ICLR 2026 论文列表

Recent advances in video multimodal large language models (Video MLLMs) have significantly enhanced video understanding and multi-modal interaction capabilities. While most existing systems operate in a turn-based manner where the model can only reply after user turns, proactively deciding when to reply during video playback presents a promising yet challenging direction for real-time applications. In this work, we propose a novel text-to-text approach to proactive interaction, where the model autonomously determines whether to respond or remain silent at each turn based on dialogue history and visual context up to current frame of an streaming video. To overcome difficulties in previous methods such as manually tuning response decision thresholds and annotating precise reply times, we introduce a multi-turn RL based training method that encourages timely and accurate responses without requiring precise response time annotations. We train our model MMDuet2 on a dataset of 52k videos with two types of dialogues via SFT and RL. Experimental results demonstrate that MMDuet2 outperforms existing proactive Video MLLM baselines in response timing and quality, achieving state-of-the-art performance on the ProactiveVideoQA benchmark.

Estimating the state of an environment from high-dimensional, multimodal, and noisy observations is a fundamental challenge in reinforcement learning (RL). Traditional approaches rely on probabilistic models to account for the uncertainty, but often require explicit noise assumptions, in turn limiting generalization. In this work, we contribute a novel method to learn a structured latent representation, in which distances between states directly correlate with the minimum number of actions required to transition between them. The proposed metric space formulation provides a geometric interpretation of uncertainty without the need for explicit probabilistic modeling. To achieve this, we introduce a multimodal latent transition model and a sensor fusion mechanism based on inverse distance weighting, allowing for the adaptive integration of multiple sensor modalities without prior knowledge of noise distributions. We empirically validate the approach on a range of multimodal RL tasks, demonstrating improved robustness to sensor noise and superior state estimation compared to baseline methods. Our experiments show enhanced performance of an RL agent via the learned representation, eliminating the need of explicit noise augmentation. The presented results suggest that leveraging transition-aware metric spaces provides a principled and scalable solution for robust state estimation in sequential decision-making.

Distilling robust reasoning capabilities from large language models (LLMs) into smaller, computationally efficient student models remains an unresolved challenge. Despite recent advances, distilled models frequently suffer from superficial pattern memorization and subpar generalization. To overcome these limitations, we introduce a novel distillation framework that moves beyond simple mimicry to instill a deeper conceptual understanding. Our framework features two key innovations. \underline{\textit{First}}, to address pattern memorization, Explanatory Inversion (EI) generates targeted ``explanatory probes'' that compel the student to articulate the underlying logic behind an answer, rather than just memorizing it. \underline{\textit{Second}}, to improve generalization, Explanatory GRPO (\texttt{EXGRPO}) uses a reinforcement learning algorithm with a novel Dialogue Structure Utility Bonus, which explicitly rewards the student for maintaining a coherent reasoning process across these probes. Extensive evaluations on 12 datasets demonstrate significant improvements. Using Gemma-7b as the student model, our method yields an average \textbf{20.39\%} increase over zero-shot performance and a \textbf{6.02\%} improvement over the state-of-the-art distillation baselines. Moreover, models distilled with our method show remarkable training efficiency (e.g., surpassing vanilla fine-tuning with \textbf{10-25\%} training data) and strong generalization to out-of-distribution tasks.

Parameter-efficient Mixture-of-Experts (MoE) architectures, such as LoRA-MoE, enable strong and generalizable fine-tuning. However, a critical problem arises when fine-tuning these architectures with advanced reinforcement learning algorithms such as Group Relative Policy Optimization (GRPO). Traditional supervised techniques are not naturally compatible with the GRPO objective, and naive combinations fail to effectively address routing collapse and the underutilization of MoE adapter parameters. To resolve this disconnect, we introduce Routing-Optimized Group Relative Policy Optimization (RO-GRPO), a mechanism-aware framework. It turns internal expert routing statistics collected during training into a direct reward signal, seamlessly integrating routing supervision into the reinforcement fine-tuning (RFT) process. This enables effective optimization of parameter utilization and improves performance on both unimodal and multimodal mathematical reasoning tasks, all without extra training stages. Our work provides the first demonstration that a scalar reward in GRPO can be engineered from a model's own internal mechanics to explicitly guide its optimization, extending alignment from mere behavior tuning to holistic mechanism alignment.

