ICLR 2026 论文列表

The incorporation of memory into agents is essential for numerous tasks within the domain of Reinforcement Learning (RL). In particular, memory is paramount for tasks that require the use of past information, adaptation to novel environments, and improved sample efficiency. However, the term ``memory'' encompasses a wide range of concepts, which, coupled with the lack of a unified methodology for validating an agent's memory, leads to erroneous judgments about agents' memory capabilities and prevents objective comparison with other memory-enhanced agents. This paper aims to streamline the concept of memory in RL by providing practical precise definitions of agent memory types, such as long-term vs. short-term memory and declarative vs. procedural memory, inspired by cognitive science. Using these definitions, we categorize different classes of agent memory, propose a robust experimental methodology for evaluating the memory capabilities of RL agents, and standardize evaluations. Furthermore, we empirically demonstrate the importance of adhering to the proposed methodology when evaluating different types of agent memory by conducting experiments with different RL agents and what its violation leads to.

In-context learning lets large models adapt to new tasks from a few demonstrations, but it has shown limited success in molecular design, where labeled data are scarce and properties span millions of biological assays and material measurements. We introduce demonstration-conditioned diffusion models (DemoDiff), which define task contexts through molecule–score examples instead of texts. These demonstrations guide a denoising Transformer to generate molecules aligned with target properties. For scalable pretraining, we develop a new molecular tokenizer with Node Pair Encoding that represents molecules at the motif level, requiring 5.5$\times$ fewer nodes. We pretrain a 0.7B parameter model on datasets covering drugs and materials. Across 33 design tasks in six categories, DemoDiff matches or surpasses language models 100–1000$\times$ larger and achieves an average rank of 4.10 compared to 6.56–17.95 for 19 baselines. These results position DemoDiff as a molecular foundation model for in-context molecular design.

Vision-Language Models (VLMs) in remote sensing often fail at complex analytical tasks, a limitation stemming from their end-to-end training paradigm that bypasses crucial reasoning steps and leads to unverifiable outputs. To address this limitation, we introduce the Perceptually-Grounded Geospatial Chain-of-Thought (Geo-CoT), a framework that models remote sensing analysis as a verifiable, multi-step process. We instill this analytical process through a two-stage alignment strategy, leveraging Geo-CoT380k, the first large-scale dataset of structured Geo-CoT rationales. This strategy first employs supervised fine-tuning (SFT) to instill the foundational cognitive architecture, then leverages Group Reward Policy Optimization (GRPO) to refine the model’s reasoning policy towards factual correctness. The resulting model, RSThinker, outputs both a final answer and its justifying, verifiable analytical trace. This capability yields dominant performance, significantly outperforming state-of-the-art models across a comprehensive range of tasks. The public release of our Geo-CoT380k dataset and RSThinker model upon publication serves as a concrete pathway from opaque perception towards structured, verifiable reasoning for Earth Observation.

In this work, we propose ***R**einforced **F**unctional **T**oken **T**uning* (RFTT), a novel reinforced fine-tuning framework that empowers Large Language Models (LLMs) with learn-to-reason capabilities. Unlike prior prompt-driven reasoning efforts, RFTT embeds a rich set of learnable functional tokens (*e.g.*, \<analyze\>, \<verify\>, \<refine\>) directly into the model vocabulary, enabling chain-of-thought construction with diverse human-like reasoning behaviors. Specifically, RFTT comprises two phases: (1) supervised fine-tuning performs prompt-driven tree search to obtain self-generated training data annotated with functional tokens, which warms up the model to learn these tokens for initial reasoning capability; and (2) online reinforcement learning further allows the model to explore diverse reasoning pathways through functional token sampling without relying on prompts, thereby facilitating effective self-improvement for functional reasoning. Extensive experiments demonstrate the superiority of the proposed RFTT on mathematical benchmarks and highlight its strong generalization capability to other general domains. Moreover, the performance of RFTT exhibits consistent gains with increased test-time computation through additional search rollouts. Our code and dataset are available at anonymous url.

