ICML 2026 论文列表

Unsupervised Reinforcement Learning from Internal Feedback (RLIF) has emerged as a promising paradigm for eliciting the latent capabilities of Large Language Models (LLMs) without external supervision. However, current methods rely on heuristic intrinsic rewards, which often lack a well-defined theoretical optimization target and are prone to degenerative biases. In this work, we introduce PowerFlow, a principled framework that reformulates unsupervised fine-tuning as a distribution matching problem. By casting GFlowNet as an amortized variational sampler for unnormalized densities, we propose a length-aware Trajectory-Balance objective that explicitly neutralizes the structural length biases inherent in autoregressive generation. By targeting $\alpha$-power distributions, PowerFlow enables the directional elicitation of the dual nature of LLMs: sharpening the distribution ($\alpha > 1$) to intensify logical reasoning, or flattening it ($\alpha < 1$) to unlock expressive creativity. Extensive experiments demonstrate that PowerFlow consistently outperforms existing RLIF methods, matching or even exceeding supervised GRPO. Furthermore, by mitigating over-sharpening in aligned models, our approach achieves simultaneous gains in diversity and quality, shifting the Pareto frontier in creative tasks.

Device-cloud collaboration holds promise for deploying large language models (LLMs), leveraging lightweight on-device models for efficiency while relying on powerful cloud models for superior reasoning. A central challenge in this setting is determining, for each incoming query, whether it should be processed locally or offloaded to the cloud. Existing approaches typically rely on external routers, which often struggle to determine difficulty from the prompt itself, especially for tasks involving complex reasoning. Motivated by this limitation, we propose enabling on-device LLMs to decide internally whether to invoke cloud assistance at inference time, with this capability instilled through reinforcement learning based post-training. Casting on-device LLM post-training as a reward maximization problem, we design hierarchical rewards to encourage local problem solving and judicious cloud offloading. To solve the resulting problem, we develop an algorithm featuring a group-level policy gradient that stabilizes optimization, together with adaptive prompt filtering that provides complementary learning signals to mitigate policy collapse (i.e., exclusive local execution or exclusive cloud offloading). Extensive experiments on on-device-scale LLaMA and Qwen models across multiple reasoning benchmarks show that our method consistently outperforms baselines and significantly narrows the gap to full cloud LLMs.

Universal morphology control aims to learn a universal policy that generalizes across heterogeneous robot morphologies, with Transformer-based controllers emerging as a dominant choice. However, such architectures incur substantial computational costs, resulting in high deployment overhead, and existing methods exhibit limited cross-task generalization, necessitating training from scratch for each new task. To this end, we propose DivMorph, a modular training paradigm that leverages knowledge diversion to learn *decomposable controllers*. DivMorph factorizes randomly initialized Transformer weights into *basic knowledge units* via SVD and employs dynamic soft gating, conditioned on task and morphology embeddings, to adaptively modulate these units into universal *learngenes* and morphology- and task-specific *tailors* during training, thereby achieving knowledge disentanglement. By selectively activating relevant components, DivMorph adaptively recomposes the controller, enabling efficient policy deployment and effective policy transfer to novel tasks. Extensive experiments demonstrate that DivMorph achieves state-of-the-art performance, improving sample efficiency for cross-task transfer by 3.3$\times$ and reducing model size for single-agent deployment by 16.7$\times$.

Despite scale driving substantial recent advancements in machine learning, reinforcement learning (RL) methods still primarily use small value functions. Naively scaling value functions -- including with a transformer architecture, which is known to be highly scalable -- often results in learning instability and worse performance. In this work, we ask what prevents transformers from scaling effectively for value functions? Through empirical analysis, we identify the critical failure mode in this scaling: attention scores collapse as capacity increases. Our key insight is that we can effectively prevent this collapse and stabilize training by controlling the entropy of the attention scores, thereby enabling the use of larger models. To this end, we propose Transformer Q-Learning (TQL), a method that unlocks the scaling potential of transformers in learning value functions in RL. Our approach yields up to a 43\% improvement in performance when scaling from the smallest to the largest network sizes, while prior methods suffer from performance degradation.