Reinforcement Learning from Verifiable Rewards (RLVR) is a promising method for enhancing the complex problem-solving abilities of large language models (LLMs). This is particularly evident in domains requiring long-horizon reasoning and precise execution, such as solving complex mathematical problems where solutions hinge on a fragile sequence of tool-based actions. However, current approaches are often crippled by two interconnected issues: the near-miss problem, where sparse rewards nullify the learning signal for almost-correct attempts, and the resulting exploration stagnation, which prevents the model from discovering better solutions. To address these challenges, we introduce HiPO (Hint-guided Policy Optimization), a novel RLVR framework that enables the agent to learn from its own rare successes. Our core insight is to capture an occasional successful trajectory within a training batch and repurpose its initial correct steps as an on-policy “hint”. This process transforms a single, stochastically-found success into a dense contrastive learning signal, effectively allowing the model to teach itself how to overcome the near-miss problem and break exploration stagnation. On a challenging suite of five mathematical reasoning benchmarks, HiPO improves the average avg@32 by +5.0 percentage points (pp) over the strong GRPO baseline. This improvement is driven by substantial absolute point gains on challenging datasets, including +10.3 pp on CMIMC 2025, +4.9 pp on BRUMO 2025, +4.6 pp on AIME 2024, and +3.1 pp on AIME 2025. Furthermore, HiPO demonstrates a new exploration paradigm, repurposing rare successes into reusable guidance to significantly accelerate skill acquisition for complex tasks, establishing a more efficient and scalable path for models to autonomously master intricate reasoning.

We introduce a sequence-conditioned critic for Soft Actor--Critic (SAC) that models trajectory context with a lightweight Transformer and trains on aggregated $N$-step targets. Unlike prior approaches that (i) score state--action pairs in isolation or (ii) rely on actor-side action chunking to handle long horizons, our method strengthens the critic itself by conditioning on short trajectory segments and integrating multi-step returns---without importance sampling (IS). The resulting sequence-aware value estimates capture temporal structure critical for extended-horizon and sparse-reward problems. On local-motion benchmarks, we further show that freezing critic parameters for several steps makes our update compatible with CrossQ's core idea, enabling stable training without a target network. Despite its simplicity---a 2-layer Transformer with 128--256 hidden units and a maximum update-to-data ratio (UTD) of $1$---the approach consistently outperforms standard SAC and strong off-policy baselines, with particularly large gains on long-trajectory control. These results highlight the value of sequence modeling and $N$-step bootstrapping on the critic side for long-horizon reinforcement learning.

Neural solvers have achieved impressive progress in addressing simple routing problems, particularly excelling in computational efficiency. However, their advantages under complex constraints remain nascent, for which current constraint-handling schemes via feasibility masking or implicit feasibility awareness can be inefficient or inapplicable for hard constraints. In this paper, we present Construct-and-Refine (CaR), the first general and efficient constraint-handling framework for neural routing solvers based on explicit learning-based feasibility refinement. Unlike prior construction-search hybrids that target reducing optimality gaps through heavy improvements yet still struggle with hard constraints, CaR achieves efficient constraint handling by designing a joint training framework that guides the construction module to generate diverse and high-quality solutions well-suited for a lightweight improvement process, e.g., 10 steps versus 5k steps in prior work. Moreover, CaR presents the first use of construction-improvement-shared representation, enabling potential knowledge sharing across paradigms by unifying the encoder, especially in more complex constrained scenarios. We evaluate CaR on typical hard routing constraints to showcase its broader applicability. Results demonstrate that CaR achieves superior feasibility, solution quality, and efficiency compared to both classical and neural state-of-the-art solvers. Our code, pre-trained models, and datasets are available at: https://github.com/jieyibi/CaR-constraint.

