ICLR 2026 论文列表

Vision–Language–Action (VLA) models in autonomous driving systems have recently demonstrated transformative potential by integrating multimodal perception with decision-making capabilities. However, the interpretability and coherence of the decision process and the plausibility of action sequences remain largely underexplored. To address these issues, we propose AutoDrive-R², a novel VLA framework that enhances both reasoning and self-reflection capabilities of autonomous driving systems through chain-of-thought (CoT) processing and reinforcement learning (RL). Specifically, we first propose an innovative CoT dataset named nuScenesR²-6K for supervised fine-tuning, which effectively builds cognitive bridges between input information and output trajectories through a four-step logical chain with self-reflection for validation. Moreover, to maximize both reasoning and self-reflection during the RL stage, we further employ the Group Relative Policy Optimization (GRPO) algorithm within a physics-grounded reward framework that incorporates spatial alignment, vehicle dynamic, and temporal smoothness criteria to ensure reliable and realistic trajectory planning. Extensive evaluation results across both nuScenes and Waymo datasets demonstrates the state-of-the-art performance and robust generalization capacity of our proposed method.

We prove the stability and global convergence of a coupled actor-critic gradient flow for infinite-horizon and entropy-regularised Markov decision processes (MDPs) in continuous state and action space with linear function approximation under Q-function realisability. We consider a version of the actor critic gradient flow where the critic is updated using temporal difference (TD) learning while the policy is updated using a policy mirror descent method on a separate timescale. For general action spaces, the relative entropy regularizer is unbounded and thus it is not clear a priori that the actor-critc flow does not suffer from finite-time blow-up. Therefore we first demonstrate stability which in turn enables us obtain a convergence rate of the actor critic flow to the optimal regularised value function. The arguments presented show that timescale separation is crucial for stability and convergence in this setting.

In recent years, pre-trained large language models have achieved remarkable success across diverse tasks. Besides the pivotal role of self-supervised pre-training, their effectiveness in downstream applications also depends critically on the post-training process, which adapts models to task-specific data and objectives. However, this process inevitably introduces model shifts that can influence performance in different domains, and how such shifts transfer remains poorly understood. To open up the black box, we propose the SAE-based Transferability Score (STS), a new metric that leverages sparse autoencoders (SAEs) to forecast post-training transferability. Taking supervised fine-tuning as an example, STS identifies shifted dimensions in SAE representations and calculates their correlations with downstream domains, enabling reliable estimation of transferability \textit{before} fine-tuning. Extensive experiments across multiple models and domains show that STS accurately predicts the transferability of supervised fine-tuning, achieving Pearson correlation coefficients above 0.75 with actual performance changes. Beyond this, we take an initial step toward extending STS to reinforcement learning. We believe that STS can serve as an interpretable tool for guiding post-training strategies in LLMs.

The extension of diffusion models to language tasks has shown promising results, but their post-training methods remain largely unexplored. We highlight the importance of aligning a diffusion language model’s preference-inference trajectory with its post-training objective. To this end, we propose TraceRL, a trajectory-aware reinforcement learning framework for DLMs that incorporates information from inference trajectories into post-training and is applicable to both full-attention and block-attention diffusion models. We also introduce a diffusion-based value model that enhances training stability and naturally accommodates process rewards. We demonstrate TraceRL’s superiority in enhancing a model’s reasoning ability on complex math and coding tasks, as well as its applicability in scaling block diffusion models to larger block sizes. Employing TraceRL, we derive a series of state-of-the-art diffusion language models, namely TraDo. Although smaller than Qwen2.5-7B-Instruct, TraDo-4B-Instruct consistently outperforms it on complex math reasoning tasks. TraDo-8B-Instruct achieves 4.5% higher accuracy on MATH500 than Qwen2.5-7B-Instruct and 6.6% higher accuracy on LiveCodeBench-V2 than Llama3.1-8B-Instruct. Through curriculum learning, we also develop the first 8B-scale long-CoT diffusion language model.