Large language models (LLMs) have recently advanced in reasoning when optimized with reinforcement learning (RL) under verifiable rewards. Existing methods primarily rely on outcome-based supervision to strengthen internal LLM reasoning, often leading to inefficient exploration and sparse rewards. To mitigate this issue, we propose Expert-Assisted Policy Optimization (EAPO), a novel RL framework that enhances exploration by incorporating multi-turn interactions with external experts during training. Unlike prior methods, where policies reason in isolation, EAPO incentivizes the policy to adaptively determine when and how to consult experts, yielding richer reward signals and more reliable reasoning trajectories. External assistance ultimately internalizes expert knowledge into the policy model, amplifying the model’s inherent reasoning capabilities. During evaluation, the policy model has been well-optimized to solve questions independently, producing improved reasoning paths and more accurate solutions. On AIME 2024/2025 and AIMO 2025, EAPO consistently outperforms expert-assisted, expert-distilled, and RL baselines, averaging a 5-point gain over self-exploration RL, and also generalizes to non-math benchmarks, including HumanEval, HLE, GPQA, MMLU, EvalPlus, HotpotQA, and SimpleQA.

High-quality data is a cornerstone of large language model (LLM) pretraining, yet its growth has not kept pace with the needs of frontier models. In this paper, we introduce RePro, a novel web recycling method that trains a relatively small LM with reinforcement learning to generate effective and faithful rephrasings of pretraining data. Specifically, we design one *quality* reward and three *faithfulness* rewards, optimizing the LM rephraser to convert organic data into high-quality rephrasings while maintaining its core semantics and structure. In our experiment, we train a rephraser as small as 1B parameters to recycle 72B tokens sampled from DCLM-RefinedWeb. Pretraining results on 400M, 1.4B, and 2.8B models demonstrate that RePro delivers 3.7\%-14.5\% relative accuracy gains over organic-only baseline on 22 downstream tasks, doubling the performance gains achieved by the state-of-the-art web recycling method that prompts a 70B rephraser. Experiments with different amounts of recycled data highlight that RePro improves organic data efficiency by 2-3$\times$. Individual and distributional analyses validate that RePro preserves more critical information and faithfully reflects the characteristics of organic data compared to prompting-based methods. Together, these results show that RePro provides an efficient and controllable path to effectively recycle organic data for pretraining. Our code is available at https://github.com/cxcscmu/RePro.

Proactive Recommender Systems (PRSs) aim to guide user preference shift toward target items by generating paths of intermediate recommendations. Reinforcement learning (RL) provides a principled framework for optimizing such sequential decision tasks, as path rewards can naturally capture both short-term acceptance and long-term guidance effectiveness. However, naively applying policy gradients to PRS results in deficient gradient estimation. We identify two deficiencies: (1) path-level rewards decompose into step-level rewards with positive mean, creating a *length-dependent bias* that causes gradients to favor path extension over meaningful exploration; (2) weighting each step by the entire path-level reward ignores the decomposition structure, leading to high gradient variance. To rectify these two deficiencies, we propose an effective RL framework **ProRL** with two novel mechanisms for proactive recommendation. First, Stepwise Reward Centering subtracts expected rewards to neutralize length-dependent bias, ensuring that path extension yields zero expected gradient signal. Second, Position-Specific Advantage Estimation leverages the reward decomposition structure to compute step-dependent baselines, reducing gradient variance. Together, these mechanisms yield policy gradients that precisely target path quality. Our experiments on three real-world datasets demonstrate that ProRL significantly outperforms state-of-the-art PRSs. Our code is available at https://github.com/hongruhou89/ProRL.