Recent neural methods have shown promise in generalizing across various vehicle routing problems (VRPs). These methods adopt either a fully-shared dense model across all VRP tasks (i.e., variants) or a mixture-of-experts model that assigns node embeddings within each task instance to different experts. However, they both struggle to generalize from training tasks with basic constraints to out-of-distribution (OOD) tasks involving unseen constraint combinations and new basic constraints, as they overlook the fact that each VRP task is defined by a combination of multiple basic constraints. To address this, this paper proposes a novel model, combination-of-experts with knowledge sharing (CoEKS), which leverages the structural characteristic of VRP tasks. CoEKS enhances generalization to constraint combinations via two complementary components: a combination-of-experts architecture enabling flexible combinations via prior assignment of constraint-specific experts, and a knowledge sharing strategy strengthening generalization via automatic learning of transferable general knowledge across constraints. Moreover, CoEKS allows new experts to be plugged into the trained model for rapid adaptation to new constraints. Experiments demonstrate that CoEKS outperforms state-of-the-art methods on in-distribution tasks and delivers greater gains on OOD tasks, including unseen constraint combinations (relative improvement of 12\% over SOTA) and new constraints (25\% improvement).

In heterogeneous treatment effect estimation from observational data, the fundamental challenge is that only the factual outcome under the received treatment is observable, while the potential outcomes under other treatments or no treatment can never be observed. As a simple and effective approach, matching aims to predict counterfactual outcomes of the target treatment by leveraging the nearest neighbors within the target group. However, due to limited observational data and the distribution shifts between groups, one cannot always find sufficiently close neighbors in the target group, resulting in inaccurate counterfactual prediction because of the manifold structure of data. To address this, we remove group barriers and propose a matching method that selects neighbors from all samples, not just the target group. This helps find closer neighbors and improves counterfactual prediction. Specifically, we analyze the effect estimation error in matching, which motivates us to propose a self optimal transport model for matching. Based on this, we employ an outcome propagation mechanism via the transport plan for counterfactual prediction, and exploit factual outcomes to learn a distance as the transport cost. The experiments are conducted on both binary and multiple treatment settings to evaluate our method.

Visualization, a domain-specific yet widely used form of imagery, is an effective way to turn complex datasets into intuitive insights, and its value depends on whether data are faithfully represented, clearly communicated, and aesthetically designed. However, evaluating visualization quality is challenging: unlike natural images, it requires simultaneous judgment across data encoding accuracy, information expressiveness, and visual aesthetics. Although multimodal large language models (MLLMs) have shown promising performance in aesthetic assessment of natural images, no systematic benchmark exists for measuring their capabilities in evaluating visualizations. To address this, we propose VisJudge-Bench, the first comprehensive benchmark for evaluating MLLMs' performance in assessing visualization aesthetics and quality. It contains 3,090 expert-annotated samples from real-world scenarios, covering single visualizations, multiple visualizations, and dashboards across 32 chart types. Systematic testing on this benchmark reveals that even the most advanced MLLMs (such as GPT-5) still exhibit significant gaps compared to human experts in judgment, with a Mean Absolute Error (MAE) of 0.553 and a correlation with human ratings of only 0.428. To address this issue, we propose VisJudge, a model specifically designed for visualization aesthetics and quality assessment. Experimental results demonstrate that VisJudge significantly narrows the gap with human judgment, reducing the MAE to 0.421 (a 23.9% reduction) and increasing the consistency with human experts to 0.687 (a 60.5% improvement) compared to GPT-5.

Feed-forward 3D Gaussian Splatting (3DGS) has shown great promise for real-time novel view synthesis, but its application to panoramic imagery remains challenging. Existing methods often rely on multi-view cost volumes for geometric refinement, which struggle to resolve occlusions in sparse-view scenarios. Furthermore, standard volumetric representations like Cartesian Triplanes are poor in capturing the inherent geometry of $360^\circ$ scenes, leading to distortion and aliasing. In this work, we introduce CylinderSplat, a feed-forward framework for panoramic 3DGS that addresses these limitations. The core of our method is a new {cylindrical Triplane} representation, which is better aligned with panoramic data and real-world structures adhering to the Manhattan-world assumption. We use a dual-branch architecture: a pixel-based branch reconstructs well-observed regions, while a volume-based branch leverages the cylindrical Triplane to complete occluded or sparsely-viewed areas. Our framework is designed to flexibly handle a variable number of input views, from single to multiple panoramas. Extensive experiments demonstrate that CylinderSplat achieves state-of-the-art results in both single-view and multi-view panoramic novel view synthesis, outperforming previous methods in both reconstruction quality and geometric accuracy.