High-stakes, infrequent consumer decisions, such as housing selection, challenge conventional recommender systems due to sparse interaction signals, heterogeneous multi-criteria objectives, and high-dimensional feature spaces. This work presents an interactive preference elicitation framework that couples preferential Bayesian optimization (PBO) with two complementary components: (i) large language models (LLMs) that interpret natural language input to produce personalized probabilistic priors over feature utility weights to mitigate cold start, and (ii) an autoencoder (AE)-based latent representation that reduces effective dimensionality for sample-efficient exploration. The framework learns a latent utility function from user pairwise comparisons observed and integrated in real-time. We evaluate the developed method on rental real estate datasets from two major European cities. The results show that executing PBO in an AE latent space improves final pairwise ranking accuracy by 12%. For LLM-based preference prior generation, we find that direct, LLM-driven weight specification is outperformed by a static prior, while probabilistic weight priors that use LLMs only to rank feature importance achieve 25% better pairwise accuracy on average than a direct approach.

DPO and related algorithms align language models by directly optimizing the RLHF objective: find a policy that maximizes the Bradley-Terry reward while staying close to a reference policy through a KL divergence penalty. Previous work showed that this approach could be further generalized: the original problem remains tractable even if the KL divergence is replaced by a family of $f$-divergence with a convex generating function $f$. Our first contribution is to show that convexity of $f$ is not essential. Instead, we identify a more general condition, referred to as DPO-inducing, that precisely characterizes when the RLHF problem remains tractable. Our next contribution is to establish a second condition on $f$ that is necessary to prevent probability displacement, a known empirical phenomenon in which the probabilities of the winner and the loser responses approach zero. We refer to any $f$ that satisfies this condition as displacement-resistant. We finally focus on a specific DPO-inducing and displacement-resistant $f$, leading to our novel SquaredPO loss. Compared to DPO, this new loss offers stronger theoretical guarantees while performing competitively in practice.

Humans can often perform a new task after observing a few demonstrations by inferring the underlying intent. For robots, recovering the intent of the demonstrator through a learned reward function can enable more efficient, interpretable, and robust imitation through planning. A common paradigm for learning how to plan-from-demonstration involves first solving for a reward via Inverse Reinforcement Learning (IRL) and then deploying it via Model Predictive Control (MPC). In this work, we unify these two procedures by introducing planning-based Adversarial Imitation Learning, which simultaneously learns a reward and improves a planning-based agent through experience while using observation-only demonstrations. We study advantages of planning-based AIL in generalization, interpretability, robustness, and sample efficiency through experiments in simulated control tasks and real-world navigation from few or single observation-only demonstration.

Recent trends in test-time scaling for reasoning models (e.g., OpenAI o1, DeepSeek-R1) have led to remarkable improvements through long Chain-of-Thought (CoT). However, existing benchmarks mainly focus on immediate, single-horizon tasks, failing to adequately evaluate models’ ability to understand and respond to complex, long-horizon scenarios. To address this incomplete evaluation of Large Reasoning Models (LRMs), we propose R-HORIZON, a method designed to stimulate long-horizon reasoning behaviors in LRMs through query composition. Based on R-HORIZON, we construct a long-horizon reasoning benchmark, comprising complex multi-step reasoning tasks with interdependent problems that span long reasoning horizons. Through comprehensive evaluation of LRMs using the R-HORIZON benchmark, we find that even the most advanced LRMs suffer significant performance degradation. Our analysis reveals that LRMs exhibit limited effective reasoning length and struggle to allocate thinking budget across multiple problems appropriately. Recognizing these limitations, we use R-HORIZON to construct long-horizon reasoning data for reinforcement learning with verified rewards (RLVR). Compared to training with single-horizon data, RLVR with R-HORIZON not only substantially improves performance on the multi-horizon reasoning tasks, but also promotes accuracy on standard reasoning tasks (+7.5 on AIME2024). These results position R-HORIZON as a scalable, controllable, and low-cost paradigm for enhancing and evaluating the long-horizon reasoning capabilities of LRMs.