We aim to improve the reasoning capabilities of language models via reinforcement learning with verifiable rewards (RLVR). Recent RLVR post-trained models like DeepSeek-R1 have demonstrated reasoning abilities on mathematical and coding tasks. However, prior studies suggest that using RLVR alone to improve reasoning on inherently difficult tasks is less effective due to sparse rewards. Here, we draw inspiration from curriculum learning and propose to schedule tasks from easy to hard (E2H), allowing LLMs to build reasoning skills gradually. Our method is termed E2H Reasoner. Empirically, we observe that, although easy tasks are important initially, fading them out through appropriate scheduling is essential in preventing overfitting. Theoretically, we establish convergence guarantees for E2H Reasoner within an approximate policy iteration framework. We derive finite-sample complexity bounds and show that when tasks are appropriately decomposed and conditioned, learning through curriculum stages requires fewer total samples than direct learning. Experiments across diverse datasets and models demonstrate that E2H Reasoner substantially enhances LLM reasoning.

Recently, Large Language Models (LLMs) have been applied to scientific equation discovery, leveraging their embedded scientific knowledge for hypothesis generation. However, current methods typically confine LLMs to the role of an equation proposer within search algorithms like genetic programming. In this paper, we present SR-Scientist, a framework that elevates the LLM from a simple equation proposer to an autonomous AI scientist that writes code to analyze data, implements the equation as code, submits it for evaluation, and optimizes the equation based on experimental feedback. Specifically, we wrap the code interpreter into a set of tools for data analysis and equation evaluation. The agent is instructed to optimize the equation by utilizing these tools over a long horizon with minimal human-defined pipelines. Empirical results show that SR-Scientist outperforms baseline methods by an absolute margin of 6\% to 35\% on datasets covering four science disciplines. Additionally, we demonstrate our method's robustness to noise, the generalization of the discovered equations to out-of-domain data, and their symbolic accuracy. Furthermore, we develop an end-to-end reinforcement learning framework to enhance the agent's capabilities.

At the boundary between the known and the unknown, an agent inevitably confronts the dilemma of whether to explore or to exploit. Epistemic uncertainty reflects such boundaries, representing systematic uncertainty due to limited knowledge. In this paper, we propose a Bayesian reinforcement learning (RL) algorithm, $\texttt{EUBRL}$, which leverages epistemic guidance to achieve principled exploration. This guidance adaptively reduces per-step regret arising from estimation errors. We establish nearly minimax-optimal regret and sample complexity guarantees for a specific class of priors in infinite-horizon discounted MDPs. Empirically, we evaluate $\texttt{EUBRL}$ on tasks characterized by sparse rewards, long horizons, and stochasticity. Results demonstrate that $\texttt{EUBRL}$ achieves superior sample efficiency, scalability, and consistency.

By employing large language models (LLMs) to retrieve documents and generate natural language responses, Generative Engines, such as Google AI overview and ChatGPT, provide significantly enhanced user experiences and have rapidly become the new form of search. Their rapid adoption also drives the needs of Generative Engine Optimization (GEO), as content providers are eager to gain more traction from them. In this paper, we introduce AutoGEO, a framework to automatically learn generative engine preferences when using retrieved contents for response generation, and rewrite web contents for more such traction. AutoGEO first prompts frontier LLMs to explain generative engine preferences and extract meaningful preference rules from these explanations. Then it uses preference rules as context engineering for AutoGEO$\_\text{API}$, a prompt-based GEO system, and as rule-based rewards to train AutoGEO$\_\text{Mini}$, a cost-effective GEO model. Experiments on the standard GEO-Bench and two newly constructed benchmarks using real user queries demonstrate the effectiveness of AutoGEO in enhancing content traction while preserving search utility. Analyses confirmed the learned rules' robustness and abilities to capture unique preferences in variant domains, and AutoGEO systems' ability to embed them in content optimization. The learned preference rules, our models, and codes will be open-sourced.