In-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks without any parameter updates, instead relying on an expanding context of interaction history. While ICRL has shown impressive generalization, safety during this adaptation process remains unexplored, limiting its applicability in real-world deployments where test-time behavior is expected to be safe. In this work, we propose SCARED: Safe Contextual Adaptive Reinforcement via Exact-penalty Dual, the first method that promotes safe adaptation of ICRL under the constrained Markov decision process framework. During the parameter-update-free adaptation process, our agent not only maximizes the reward but also keeps the accumulated cost within a user-specified safety budget. We also demonstrate that the agent actively reacts to the safety budget; with a higher safety budget, the agent behaves more aggressively, and with a lower safety budget the agent behaves more conservatively. Across challenging benchmarks, SCARED consistently enables safe and robust in-context adaptation, outperforming existing ICRL and safe meta-RL baselines.

Evolutionary multi-tasking accelerates black-box optimization via knowledge transfer but falters in scenarios involving many low-similarity tasks. We identify this scalability barrier as the *Multi-Task Curse*, driven by evaluation budget dispersion and negative transfer. To overcome this, we propose MES-RET (*M*any-task *E*volution *S*trategy with *R*eward-weighted *E*valuation and *T*ransfer), which combats budget dispersion via a reward-weighted evaluation scheme that guarantees superior expected improvement, while simultaneously mitigating negative transfer through a robust reward-weighted aggregation of mean and covariance statistics, ensuring a safe fallback to independent evolution. Furthermore, to handle neural dimensional mismatches in many-task policy search, we introduce a semantic parameter alignment strategy that bridges heterogeneous state-action spaces. Extensive experiments on synthetic benchmarks, real-world engineering problems, and reinforcement learning tasks demonstrate that MES-RET consistently outperforms state-of-the-art methods, notably enabling skill transfer across morphologically distinct policies.

Preference-based reinforcement learning (RL) is a key paradigm for aligning policies with human judgments, yet its theoretical behavior in distributed settings where preference data are fragmented across heterogeneous users remains poorly understood. Direct Preference Optimization (DPO) avoids explicit reward modeling but lacks convergence guarantees under federated and decentralized training, where communication constraints and non-IID preferences fundamentally alter optimization dynamics. We provide the first convergence and time-complexity analysis of DPO in distributed environments. Modeling personalized offline RL with user-specific preference distributions, we characterize the induced global optimization landscape. For federated DPO, we derive convergence rates that quantify the impact of client drift, communication frequency, and preference heterogeneity; for decentralized DPO, we establish convergence over general communication graphs and show how spectral connectivity governs optimization speed and consensus. Empirically, we corroborate our theoretical insights on standard alignment benchmarks, demonstrating that our proposed methods not only enjoy strong theoretical guarantees but also deliver robust and scalable performance in practice. The code base is available here.

Recent video foundation models demonstrate impressive visual synthesis but frequently suffer from geometric inconsistencies. While existing methods attempt to inject 3D priors via architectural modifications, they often incur high computational costs and limit scalability. We propose World-R1, a framework that aligns video generation with 3D constraints through reinforcement learning. To facilitate this alignment, we introduce a specialized pure text dataset tailored for world simulation. Utilizing Flow-GRPO, we optimize the model using feedback from pre-trained 3D foundation models and vision-language models to enforce structural coherence without altering the underlying architecture. We further employ a periodic decoupled training strategy to balance rigid geometric consistency with dynamic scene fluidity. Extensive evaluations reveal that our approach significantly enhances 3D consistency while preserving the original visual quality of the foundation model, effectively bridging the gap between video generation and scalable world simulation.