Integrated circuit (IC) designs require transforming high-level specifications into physical layouts, demanding extensive expertise and specialized tools, as well as months of time and numerous iterations. While Machine Learning (ML) has shown promise in various research domains, the lack of large-scale, open datasets limits its application in chip design. To address this limitation, we introduce CircuitNet 3.0, a large-scale, comprehensive, and open-source dataset curated to facilitate the evaluation of ML models on challenging timing and power prediction tasks. Starting with a diverse set of 8,659 validated open-source designs, we employ a systematic framework to generate over 15,000 instances. Through specialized syntax-tree mutation strategies and principled, task-oriented filtering methodology, we enrich each design with multi-modal information spanning multiple design stages, including complete design flow documentation, register-transfer-level (RTL) designs and corresponding netlists, detailed physical layouts, and comprehensive performance metrics. The experimental results convincingly demonstrate that ML models leveraging multi-stage, multi-modal circuit representations significantly improve performance over existing open-source datasets in electronic design automation (EDA) tasks, paving the way for efficient and accessible circuit representation learning. The dataset and codes are available in https://anonymous.4open.science/r/ICLR26-CircuitNet3-272B.

The inverse design of RNA three-dimensional (3D) structures is crucial for engineering functional RNAs in synthetic biology and therapeutics. While recent deep learning approaches have advanced this field, they are typically optimized and evaluated using native sequence recovery, which is a limited surrogate for structural fidelity, since different sequences can fold into similar 3D structures and high recovery does not necessarily indicate correct folding. To address this limitation, we propose RIDER, an RNA Inverse DEsign framework with Reinforcement learning that directly optimizes for 3D structural similarity. First, we develop and pre-train a GNN-based generative diffusion model conditioned on the target 3D structure, achieving a $9\\%$ improvement in native sequence recovery over state-of-the-art methods. Then, we fine-tune the model with an improved policy gradient algorithm using four task-specific reward functions based on 3D self-consistency metrics. Experimental results show that RIDER improves structural similarity by over $100\\%$ across all metrics and discovers designs that are distinct from native sequences.

Although Multimodal Large Language Models (MLLMs) have demonstrated proficiency in video captioning, practical applications require captions that follow specific user instructions rather than generating exhaustive, unconstrained descriptions. Current benchmarks, however, primarily assess descriptive comprehensiveness while largely overlook instruction-following capabilities. To address this gap, we introduce IF-VidCap, a new benchmark for evaluating controllable video captioning, which contains 1,400 high-quality samples. Distinct from existing video captioning or general instruction-following benchmarks, IF-VidCap incorporates a systematic framework that assesses captions on two dimensions: format correctness and content correctness. Our comprehensive evaluation of over 19 prominent models reveals a nuanced landscape: despite the continued dominance of proprietary models, the performance gap is closing, with top-tier open-source solutions now achieving near-parity. Furthermore, we find that models specialized for dense captioning underperform general-purpose MLLMs on complex instructions, indicating that future work should simultaneously advance both descriptive richness and instruction-following fidelity.

Diffusion language models have emerged as a powerful alternative to autoregressive models, enabling fast inference through more flexible and parallel generation paths. This flexibility of sampling is unlocked by new engineered sampling strategies, or *planners*, that select more favorable generation paths by iteratively planning---versus uniformly at random---where to denoise along the sequence. However, by modifying the reverse paths via planning, planners create an irrevocable mismatch between the uniformly random denoising paths during training and planning-based inference. In this paper, we systematically investigate the mismatch of discrete diffusion training and inference under planning and theoretically prove that the standard discrete diffusion training evidence lower bound (ELBO) does not accurately describe a denoiser that uses a non-uniform planner. To address this gap, we derive a new planned evidence lower bound (P-ELBO) that incorporates planner-based reverse dynamics directly into the training objective. Using the P-ELBO, we introduce *Planner Aware Path Learning* (PAPL), a novel training scheme that aligns training and inference under a planned denoiser. PAPL is implemented as a simple yet effective modification to the standard masked discrete diffusion loss, making it widely applicable and easy to adopt. Empirically, we show PAPL delivers consistent gains across domains, including a 40\% relative improvement in protein sequences, improved text generation with up to a $4\times$ relative MAUVE gain, and 23\% relative improvement in code generation HumanEval pass@10.