The "Reason-Then-Respond" paradigm, enhanced by Reinforcement Learning, has shown great promise in advancing Multimodal Large Language Models. However, its application to the video domain has led to specialized models that excel at either question answering (QA) or captioning tasks, but struggle to master both. Naively combining reward signals from these tasks results in mutual performance degradation, which we attribute to a conflict between their opposing task natures. To address this challenge, we propose a novel training framework built upon two intermediate proxy tasks: DarkEventInfer, which presents videos with masked event segments, requiring models to infer the obscured content based on contextual video cues; and MixVidQA, which presents interleaved video sequences composed of two distinct clips, challenging models to isolate and reason about one while disregarding the other. These proxy tasks compel the model to simultaneously develop both holistic, divergent understanding and precise, convergent reasoning capabilities. Embodying this framework, we present VidBridge-R1, the first versatile video reasoning model that effectively bridges the paradigm conflict. Extensive experiments show that VidBridge-R1 achieves significant performance gains on both QA and captioning within one model, demonstrating the efficacy of our approach in fostering more generalizable and powerful video understanding models. All code, models, and data will be made publicly available.

Large Reasoning Models (LRMs) have demonstrated impressive capabilities but suffer from cognitive inefficiencies like ''overthinking'' simple problems and ''underthinking'' complex ones. While existing methods that use supervised fine-tuning (SFT) or reinforcement learning (RL) with token-length rewards can improve efficiency, they often do so at the cost of accuracy. This paper introduces DeepCompress, a novel framework that simultaneously enhances both the accuracy and efficiency of LRMs. We challenge the prevailing approach of consistently favoring shorter reasoning paths, showing that longer responses can contain a broader range of correct solutions for difficult problems. DeepCompress employs an adaptive length reward mechanism that dynamically classifies problems as "Simple" or "Hard" in real-time based on the model's evolving capability. It encourages shorter, more efficient reasoning for "Simple" problems while promoting longer, more exploratory thought chains for "Hard" problems. This dual-reward strategy enables the model to autonomously adjust its Chain-of-Thought (CoT) length, compressing reasoning for well-mastered problems and extending it for those it finds challenging. Experimental results on challenging mathematical benchmarks show that DeepCompress consistently outperforms baseline methods, achieving superior accuracy while significantly improving token efficiency.

Generalizing policies across environments with altered dynamics remains a key challenge in reinforcement learning, particularly in offline settings where direct interaction or fine-tuning is impractical. We introduce Masked Skill Token Training (MSTT), a fully offline hierarchical RL framework that enables policy transfer using observation-only demonstrations. MSTT constructs a discrete skill space via unsupervised trajectory tokenization and trains a skill-conditioned value function using masked Bellman updates, which simulate dynamics shifts by selectively disabling skills. A diffusion-based trajectory generator, paired with feasibility-based filtering, enables the agent to execute valid, temporally extended actions without requiring action labels or access to the target environment. Our results in both discrete and continuous domains demonstrate the potential of mask-guided planning for robust generalization under dynamics shifts. To our knowledge, MSTT is the first work to explore masking as a mechanism for simulating and generalizing across off-dynamics environments. It marks a promising step toward scalable, structure-aware transfer and opens avenues to explore multi-goal conditioning, and extensions to more complex, real-world scenarios.

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based--train a reward model on preference pairs and optimize with reinforcement learning (RL)--or reward-free--directly fine-tune on ranked outputs. Recent research show that well-tuned reward-based pipelines remain the most robust, and single-response demonstrations can outperform pairwise preference data. However, there still exist two key challenges: (1) imbalanced safety dataset that overrepresent common hazards while neglecting long-tail threats; and (2) static reward models that ignore task difficulty, limiting optimization efficiency and attainable gains. To address these limitations, we propose DR-IRL, which Dynamically adjusts Rewards through Inverse Reinforcement Learning. We first train category‑specific reward models using a balanced safety dataset of seven harmful categories as demonstration via IRL. Then we enhance Group Relative Policy Optimization (GRPO) by introducing dynamic reward scaling--adjusting rewards by task difficulty--data-level hardness by text encoder cosine similarity, model-level responsiveness by reward gaps. Extensive experiments across various benchmarks and LLMs demonstrate that DR-IRL outperforms all baseline methods in safety alignment while maintaining usefulness.