While diffusion language models (DLMs) have achieved competitive performance in text generation, improving their reasoning ability with reinforcement learning remains an active research area. Here, we introduce d2, a reasoning framework tailored for masked DLMs. Central to our framework is a new policy gradient algorithm that relies on accurate estimates of the sampling trajectory likelihoods. Because computing these likelihoods naively is computationally expensive for masked DLMs, we develop a family of estimators tailored to distinct model classes. For DLMs that support a sampling algorithm called any-order decoding, we propose d2-AnyOrder, which achieves exact trajectory likelihood with a single model pass. Through an empirical study of widely used DLMs, we show that any-order decoding is not universally supported in practice. For standard masked diffusion models, we propose d2-StepMerge, which approximates the trajectory likelihood, trading off compute for approximation accuracy in an analytically tractable manner. Empirically, d2 significantly outperforms widely-used RL baselines when applied to popular DLMs, and sets a new state-of-the-art performance for DLMs on logical reasoning tasks (Countdown and Sudoku) and math reasoning benchmarks (GSM8K and MATH500). We provide the code along with a blog post on the project page: https://guanghanwang.com/d2

The reasoning patterns of large language models (LLMs) remain opaque, and Reinforcement learning (RL) typically assigns uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work treats attention as a natural substrate for interpreting LLM reasoning and a window for aligning optimization with its internal dynamics. We first distinguish attention heads between locally and globally focused information processing and reveal that locally focused heads produce a sawtooth pattern near the diagonal indicating phrasal chunks, while globally focused heads expose tokens that exert broad downstream influence over future tokens. We quantify these with two metrics measuring the extent of backward attention within a clipped window and the average attention a token receives from subsequent tokens, respectively. Taken together, these signals indicate a recurring preplan-and-anchor regularity, where the model first performs a long-range contextual reference to generate an introductory token, which is immediately followed by or coincides with a semantic anchor token that organizes subsequent reasoning. Leveraging these insights, we introduce three novel RL strategies that dynamically perform targeted credit assignment to critical nodes (preplan tokens, anchor tokens, and their temporal coupling) and show consistent performance gains across various reasoning tasks.

Multimodal LLMs (MLLMs) are increasingly deployed across diverse applications, but they pose significant safety concerns due to cross-modal interactions. To improve model safety awareness, existing methods rely on explicit-risk preference datasets and reinforcement learning guided by safety rewards. While effective in improving models' safety awareness, these methods still face data scarcity and reward hacking in implicit-risk scenarios, leading to insufficient risk perception and harmful responses. To address these challenges, we propose Meerkat-VL, a framework that enables models to perceive and verify implicit risks while generating safe responses. First, we introduce Meerkat-Safe, the first training dataset with detailed labels for implicit risks. Second, we develop Normative Perceptual Self-Verification, which enables models to verify both perceptual reasoning and responses. This process provides denser and more reliable rewards for perception accuracy and answer safety, thereby mitigating reward hacking. Finally, we propose Dual-Objective Perceptual Consistency Alignment, encouraging models to generate safe responses by penalizing answers that follow safe templates without accurate risk perception. Extensive experiments show that Meerkat-VL consistently outperforms baselines on multimodal safety benchmarks, improving safety and helpfulness by 16% and 13%, and achieving a 32% safety gain on implicit-risk tasks. Our codes are available at https://github.com/Tunanzzz/Meerkat-VL.

The growing capability of video generation poses escalating security risks, making reliable detection increasingly essential. In this paper, we introduce **VideoVeritas**, a framework that integrates fine-grained perception and fact-based reasoning. We observe that while current multi-modal large language models (MLLMs) exhibit strong reasoning capacity, their granular perception ability remains limited. To mitigate this, we introduce *Joint Preference Alignment* and *Perception Pretext Reinforcement Learning (PPRL)*. Specifically, rather than directly optimizing for detection task, we adopt general spatiotemporal grounding and self-supervised object counting in the RL stage, enhancing detection performance with simple *perception pretext tasks*. To facilitate robust evaluation, we further introduce **MintVid**, a light yet high-quality dataset containing 3K videos from 9 state-of-the-art generators, along with a real-world collected subset that has factual errors in content. Experimental results demonstrate that existing methods tend to bias towards either *superficial* reasoning or *mechanical* analysis, while **VideoVeritas** achieves more balanced performance across diverse benchmarks.