The widespread deployment of large language models (LLMs) has made the reliable detection of AI-generated text a crucial task. However, existing zero-shot detectors typically rely on proxy models to approximate probability distributions of unknown source models at a single token level. Such approaches limit detection effectiveness and make the results highly sensitive to the choice of proxy models. In contrast, supervised classifiers are often detected as black boxes, sacrificing interpretability in the detection process. To address these limitations, we propose a novel detection framework that identifies LLM-generated text by approximating \textbf{H}ierarchical \textbf{L}inguistic \textbf{D}istributions--\textbf{HLD-Detector}. Specifically, we leverage n-grams to capture the feature distribution of human-written and machine-generated text across the word, syntactic, and semantic levels, and perform LLM-generated text detection by comparing these distributions under the Bayesian theory. By progressively modeling the linguistic distribution from shallow-level (token/word), then medium-level (syntactic), and ultimately high-level (semantic representations), our method mitigates the shortcomings of previous single feature level detectors, improving both robustness and overall performance. Additionally, HLD-Detector requires only a small amount of offline corpus for distribution estimation, instead of relying on online approximation with large proxy models, resulting in significantly lower computational overhead. Extensive experiments have verified the superiority of our method in detection tasks such as multi-llm and multi-domain scenarios, achieving the current SOTA performance.

Recent advances in Bird’s Eye View (BEV) layout estimation have advanced through refinements in architectural and geometric design. However, existing methods often overlook the structured relationships among traffic elements. Components such as drivable areas, lane dividers, and pedestrian crossings constitute an interdependent system governed by civil engineering standards. For instance, stop lines precede crosswalks, which align with sidewalks, while lane dividers follow road curvature. To capture these interdependencies, we propose \textbf{ARINBEV}, an autoregressive model for BEV map estimation. Unlike prior generative approaches that rely on complex multiphase training or encoder-decoder architectures, ARINBEV employs a single-stage, decoder-only autoregressive design. This architecture enables semantically consistent BEV map estimation. On nuScenes and Argoverse2, ARINBEV attains 64.3 and 65.6 mIoU, respectively, while using $1.7\times$ fewer parameters and training $1.8\times$ faster than state-of-the-art models.

Approximate nearest neighbor search (ANN) is a common way to retrieve relevant search results, especially now in the context of large language models and retrieval augmented generation. One of the most widely used algorithms for ANN is based on constructing a multi-layer graph over the dataset, called the Hierarchical Navigable Small World (HNSW). While this algorithm supports insertion of new data, it does not support deletion of existing data. Moreover, deletion algorithms described by prior work come at the cost of increased query latency, decreased recall, or prolonged deletion time. In this paper, we propose a new theoretical framework for graph-based ANN based on random walks. We then utilize this framework to analyze a randomized deletion approach that preserves hitting time statistics compared to the graph before deleting the point. We then turn this theoretical framework into a \emph{deterministic} deletion algorithm, and show that it provides better tradeoff between query latency, recall, deletion time, and memory usage through an extensive collection of experiments.

Exogenous MDPs (Exo-MDPs) capture sequential decision-making where uncertainty comes solely from exogenous inputs that evolve independently of the learner’s actions. This structure is especially common in operations research applications such as inventory control, energy storage, and resource allocation, where exogenous randomness (e.g., demand, arrivals, or prices) drives system behavior. Despite decades of empirical evidence that greedy, exploitation-only methods work remarkably well in these settings, theory has lagged behind: all existing regret guarantees for Exo-MDPs rely on explicit exploration or tabular assumptions. We show that exploration is unnecessary. We propose Pure Exploitation Learning ($\texttt{PEL}$) and prove the first general finite-sample regret bounds for exploitation-only algorithms in Exo-MDPs. In the tabular case, PEL achieves $\widetilde{O}(H^2|\Xi|\sqrt{K})$. For large, continuous endogenous state spaces, we introduce $\texttt{LSVI-PE}$, a simple linear-approximation method whose regret is polynomial in the feature dimension, exogenous state space, and horizon, independent of the endogenous state and action spaces. Our analysis introduces two new tools: counterfactual trajectories and Bellman-closed feature transport, which together allow greedy policies to have accurate value estimates without optimism. Experiments on synthetic and resource-management tasks show $\texttt{PEL}$ consistently outperforming baselines. Overall, our results overturn the conventional wisdom that exploration is required, demonstrating that in Exo-MDPs, pure exploitation is enough.