Parallel sampling promises substantial gains in test-time scaling, but its effectiveness is sharply limited by diversity collapse, where models concentrate on a few modes and repeated samples reproduce the same mistakes. We propose the mode-conditioning (ModC) framework, which explicitly allocates test-time compute across reasoning modes using either specialist models or mode-specific prefixes. ModC consistently improves scaling across controlled graph-search tasks and large-scale reasoning benchmarks, spanning model families and sizes from 0.5B to 7B. On OpenThoughts, fine-tuning Qwen2.5-7B with ModC achieves an 8× efficiency gain over standard training while also improving the maximum attainable Pass@k. We further show that gradient clustering enables ModC without explicit mode labels, yielding up to 10% gains on datasets such as NuminaMath. Finally, we show that ModC improves reinforcement learning (RL) and can further boost diversity-inducing RL methods. These results demonstrate that standard training underutilizes the diversity in data, and that ModC provides a simple, effective remedy for unlocking the full benefits of diversity in test-time scaling.

Recent studies have explored leveraging the world knowledge and cognitive capabilities of Vision-Language Models (VLMs) to address the long-tail problem in end-to-end autonomous driving. However, existing methods typically formulate trajectory planning as a language modeling task, where physical actions are output in the language space, potentially leading to issues such as format-violating outputs, infeasible actions, and slow inference speeds. In this paper, we propose ReCogDrive, a novel **Re**inforced **Cog**nitive framework for end-to-end autonomous **Driv**ing, unifying driving understanding and planning by integrating an autoregressive model with a diffusion planner. First, to instill human driving cognition into the VLM, we introduce a hierarchical data pipeline that mimics the sequential cognitive process of human drivers through three stages: generation, refinement, and quality control. Building on this cognitive foundation, we then address the language-action mismatch by injecting the VLM's learned driving priors into a diffusion planner to efficiently generate continuous and stable trajectories. Furthermore, to enhance driving safety and reduce collisions, we introduce a Diffusion Group Relative Policy Optimization (DiffGRPO) stage, reinforcing the planner for enhanced safety and comfort. Extensive experiments on the NAVSIM and Bench2Drive benchmarks demonstrate that ReCogDrive achieves state-of-the-art performance. Additionally, qualitative results across diverse driving scenarios and DriveBench highlight the model's scene comprehension. All code, model weights, and datasets will be made publicly available to facilitate subsequent research.

Large reasoning models such as OpenAI o1 and DeepSeek-R1 have demonstrated remarkable performance in complex reasoning tasks. A critical component of their training is the incorporation of reference-based reward systems within reinforcement learning (RL), where model outputs are evaluated against ground truth references. However, existing reward benchmarks focus on preference comparisons between responses rather than evaluating verification against ground truth references, leaving a critical gap in our ability to evaluate verification systems used in reasoning model training. In this paper, we introduce VerifyBench and its challenging variant VerifyBench-Hard, two benchmarks specifically designed to assess reference-based reward systems. These benchmarks are constructed through meticulous data collection and curation, followed by careful human annotation to ensure high quality. Our comprehensive evaluation reveals that while larger model-based verifiers show promise on standard cases, all current systems demonstrate substantial room for improvement on challenging instances. Through systematic analysis of performance patterns across reasoning tasks and error categories, we provide insights for advancing reference-based reward systems. These benchmarks establish a standardized framework for improving verification accuracy, ultimately enhancing reasoning capabilities in models trained via RL.

A central challenge in image-based Model-Based Reinforcement Learning (MBRL) is to learn representations that distill essential information from irrelevant visual details. While promising, reconstruction-based methods often waste capacity on large task-irrelevant regions. Decoder-free methods instead learn robust representations by leveraging Data Augmentation (DA), but reliance on such external regularizers limits versatility. We propose R2-Dreamer, a decoder-free MBRL framework with a self-supervised objective that serves as an internal regularizer, preventing representation collapse without resorting to DA. The core of our method is a \emph{redundancy-reduction} objective inspired by Barlow Twins, which can be easily integrated into existing frameworks. On DeepMind Control Suite and Meta-World, R2-Dreamer is competitive with strong baselines such as DreamerV3 and TD-MPC2 while training 1.59$\times$ faster than DreamerV3, and yields substantial gains on DMC-Subtle with tiny task-relevant objects. These results suggest that an effective internal regularizer can enable versatile, high-performance decoder-free MBRL. Code is available at https://github.com/NM512/r2dreamer.

