论文检索

Applications · Robotics

Shuai Liu, Quanmin Liang, Zefeng Li, Boyang Li, Kai Huang

Multi-sensor fusion is crucial for improving the performance and robustness of end-to-end autonomous driving systems. Existing methods predominantly adopt either attention-based flatten fusion or bird’s eye view fusion through geometric transformations. However, these approaches often suffer from limited interpretability or dense computational overhead. In this paper, we introduce GaussianFusion, a Gaussian-based multi-sensor fusion framework for end-to-end autonomous driving. Our method employs intuitive and compact Gaussian representations as intermediate carriers to aggregate information from diverse sensors. Specifically, we initialize a set of 2D Gaussians uniformly across the driving scene, where each Gaussian is parameterized by physical attributes and equipped with explicit and implicit features. These Gaussians are progressively refined by integrating multi-modal features. The explicit features capture rich semantic and spatial information about the traffic scene, while the implicit features provide complementary cues beneficial for trajectory planning. To fully exploit rich spatial and semantic information in Gaussians, we design a cascade planning head that iteratively refines trajectory predictions through interactions with Gaussians. Extensive experiments on the NAVSIM and Bench2Drive benchmarks demonstrate the effectiveness and robustness of the proposed GaussianFusion framework. The source code is included in the supplementary material and will be released publicly.

Reinforcement Learning · Deep RL

Zizhao Wang, Kaixin Wang, Li Zhao, Peter Stone, Jiang Bian

World models aim to capture the dynamics of the environment, enabling agents to predict and plan for future states. In most scenarios of interest, the dynamics are highly centered on interactions among objects within the environment. This motivates the development of world models that operate on object-centric rather than monolithic representations, with the goal of more effectively capturing environment dynamics and enhancing compositional generalization. However, the development of object-centric world models has largely been explored in environments with limited visual complexity (such as basic geometries). It remains underexplored whether such models can be effective in more challenging settings. In this paper, we fill this gap by introducing Dyn-O, an enhanced structured world model built upon object-centric representations. Compared to prior work in object-centric representations, Dyn-O improves in both learning representations and modeling dynamics. On the challenging Procgen games, we demonstrate that our method can learn object-centric world models directly from pixel observations, outperforming DreamerV3 in rollout prediction accuracy. Furthermore, by decoupling object centric features into dynamic-agnostic and dynamic-aware components, we enable finer-grained manipulation of these features and generate more diverse imagined trajectories. The code of Dyn-O can be found at: https://github.com/wangzizhao/dyn-O.

Theory · Reinforcement Learning and Planning

Tong Yang, Bo Dai, Lin Xiao, Yuejie Chi

Online reinforcement learning (RL) with complex function approximations such as transformers and deep neural networks plays a significant role in the modern practice of artificial intelligence. Despite its popularity and importance, balancing the fundamental trade-off between exploration and exploitation remains a long-standing challenge; in particular, we are still in lack of efficient and practical schemes that are backed by theoretical performance guarantees. Motivated by recent developments in exploration via optimistic regularization, this paper provides an interpretation of the principle of optimism through the lens of primal-dual optimization. From this fresh perspective, we set forth a new value-incentivized actor-critic (VAC) method, which optimizes a single easy-to-optimize objective integrating exploration and exploitation --- it promotes state-action and policy estimates that are both consistent with collected data transitions and result in higher value functions. Theoretically, the proposed VAC method has near-optimal regret guarantees under linear Markov decision processes (MDPs) in both finite-horizon and infinite-horizon settings, which can be extended to the general function approximation setting under appropriate assumptions.

Leheng Sheng, An Zhang, Zijian Wu, Weixiang Zhao, Changshuo Shen, zhang yi, Xiang Wang, Tat-Seng Chua