Reinforcement finetuning (RFT) is a key technique for aligning Large Language Models (LLMs) with human preferences and enhancing reasoning, yet its effectiveness is highly sensitive to which tasks are explored during training. Uniform task sampling is inefficient, wasting computation on tasks that are either trivial or unsolvable, while existing task selection methods often suffer from high rollout costs, poor adaptivity, or incomplete evidence. We introduce \textbf{BOTS}, a unified framework for \textbf{B}ayesian \textbf{O}nline \textbf{T}ask \textbf{S}election in LLM reinforcement finetuning. Grounded in Bayesian inference, BOTS adaptively maintains posterior estimates of task difficulty as the model evolves. It jointly incorporates \emph{explicit evidence} from direct evaluations of selected tasks and \emph{implicit evidence} inferred from these evaluations for unselected tasks, with Thompson sampling ensuring a principled balance between exploration and exploitation for task selection. To make implicit evidence practical, we instantiate it with an ultra-light interpolation-based plug-in that estimates difficulties of unevaluated tasks without extra rollouts, adding negligible overhead. Empirically, across diverse domains and LLM scales, BOTS consistently improves data efficiency and performance over baselines and ablations, providing a practical and extensible solution for dynamic task selection in RFT.

Reinforcement learning in combinatorial action spaces requires searching over exponentially many joint actions to simultaneously select multiple sub-actions that form coherent combinations. Existing approaches either simplify policy learning by assuming independence across sub-actions, which often yields incoherent or invalid actions when coordination is required, or attempt to learn action structure and control jointly, which is slow and unstable. We introduce Structured Policy Initialization (SPIN), a two-stage framework that first pre-trains an Action Structure Model (ASM) to capture the manifold of valid actions, then freezes this representation and trains lightweight policy heads for control. On challenging DM Control benchmarks, SPIN improves average return by up to $39\%$ over the state of the art while reducing time to convergence by up to $12.8\times$.

Vision-language models, such as CLIP, achieve strong zero-shot performance through contrastive pre-training but face significant challenges in class-incremental image classification scenarios. When learning new tasks sequentially, current methods suffer from degradation in prototype quality due to passive averaging and underutilize their visual adaptation capabilities. We propose RLAP-CLIP, which addresses these limitations through three components. First, Reinforcement Learning-based Prototype Optimization (RLPO) formulates prototype construction as a reinforcement learning problem to actively optimize class separability rather than relying on simple averaging. Second, difficulty-aware cross-modal fusion uses a mixture-of-experts to route samples through specialized processing pathways based on complexity. Third, dual-modal prompting balances visual and textual adaptation. Experiments on eight image classification benchmarks demonstrate consistent improvements, with RLAP-CLIP achieving average accuracy gains of 3.72-4.46 points and final accuracy improvements of 0.49-4.48 points over other methods, validating that RLAP-CLIP achieves state-of-the-art performance. Our source code is available at [RLAP-CLIP](https://anonymous.4open.science/r/197165541613026132779/RLAP-CLIP).

Large language models (LLMs) are increasingly used to assist scientists across diverse workflows. A key challenge is generating high-quality figures from textual descriptions, often represented as TikZ programs that can be rendered as scientific images. Prior research has proposed a variety of datasets and modeling approaches for this task. However, existing datasets for Text-to-TikZ are too small and noisy to capture the complexity of TikZ, causing mismatches between text and rendered figures. Moreover, prior approaches rely solely on supervised fine-tuning (SFT), which does not expose the model to the rendered semantics of the figure, often resulting in errors such as looping, irrelevant content, and incorrect spatial relations. To address these issues, we construct DaTikZ-V4, a dataset more than four times larger and substantially higher in quality than DaTikZ-V3, enriched with LLM-generated figure descriptions. Using this dataset, we train TikZilla, a family of small open-source Qwen models (3B and 8B) with a two-stage pipeline of SFT followed by reinforcement learning (RL). For RL, we leverage an image encoder trained via inverse graphics to provide semantically faithful reward signals. Extensive human evaluations with over 1,000 judgments show that TikZilla improves by 1.5-2 points over its base models on a 5-point scale, surpasses GPT-4o by 0.5 points, and matches GPT-5 in the image-based evaluation, while operating at much smaller model sizes. Code, data, and models will be made available.