Diffusion language models (DLMs) enable parallel, order-agnostic generation with iterative refinement, offering a flexible alternative to autoregressive large language models (LLMs). However, adapting reinforcement learning (RL) fine-tuning to DLMs remains an open challenge because of the intractable likelihood. Pioneering work such as diffu-GRPO estimated token-level likelihoods via one-step unmasking. While computationally efficient, this approach is severely biased. A more principled foundation lies in sequence-level likelihoods, where the evidence lower bound (ELBO) serves as a surrogate. Yet, despite this clean mathematical connection, ELBO-based methods have seen limited adoption due to the prohibitive cost of likelihood evaluation. In this work, we revisit ELBO estimation and disentangle its sources of variance. This decomposition motivates reducing variance through fast, deterministic integral approximations along a few pivotal dimensions. Building on this insight, we introduce **Group Diffusion Policy Optimization (GDPO)**, a new RL algorithm tailored for DLMs. GDPO leverages simple yet effective *Semi-deterministic Monte Carlo* schemes to mitigate the variance explosion of ELBO estimators under vanilla double Monte Carlo sampling, yielding a provably lower-variance estimator under tight evaluation budgets. Empirically, GDPO achieves consistent gains over pretrained checkpoints and outperforms diffu-GRPO, one of the state-of-the-art baselines, on the majority of math, reasoning, and coding benchmarks.

Ultra-long generation by large language models (LLMs) is a widely demanded scenario, yet it remains a significant challenge due to their maximum generation length limit and overall quality degradation as sequence length increases. Previous approaches, exemplified by LongWriter, typically rely on ''teaching'', which involves supervised fine-tuning (SFT) on synthetic long-form outputs. However, this strategy heavily depends on synthetic SFT data, which is difficult and costly to construct, often lacks coherence and consistency, and tends to be overly artificial and structurally monotonous. In this work, we propose an incentivization-based approach that, starting entirely from scratch and without relying on any annotated or synthetic data, leverages reinforcement learning (RL) to foster the emergence of ultra-long, high-quality text generation capabilities in LLMs. We perform RL training starting from a base model, similar to R1-Zero, guiding it to engage in reasoning that facilitates planning and refinement during the writing process. To support this, we employ specialized reward models that steer the LLM towards improved length control, writing quality, and structural formatting. Experimental evaluations show that our LongWriter-Zero model, trained from Qwen2.5-32B, consistently outperforms traditional SFT methods on long-form writing tasks, achieving state-of-the-art results across all metrics on WritingBench and Arena-Write, and even surpassing 100B+ models such as DeepSeek R1 and Qwen3-235B.

Image captioning is a fundamental task that bridges the visual and linguistic domains, playing a critical role in pre-training Large Vision-Language Models (LVLMs). Current state-of-the-art captioning models are typically trained with Supervised Fine-Tuning (SFT), a paradigm that relies on expensive, non-scalable data annotated by humans or proprietary models. This approach often leads to models that memorize specific ground-truth answers, limiting their generality and ability to generate diverse, creative descriptions. To overcome the limitation of SFT, we propose applying the Reinforcement Learning with Verifiable Rewards (RLVR) paradigm to the open-ended task of image captioning. A primary challenge, however, is designing an objective reward function for the inherently subjective nature of what constitutes a "good" caption. We introduce Captioning Reinforce- ment Learning (CapRL), a novel training framework that redefines caption quality through its utility: a high-quality caption should enable a non-visual language model to accurately answer questions about the corresponding image. CapRL employs a decoupled two-stage pipeline where an LVLM generates a caption, and the objective reward is derived from the accuracy of a separate, vision-free LLM answering Multiple-Choice Questions based solely on that caption. As the first study to apply RLVR to the subjective image captioning task, we demonstrate that CapRL significantly enhances multiple settings. Pretraining on the CapRL- 5M caption dataset annotated by CapRL-3B results in substantial gains across 12 benchmarks. Moreover, within the Prism Framework for caption quality evaluation, CapRL achieves performance comparable to Qwen2.5-VL-72B, while exceeding the baseline by an average margin of 8.4%. Results validate that our CapRL effec- tively trains models to produce a more general and accurate image descriptions, moving beyond the limitations of traditional SFT-based image captioning models.