Recent studies empirically reveal that large reasoning models (LRMs) can automatically allocate more reasoning strengths (\ie the number of reasoning tokens) for harder problems, exhibiting difficulty-awareness for better task performance. While this automatic reasoning strength allocation phenomenon has been widely observed, its underlying mechanism remains largely unexplored. To this end, we provide explanations for this phenomenon from the perspective of model activations. \textbf{We find evidence that LRMs pre-plan the reasoning strengths in their activations even before generation, with this reasoning strength causally controlled by the magnitude of a pre-allocated directional vector.} Specifically, we show that the number of reasoning tokens is predictable solely based on the question activations using linear probes, indicating that LRMs estimate the required reasoning strength in advance. We then uncover that LRMs encode this reasoning strength through a pre-allocated directional vector embedded in the activations of the model, where the vector’s magnitude modulates the reasoning strength. Subtracting this vector can lead to reduced reasoning token number and performance, while adding this vector can lead to increased reasoning token number and even improved performance. We further reveal that this direction vector consistently yields positive reasoning length prediction, and it modifies the logits of end-of-reasoning token \texttt{} to affect the reasoning length. Finally, we demonstrate two potential applications of our findings: overthinking behavior detection and enabling efficient reasoning on simple problems. Our work provides new insights into the internal mechanisms of reasoning in LRMs and offers practical tools for controlling their reasoning behaviors. Our code is available at \url{https://anonymous.4open.science/r/LRM-plans-CoT-7E04}.

Theory · Reinforcement Learning and Planning

Michael Harding, Kirthevasan Kandasamy

We consider the problem of identifying the best arm in a multi-armed bandit model. Despite a wealth of literature in the traditional fixed budget and fixed confidence regimes of the best arm identification problem, it still remains a mystery to most practitioners as to how to choose an approach and corresponding budget or confidence parameter. We propose a new formalism to avoid this dilemma altogether by minimizing a risk functional which explicitly balances the performance of the recommended arm and the cost incurred by learning this arm. In this framework, a cost is incurred for each observation during the sampling phase, and upon recommending an arm, a performance penalty is incurred for identifying a suboptimal arm. The learner's goal is to minimize the sum of the penalty and cost. This new regime mirrors the priorities of many practitioners, e.g. maximizing profit in an A/B testing framework, better than classical fixed budget or confidence settings. We derive theoretical lower bounds for the risk of each of two choices for the performance penalty, the probability of misidentification and the simple regret, and propose an algorithm called DBCARE to match these lower bounds up to polylog factors on nearly all problem instances. We then demonstrate the performance of DBCARE on a number of simulated models, comparing to fixed budget and confidence algorithms to show the shortfalls of existing BAI paradigms on this problem.

Deep Learning · Graph Neural Networks

Sonia Mazelet, Rémi Flamary, Bertrand Thirion

Optimal transport between graphs, based on Gromov-Wasserstein and other extensions, is a powerful tool for comparing and aligning graph structures. However, solving the associated non-convex optimization problems is computationally expensive, which limits the scalability of these methods to large graphs. In this work, we present Unbalanced Learning of Optimal Transport (ULOT), a deep learning method that predicts optimal transport plans between two graphs. Our method is trained by minimizing the fused unbalanced Gromov-Wasserstein (FUGW) loss. We propose a novel neural architecture with cross-attention that is conditioned on the FUGW tradeoff hyperparameters. We evaluate ULOT on synthetic stochastic block model (SBM) graphs and on real cortical surface data obtained from fMRI. ULOT predicts transport plans with competitive loss up to two orders of magnitude faster than classical solvers. Furthermore, the predicted plan can be used as a warm start for classical solvers to accelerate their convergence. Finally, the predicted transport plan is fully differentiable with respect to the graph inputs and FUGW hyperparameters, enabling the optimization of functionals of the ULOT plan.

Theory · Reinforcement Learning and Planning

Tim van Erven, Jack Mayo, Julia Olkhovskaya, Chen-Yu Wei

We present an efficient algorithm for linear contextual bandits with adversarial losses and stochastic action sets. Our approach reduces this setting to misspecification-robust adversarial linear bandits with fixed action sets. Without knowledge of the context distribution or access to a context simulator, the algorithm achieves $\tilde{O}(\min\{d^2\sqrt{T}, \sqrt{d^3T\log K}\})$ regret and runs in $\mathrm{poly}(d,C,T)$ time, where $d$ is the feature dimension, $C$ is an upper bound on the number of linear constraints defining the action set in each round, $K$ is an upper bound on the number of actions in each round, and $T$ is number of rounds. This resolves the open question by Liu et al. (2023) on whether one can obtain $\mathrm{poly}(d)\sqrt{T}$ regret in polynomial time independent of the number of actions. For the important class of combinatorial bandits with adversarial losses and stochastic action sets where the action sets can be described by a polynomial number of linear constraints, our algorithm is the first to achieve $\mathrm{poly}(d)\sqrt{T}$ regret in polynomial time, while no prior algorithm achieves even $o(T)$ regret in polynomial time to our knowledge. When a simulator is available, the regret bound can be improved to $\tilde{O}(d\sqrt{L^\star})$, where $L^\star$ is the cumulative loss of the best policy.