The use of target networks is a popular approach for estimating value functions in deep Reinforcement Learning (RL). While effective, the target network remains a compromise solution that preserves stability at the cost of slowly moving targets, thus delaying learning. Conversely, using the online network as a bootstrapped target is intuitively appealing, albeit well-known to lead to unstable learning. In this work, we aim to obtain the best out of both worlds by introducing a novel update rule that computes the target using the **MIN**imum estimate between the **T**arget and **O**nline network, giving rise to our method, **MINTO**. Through this simple, yet effective modification, we show that MINTO enables faster and stable value function learning, by mitigating the potential overestimation bias of using the online network for bootstrapping. Notably, MINTO can be seamlessly integrated into a wide range of value-based and actor-critic algorithms with a negligible cost. We evaluate MINTO extensively across diverse benchmarks, spanning online and offline RL, as well as discrete and continuous action spaces. Across all benchmarks, MINTO consistently improves performance, demonstrating its broad applicability and effectiveness.

Active reasoning requires large language models (LLMs) to interact with external sources and strategically gather information to solve problems. Central to this process is belief tracking: maintaining a coherent understanding of the problem state and the missing information toward the solution. However, due to limited reasoning capabilities, LLM-based agents often suffer from belief deviation: they struggle to correctly model beliefs, lose track of problem states, and fall into uninformative or repetitive actions. Once this happens, errors compound and reinforcement learning (RL) training fails to properly credit the crucial exploratory steps. To address this issue, we propose to track the deviation of model beliefs and develop $\mathbf{T^3}$, a simple yet effective method that detects excessive belief deviation and truncates trajectories during training to remove uninformative tails. By preserving credit for informative prefixes, $\mathbf{T^3}$ systematically improves policy optimization. Across 5 challenging tasks, $\mathbf{T^3}$ consistently enhances training stability, token efficiency, and final performance, achieving up to 30\% gains while cutting rollout tokens by roughly 25\%. These results highlight belief control as a key principle for developing robust and generalizable LLM-based active reasoners.

Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models. While existing analyses identify that RLVR-induced changes are sparse, they primarily focus on the **magnitude** of these updates, largely overlooking their **direction**. In this work, we argue that the direction of updates is a more critical lens for understanding RLVR's effects, which can be captured by the signed, token-level log probability difference $\Delta\log p$ between the base and final RLVR models. Through statistical analysis and token-replacement interventions, we demonstrate that $\Delta\log p$ more effectively identifies sparse, yet reasoning-critical updates than magnitude-based metrics (e.g., divergence or entropy). Building on this insight, we propose two practical applications: (1) a *test-time extrapolation* method that amplifies the policy along the learned $\Delta\log p$ direction to improve reasoning accuracy without further training; (2) a *training-time reweighting* method that focuses learning on low-probability (corresponding to higher $\Delta\log p$) tokens, which improves reasoning performance across models and benchmarks. Our work establishes the direction of change as a key principle for analyzing and improving RLVR.

The advent of Vision-Language Models (VLMs) has significantly advanced end-to-end autonomous driving, demonstrating powerful reasoning abilities for high-level behavior planning tasks. However, existing methods are often constrained by a passive perception paradigm, relying solely on text-based reasoning. This passivity restricts the model’s capacity to actively seek crucial visual evidence when faced with uncertainty. To address this, we introduce DriveAgent-R1, an autonomous driving agent capable of active perception for planning. In complex scenarios, DriveAgent-R1 proactively invokes tools to perform visual reasoning, firmly grounding its decisions in visual evidence, thereby enhancing both interpretability and reliability. Furthermore, we propose a hybrid thinking framework, inspired by human driver cognitive patterns, allowing the agent to adaptively switch between efficient text-only reasoning and robust tool-augmented visual reasoning based on scene complexity. This capability is cultivated through a three-stage progressive training strategy, featuring a core Cascaded Reinforcement Learning (Cascaded RL) phase. Extensive experiments on the Drive-Internal dataset, which is rich in long-tail scenarios, and the public nuScenes dataset show that, with only 3B parameters, DriveAgent-R1 achieves competitive performance comparable to top closed model systems such as GPT-5 and to human driving proficiency while remaining deployment-friendly, offering a proven path toward building more intelligent autonomous driving systems.