Classifier-free guidance (CFG) is a widely used technique for improving the perceptual quality of samples from conditional diffusion models. It operates by linearly combining conditional and unconditional score estimates using a *guidance weight* $\omega$. While a large, static weight can markedly improve visual results, this often comes at the cost of poorer distributional alignment. In order to better approximate the target conditional distribution, we instead learn *guidance weights* $\omega_{c,(s,t)}$, which are continuous functions of the conditioning $c$, the time $t$ from which we denoise, and the time $s$ towards which we denoise. We achieve this by minimizing the distributional mismatch between noised samples from the true conditional distribution and samples from the guided diffusion process. We extend our framework to reward guided sampling, enabling the model to target distributions tilted by a reward function $R(x_0,c)$, defined on clean data and a conditioning $c$. We demonstrate the effectiveness of our methodology on low-dimensional toy examples and high-dimensional image settings, where we observe improvements in Fréchet inception distance (FID) for image generation. In text-to-image applications, we observe that employing a reward function given by the CLIP score leads to guidance weights that improve image-prompt alignment.

Large Vision-Language Models (LVLMs) have made significant strides in the field of video understanding in recent times. Nevertheless, existing video benchmarks predominantly rely on text prompts for evaluation, which often require complex referential language and diminish both the accuracy and efficiency of human–model interaction in turn. To address this limitation, we propose V2P-Bench, a robust and comprehensive benchmark for evaluating the ability of LVLMs to understand Video Visual Prompts in human–model interaction scenarios. V2P-Bench consists of 980 videos and 1172 well-structured high-quality QA pairs, each paired with manually annotated visual prompt frames. The benchmark spans three main tasks and twelve categories, thereby enabling fine-grained, instance-level evaluation. Through an in-depth analysis of current LVLMs, we identify several key findings: 1) Visual prompts are both more model-friendly and user-friendly in interactive scenarios than text prompts, leading to significantly improved model performance and enhanced user experience. 2) Models are reasonably capable of zero-shot understanding of visual prompts, but struggle with spatiotemporal understanding. Even o1 achieves only 71.8%, far below the human expert score of 88.3%, while most open-source models perform below 60%. 3) LVLMs exhibit pervasive Hack Phenomena in video question answering tasks, which become more pronounced as video length increases and frame sampling density decreases, thereby inflating performance scores artificially. We anticipate that V2P-Bench will not only shed light on these challenges but also serve as a foundational tool for advancing human–model interaction and improving the evaluation of video understanding.

The ever-increasing computational demands of large language models (LLMs) make efficient inference a central challenge. While recent advances leverage specialized architectures or selective activation, they typically require (re)training or architectural modifications, limiting their broad applicability. Training-free sparse activation, in contrast, offers a plug-and-play pathway to efficiency; however, existing methods often rely solely on hidden state magnitudes, leading to significant approximation error and performance degradation. To address this, we introduce WINA (Weight-Informed Neuron Activation): a simple framework for training-free sparse activation that incorporates both hidden state magnitudes and weight matrix structure. By also leveraging the ℓ2-norm of the model’s weight matrices, WINA yields a principled sparsification strategy with provably optimal approximation error bounds, offering better and tighter theoretical guarantees than prior state-of-the-art approaches. Overall, WINA also empirically outperforms many previous training-free methods across diverse LLM architectures and datasets: not only matching or exceeding their accuracy at comparable sparsity levels, but also sustaining performance better at more extreme sparsity levels. Together, these results position WINA as a practical, theoretically grounded, and broadly deployable solution for efficient inference. Our source code is anonymously available at https://github.com/microsoft/wina.