Reinforcement learning (RL) excels on tasks with verifiable rewards, but in open-ended tasks, the reliability of reward models remains a key challenge. Existing solutions either depend on costly proprietary LLM-as-a-Judge systems or opaque scalar reward models that lack interpretability. Recent works on generative reward models offer a promising alternative, but they remain constrained by static evaluation criteria, fragmented evaluation paradigms, and limited multilingual support. To address these challenges, we introduce MixReward, a large-scale multilingual dataset spanning six domains and 103 languages, containing both pairwise and listwise data, and propose UniRRM, a unified reasoning reward model supporting multiple languages and evaluation paradigms. UniRRM uses a staged reasoning chain to dynamically generate task-generic and instruction-specific criteria, enabling fine-grained, input-adaptive judgments while maintaining consistency across languages. Experiments demonstrate that UniRRM-8B and UniRRM-14B achieve performance close to the state-of-the-art for models of comparable size across multiple benchmarks, and are effective for unseen evaluation paradigms. In addition, ablation studies validate the reliability and effectiveness of UniRRM.

Ensuring safe behavior in reinforcement learning (RL) is challenging when safety constraints are implicit and cannot be densely measured. In many settings, supervision is limited to coarse approvals or rejections of whole trajectories (e.g., whether a rollout remained within an unknown safety threshold). We propose **TraCeS** (Trajectory-based Constraint Estimation for Safety), a method for learning **per-timestep violation credit** from such sparse trajectory-level labels. **TraCeS** trains a sequential violation estimator whose per-step credits factorize the predicted probability that a trajectory has **not yet violated** the constraint, and integrates this learned signal into constrained policy optimization. The method requires neither a known cost function nor a known threshold, and remains compatible with standard continuous-control algorithms. We provide a theoretical analysis of the approximation gap introduced by the learning objective, and demonstrate empirically that **TraCeS** improves constraint satisfaction and feedback efficiency over baselines across multiple continuous-control benchmarks, including long-horizon tasks and settings with noisy or inconsistent labels.

Backdoor attacks can introduce deceptive behaviors into large language models, causing them to execute prohibited actions only when specific secret triggers appear in the input. Existing safety training methods largely fail to address this vulnerability, due to the inherent difficulty of uncovering hidden triggers embedded within the model. Motivated by recent findings on LLMs’ situational awareness, we propose a novel post-training framework that cultivates backdoor self-awareness, enabling a poisoned LLM to precisely articulate its own implanted triggers. At its core, our approach introduces an inversion-inspired reinforcement learning framework that encourages models to introspectively reason about their behaviors and gradually reverse-engineer the triggers responsible for misaligned outputs. Building upon precise trigger articulation, we further present two complementary defense strategies for mitigating and detecting backdoor threats. Experiments on five backdoor attacks, compared against six baseline methods, demonstrate that our approach has strong potential to improve the robustness of LLMs against backdoor risks.

The rapid evolution of Large Language Models (LLMs) has empowered even non-programmers to create visually appealing frontend mini-games with a single instruction. However, open-source models significantly lag behind proprietary counterparts in this domain. The core bottleneck is the lack of an evaluation mechanism that balances reliability with scalability, as existing methods either fail to verify dynamic interactivity or incur prohibitive computational costs. To bridge this gap, we introduce ALIVE (Aligning LLMs via Interactive Visual Execution), a high-throughput framework that leverages one-shot planning and DOM-based analysis to automatically evaluate generated games at scale. Extensive experiments demonstrate that ALIVE significantly outperforms static judge baselines in identifying functional flaws while remaining orders of magnitude more efficient than GUI agents. Functioning as a scalable `pre-flight' evaluation layer, it curates high-quality data for Supervised Fine-Tuning (SFT) and provides a consistent reward signal for Reinforcement Learning (RL). We leverage this pipeline to train ALIVE-Coder, a model achieving superior performance in interactive frontend generation. To the best of our knowledge, our work offers the first scalable path to evaluate and optimize interactive code, substantially advancing open-source capabilities.