Qianlan Yang, XJ Wang, Danielle Perszyk, Yu-Xiong Wang

Foundation models have recently shown strong potential as web agents, capable of interpreting high-level instructions and interacting with complex web interfaces. However, existing training paradigms for these agents often rely on predefined task datasets and curated demonstrations, limiting their scalability, adaptability, and capacity for self-improvement. In this work, we introduce *Self-guided hierArchical exploration for Generalist wEb agents* (SAGE), a new training framework designed to support autonomous skill acquisition through self-guided hierarchical exploration. Our method introduces a three-tier exploration strategy: a pre-exploration phase to build structural understanding of web environments, a top-level exploration strategy to generate a self-evolving curriculum of tasks from easy to hard, and a low-level exploration mechanism that combines planning-based rollouts with step-wise learning to improve policy efficiency. Together, these components form a scalable, supervision-free framework for web agent training. Experimental results on WebVoyager and WebArena demonstrate that our method significantly outperforms prior approaches, enabling foundation model agents to learn complex web tasks with greater generalization and robustness.

Reinforcement Learning · Multi-agent

Xiaokang Ye, Jiawei Ren, Yan Zhuang, Xuhong He, Yiming Liang, Yiqing Yang, Mrinaal Dogra, Xianrui Zhong, Eric Liu, Kevin Benavente 等

While LLM/VLM-powered AI agents have advanced rapidly in math, coding, and computer use, their applications in complex physical and social environments remain challenging. Building agents that can survive and thrive in the real world (e.g., by autonomously earning income) requires massive-scale interaction, reasoning, training, and evaluation across diverse scenarios. However, existing world simulators for such development fall short: they often rely on limited hand-crafted environments, simulate simplified game-like physics and social rules, and lack native support for LLM/VLM agents. We introduce SimWorld, a new simulator built on Unreal Engine 5, designed for developing and evaluating LLM/VLM agents in rich, real-world-like settings. SimWorld offers three core capabilities: (1) realistic, open-ended world simulation, including accurate physical and social dynamics and language-driven procedural environment generation; (2) rich interface for LLM/VLM agents, with multi-modal world inputs/feedback and open-vocabulary action outputs at varying levels of abstraction; and (3) diverse physical and social reasoning scenarios that are easily customizable by users. We demonstrate SimWorld by deploying frontier LLM agents (e.g., Gemini-2.5-Flash, Claude-3.5, GPT-4o, and DeepSeek-Prover-V2) on both short-horizon navigation tasks requiring grounded re-planning, and long-horizon multi-agent food delivery tasks involving strategic cooperation and competition. The results reveal distinct reasoning patterns and limitations across models. We open-source SimWorld and hope it becomes a foundational platform for advancing real-world agent intelligence across disciplines. Please refer to the project website for the most up-to-date information: http://simworld.org/.

Applications · Chemistry and Drug Discovery

Wei Liu, Jiangtao Feng, Hongli Yu, Yuxuan Song, Yuqiang Li, Shufei Zhang, LEI BAI, Wei-Ying Ma, Hao Zhou

Retrosynthetic planning is a fundamental task in chemical discovery. Due to the vast combinatorial search space, identifying viable synthetic routes remains a significant challenge--even for expert chemists. Recent advances in Large Language Models (LLMs), particularly equipped with reinforcement learning, have demonstrated strong human-like reasoning and planning abilities, especially in mathematics and code problem solving. This raises a natural question: Can the reasoning capabilities of LLMs be harnessed to develop an AI chemist capable of learning effective policies for multi-step retrosynthesis? In this study, we introduce Retro-R1, a novel LLM-based retrosynthesis agent trained via reinforcement learning to design molecular synthesis pathways. Unlike prior approaches, which typically rely on single-turn, question-answering formats, Retro-R1 interacts dynamically with plug-in single-step retrosynthesis tools and learns from environmental feedback. Experimental results show that Retro-R1 achieves a 55.79\% pass@1 success rate, surpassing the previous state of the art by 8.95\%. Notably, Retro-R1 demonstrates strong generalization to out-of-domain test cases, where existing methods tend to fail despite their high in-domain performance. Our work marks a significant step toward equipping LLMs with advanced, chemist-like reasoning abilities, highlighting the promise of reinforcement learning for enabling data-efficient, generalizable, and sophisticated scientific problem-solving in LLM-based agents.

