webscale-RL} pipeline}, a scalable data engine that systematically converts large-scale pre-training documents into millions of diverse, verifiable question-answer pairs for RL. Using this pipeline, we construct the \textbf{\texttt{Webscale-RL} dataset}, containing 1.2 million examples across more than 9 domains. Our experiments show that the model trained on this dataset significantly outperforms continual pretraining and strong data refinement baselines across a suite of benchmarks. Notably, RL training with our dataset proves substantially more efficient, achieving the performance of continual pre-training with up to 100$\times$ fewer tokens. Our work presents a viable path toward scaling RL to pre-training levels, enabling more capable and efficient language models.

Reinforcement Learning from Human Feedback (RLHF) has achieved considerable success in aligning large language models (LLMs) by modeling human preferences with a learnable reward model and employing a reinforcement learning algorithm to maximize the reward model's scores. However, these reward models are susceptible to exploitation through various superficial confounding factors, with length bias emerging as a particularly significant concern. Moreover, while the pronounced impact of length bias on preference modeling suggests that LLMs possess an inherent sensitivity to length perception, our preliminary investigations reveal that fine-tuned LLMs consistently struggle to adhere to explicit length instructions. To address these two limitations, we propose a novel framework wherein the reward model explicitly differentiates between human semantic preferences and response length requirements. Specifically, we introduce a $\textbf{R}$esponse-$\textbf{c}$onditioned $\textbf{B}$radley-$\textbf{T}$erry (Rc-BT) model that enhances the model's capability in length bias mitigating and length instruction following, through training on our augmented dataset. Furthermore, we propose the Rc-RM and Rc-DPO algorithm to leverage the Rc-BT model for reward modeling and direct policy optimization (DPO) of LLMs, simultaneously mitigating length bias and promoting adherence to length instructions. Extensive experiments across various models and datasets demonstrate the effectiveness and generalizability of our approach.

Well-trained multi-agent systems can fail when deployed in real-world environments due to model mismatches between the training and deployment environments, caused by environment uncertainties including noise or adversarial attacks. Distributionally Robust Markov Games (DRMGs) enhance system resilience by optimizing for worst-case performance over a defined set of environmental uncertainties. However, current methods are limited by their dependence on simulators or large offline datasets, which are often unavailable. This paper pioneers the study of online learning in DRMGs, where agents learn directly from environmental interactions without prior data. We introduce the Multiplayer Optimistic Robust Nash Value Iteration (MORNAVI) algorithm and provide the first provable guarantees for this setting. Our theoretical analysis demonstrates that the algorithm achieves low regret and efficiently finds the optimal robust policy for uncertainty sets measured by Total Variation divergence and Kullback-Leibler divergence. These results establish a new, practical path toward developing truly robust multi-agent systems.

Temporal search aims to identify a minimal set of relevant frames from tens of thousands based on a given query, serving as a foundation for accurate long-form video understanding. Many existing works attempt to progressively narrow the search space. However, these approaches typically rely on a hand-crafted search process, lacking end-to-end optimization for learning optimal search strategies. In this paper, we propose **TimeSearch-R**, which reformulates temporal search as interleaved text–video thinking, seamlessly integrating searching video clips into the reasoning process through reinforcement learning (RL). However, applying RL training methods, such as Group Relative Policy Optimization (GRPO), to video reasoning can result in unsupervised intermediate search decisions. This leads to insufficient exploration of the video content and inconsistent logical reasoning. To address these issues, we introduce GRPO with Completeness Self-Verification (GRPO-CSV), which gathers searched video frames from the interleaved reasoning process and utilizes the same policy model to verify the adequacy of searched frames, thereby improving the completeness of video reasoning. Additionally, we construct datasets specifically designed for the SFT cold-start and RL training of GRPO-CSV, filtering out samples with weak temporal dependencies to enhance task difficulty and improve temporal search capabilities. Extensive experiments demonstrate that TimeSearch-R achieves substantial improvements on temporal search benchmarks such as Haystack-LVBench and Haystack-Ego4D, long-form video understanding benchmarks like VideoMME, MLVU, and LongVideoBench, as well as video reasoning benchmarks such as Video-Holmes, consistently and significantly outperforming other existing temporal search approaches and text-only reasoning models. Our code is available at *https://github.com/Time-Search/TimeSearch-R*.

Incorporating demonstration data into reinforcement learning (RL) can greatly accelerate learning, but existing approaches often assume demonstrations are optimal and fully aligned with the target task. In practice, demonstrations are frequently sparse, suboptimal, or misaligned, which can degrade performance when these demonstrations are integrated into RL. We propose Adaptive Policy Composition (APC), a hierarchical model that adaptively composes multiple data-driven Normalizing Flow (NF) priors. Instead of enforcing strict adherence to the priors, APC estimates each prior's applicability to the target task while leveraging them for exploration. Moreover, APC either refines useful priors, or sidesteps misaligned ones when necessary to optimize downstream reward. Across diverse benchmarks, APC accelerates learning when demonstrations are aligned, remains robust under severe misalignment, and leverages suboptimal demonstrations to bootstrap exploration while avoiding performance ceilings caused by overly strict adherence to suboptimal demonstrations.

Scaling reinforcement learning to tens of thousands of parallel environments requires overcoming the limited exploration capacity of a single policy. Ensemble-based policy gradient methods, which employ multiple policies to collect diverse samples, have recently been proposed to promote exploration. However, merely broadening the exploration space does not always enhance learning capability, since excessive exploration can reduce exploration quality or compromise training stability. In this work, we theoretically analyze the impact of inter-policy diversity on learning efficiency in policy ensembles, and propose Coupled Policy Optimization (CPO), which regulates diversity through KL constraints between policies. The proposed method enables effective exploration and outperforms strong baselines such as SAPG, PBT, and PPO across multiple dexterous manipulation tasks in both sample efficiency and final performance. Furthermore, analysis of policy diversity and effective sample size during training reveals that follower policies naturally distribute around the leader, demonstrating the emergence of structured and efficient exploratory behavior. Our results indicate that diverse exploration under appropriate regulation is key to achieving stable and sample-efficient learning in ensemble policy gradient methods.