Theory · Reinforcement Learning and Planning

Sajad Khodadadian, Martin Zubeldia

Polyak–Ruppert averaging is a widely used technique to achieve the optimal asymptotic variance of stochastic approximation (SA) algorithms, yet its high-probability performance guarantees remain underexplored in general settings. In this paper, we present a general framework for establishing non-asymptotic concentration bounds for the error of averaged SA iterates. Our approach assumes access to individual concentration bounds for the unaveraged iterates and yields a sharp bound on the averaged iterates. We also construct an example, showing the tightness of our result up to constant multiplicative factors. As direct applications, we derive tight concentration bounds for contractive SA algorithms and for algorithms such as temporal difference learning and $Q$-learning with averaging, obtaining new bounds in settings where traditional analysis is challenging.

Reinforcement Learning · Everything Else

Rajesh Mangannavar, Stefan Lee, Alan Fern, Prasad Tadepalli

We propose a novel approach to learn relational policies for classical planning based on learning to rank actions. We introduce a new graph representation that explicitly captures action information and propose a Graph Neural Network (GNN) architecture augmented with Gated Recurrent Units (GRUs) to learn action rankings. Unlike value-function based approaches that must learn a globally consistent function, our action ranking method only needs to learn locally consistent ranking. Our model is trained on data generated from small problem instances that are easily solved by planners and is applied to significantly larger instances where planning is computationally prohibitive. Experimental results across standard planning benchmarks demonstrate that our action-ranking approach not only achieves better generalization to larger problems than those used in training but also outperforms multiple baselines (value function and action ranking) methods in terms of success rate and plan quality.

Applications · Robotics

Wenyao Zhang, Hongsi Liu, Zekun Qi, Yunnan Wang, XinQiang Yu, Jiazhao Zhang, Runpei Dong, Jiawei He, He Wang, Zhizheng Zhang 等

Recent advances in vision-language-action (VLA) models have shown promise in integrating image generation with action prediction to improve generalization and reasoning in robot manipulation. However, existing methods are limited to challenging image-based forecasting, which suffers from redundant information and lacks comprehensive and critical world knowledge, including geometry, semantics and spatial information. To address these limitations, we propose DreamVLA, a novel VLA framework that integrates comprehensive world knowledge forecasting to enable inverse dynamics modeling, thereby establishing an action-forecasting loop for manipulation tasks. Specifically, DreamVLA introduces a dynamic-region-guided world knowledge prediction mechanism, which anticipates visual, depth, geometric, semantic, and segmentation cues to provide compact yet comprehensive representations for action planning. This design aligns with how humans interact with the world by first forming abstract multimodal reasoning chains before acting. Moreover, to model the conditional distribution over future actions, we employ a diffusion-based transformer that disentangles action representations from shared latent features and better captures multimodal uncertainty. Extensive experiments on both real-world and simulation environments demonstrate that DreamVLA achieves 76.7% success rate on real robot tasks and 4.45 average length on the CALVIN ABC-D benchmarks.

Theory · Reinforcement Learning and Planning

Feng Zhu, David Simchi-Levi

Thompson Sampling (TS) has emerged as a powerful algorithm for sequential decision-making, with strong empirical success and theoretical guarantees. However, it has been shown that its behavior under stringent safety and robustness criteria --- such as safety of cumulative regret distribution and robustness to model mis-specification --- can sometimes perform poorly. In this work, we try to address these aspects through the lens of adaptive variance inflation for Gaussian Thompson Sampling. Our one-line change introduces a time- and arm-dependent inflation factor into the sampling variance, and yields several compelling benefits. The resulting policy achieves provably worst-case optimal expected regret and worst-case optimal fast-decaying regret tail bounds, even in the presence of heavy-tailed (sub-exponential) noise or mis-specified environments. The policy is also robust to mis-specified noise variances. Beyond cumulative regret, we further demonstrate that our method ensures strong post-experiment guarantees: simple regret and estimation error per arm exhibit fast-decaying tail probabilities, contributing to more reliable and robust downstream decisions. Finally, we extend our policy to incorporate settings with unknown arm-specific variances and empirically validate the consistent performance of our approach across a range of environments.

Computer Vision · Everything Else

Xingjian Ran, Yixuan Li, Linning Xu, Mulin Yu, Bo Dai

Realistic 3D indoor scene synthesis is vital for embodied AI and digital content creation. It can be naturally divided into two subtasks: object generation and layout generation. While recent generative models have significantly advanced object-level quality and controllability, layout generation remains challenging due to limited datasets. Existing methods either overfit to these datasets or rely on predefined constraints to optimize numerical layout that sacrifice flexibility. As a result, they fail to generate scenes that are both open-vocabulary and aligned with fine-grained user instructions. We introduce DirectLayout, a framework that directly generates numerical 3D layouts from text descriptions using generalizable spatial reasoning of large language models (LLMs). DirectLayout decomposes the generation into three stages: producing a Bird's-Eye View (BEV) layout, lifting it into 3D space, and refining object placements. To enable explicit spatial reasoning and help the model grasp basic principles of object placement, we employ Chain-of-Thought (CoT) Activation based on the 3D-Front dataset. Additionally, we design CoT-Grounded Generative Layout Reward to enhance generalization and spatial planning. During inference, DirectLayout addresses asset-layout mismatches via Iterative Asset-Layout Alignment through in-context learning. Extensive experiments demonstrate that DirectLayout achieves impressive semantic consistency, generalization and physical plausibility.

Theory · Reinforcement Learning and Planning

Yash Jhaveri, Harley Wiltzer, Patrick Shafto, Marc Bellemare, David Meger

In the pursuit of finding an optimal policy, reinforcement learning (RL) methods generally ignore the properties of learned policies apart from their expected return. Thus, even when successful, it is difficult to characterize which policies will be learned and what they will do. In this work, we present a theoretical framework for policy optimization that guarantees convergence to a particular optimal policy, via vanishing entropy regularization and a *temperature decoupling gambit*. Our approach realizes an interpretable, diversity-preserving optimal policy as the regularization temperature vanishes and ensures the convergence of policy derived objects--value functions and return distributions. In a particular instance of our method, for example, the realized policy samples all optimal actions uniformly. Leveraging our temperature decoupling gambit, we present an algorithm that estimates, to arbitrary accuracy, the return distribution associated to its interpretable, diversity-preserving optimal policy.

Applications · Neuroscience, Cognitive Science

Po-Chen Kuo, Han Hou, Will Dabney, Edgar Walker

Learning a compact representation of history is critical for planning and generalization in partially observable environments. While meta-reinforcement learning (RL) agents can attain near Bayes-optimal policies, they often fail to learn the compact, interpretable Bayes-optimal belief states. This representational inefficiency potentially limits the agent's adaptability and generalization capacity. Inspired by predictive coding in neuroscience---which suggests that the brain predicts sensory inputs as a neural implementation of Bayesian inference---and by auxiliary predictive objectives in deep RL, we investigate whether integrating self-supervised predictive coding modules into meta-RL can facilitate learning of Bayes-optimal representations. Through state machine simulation, we show that meta-RL with predictive modules consistently generates more interpretable representations that better approximate Bayes-optimal belief states compared to conventional meta-RL across a wide variety of tasks, even when both achieve optimal policies. In challenging tasks requiring active information seeking, only meta-RL with predictive modules successfully learns optimal representations and policies, whereas conventional meta-RL struggles with inadequate representation learning. Finally, we demonstrate that better representation learning leads to improved generalization. Our results strongly suggest the role of predictive learning as a guiding principle for effective representation learning in agents navigating partial observability.

Deep Learning · Robustness

Xiang Li, Yong Tao, Siyuan Zhang, Siwei Liu, Zhitong Xiong, Chunbo Luo, Lu Liu, Mykola Pechenizkiy, Xiaoxiang Zhu, Tianjin Huang

Earth observation foundation models have shown strong generalization across multiple Earth observation tasks, but their robustness under real-world perturbations remains underexplored. To bridge this gap, we introduce REOBench, the first comprehensive benchmark for evaluating the robustness of Earth observation foundation models across six tasks and twelve types of image corruptions, including both appearance-based and geometric perturbations. To ensure realistic and fine-grained evaluation, our benchmark focuses on high-resolution optical remote sensing images, which are widely used in critical applications such as urban planning and disaster response. We conduct a systematic evaluation of a broad range of models trained using masked image modeling, contrastive learning, and vision-language pre-training paradigms. Our results reveal that (1) existing Earth observation foundation models experience significant performance degradation when exposed to input corruptions. (2) The severity of degradation varies across tasks, model architectures, backbone sizes, and types of corruption, with performance drop varying from less than 1% to over 25%. (3) Vision-language models show enhanced robustness, particularly in multimodal tasks. REOBench underscores the vulnerability of current Earth observation foundation models to real-world corruptions and provides actionable insights for developing more robust and reliable models.

Reinforcement Learning · Deep RL

Jiayu Wang, Yifei Ming, Zixuan Ke, Caiming Xiong, Shafiq Joty, Aws Albarghouthi, Frederic Sala

Reinforcement learning (RL) has become the dominant paradigm for improving the performance of language models on complex reasoning tasks. Despite the substantial empirical gains demonstrated by RL-based training methods like GRPO, a granular understanding of why and how RL enhances performance is still lacking. To bridge this gap, we introduce SPARKLE, a fine-grained analytic framework to dissect the effects of RL across three key dimensions: (1) plan following and execution, (2) knowledge integration, and (3) chain of subproblems. Using this framework, we gain insights beyond mere accuracy. For instance, providing models with explicit human-crafted, step-by-step plans can surprisingly degrade performance on the most challenging benchmarks, yet RL-tuned models exhibit greater robustness, experiencing markedly smaller performance drops than base or SFT models. This suggests that RL may not primarily enhance the execution of external plans but rather empower models to formulate and follow internal strategies better suited to their reasoning processes. Conversely, we observe that RL enhances models' ability to integrate provided knowledge into their reasoning process, yielding consistent gains across diverse tasks. Finally, we study whether difficult problems---those yielding no RL signals and mixed-quality reasoning traces---can still be effectively used for training. We introduce SparkleRL-PSS, a multi-stage RL pipeline that reuses hard problems with partial step scaffolding, guiding exploration effectively without additional data generation. Together, our findings provide a principled foundation for understanding how RL shapes model behavior, offering practical insights for building more adaptive, data-efficient, and interpretable RL pipelines for reasoning tasks. Our code, data, and checkpoints are available at: https://sparkle-reasoning.github.io/.

Computer Vision · Image and Video Generation

Bozhou Zhang, Nan Song, jingyu li, Xiatian Zhu, Jiankang Deng, Li Zhang

End-to-end autonomous driving methods aim to directly map raw sensor inputs to future driving actions such as planned trajectories, bypassing traditional modular pipelines. While these approaches have shown promise, they often operate under a one-shot paradigm that relies heavily on the current scene context, potentially underestimating the importance of scene dynamics and their temporal evolution. This limitation restricts the model’s ability to make informed and adaptive decisions in complex driving scenarios. We propose a new perspective: the future trajectory of an autonomous vehicle is closely intertwined with the evolving dynamics of its environment, and conversely, the vehicle’s own future states can influence how the surrounding scene unfolds. Motivated by this bidirectional relationship, we introduce **SeerDrive**, a novel end-to-end framework that jointly models future scene evolution and trajectory planning in a closed-loop manner. Our method first predicts future bird’s-eye view (BEV) representations to anticipate the dynamics of the surrounding scene, then leverages this foresight to generate future-context-aware trajectories. Two key components enable this: (1) future-aware planning, which injects predicted BEV features into the trajectory planner, and (2) iterative scene modeling and vehicle planning, which refines both future scene prediction and trajectory generation through collaborative optimization. Extensive experiments on the NAVSIM and nuScenes benchmarks show that SeerDrive significantly outperforms existing state-of-the-art methods.