Quadrupedal robots with manipulators offer strong mobility and adaptability for grasping in unstructured, dynamic environments through coordinated whole-body control. However, existing research has predominantly focused on static-object grasping, neglecting the challenges posed by dynamic targets and thus limiting applicability in dynamic scenarios such as logistics sorting and human–robot collaboration. To address this, we introduce DQ-Bench, a new benchmark that systematically evaluates dynamic grasping across varying object motions, velocities, heights, object types, and terrain complexities, along with comprehensive evaluation metrics. Building upon this benchmark, we propose DQ-Net, a compact teacher–student framework designed to infer grasp configurations from limited perceptual cues. During training, the teacher network leverages privileged information to holistically model both the static geometric properties and dynamic motion characteristics of the target, and integrates a grasp fusion module to deliver robust guidance for motion planning. Concurrently, we design a lightweight student network that performs dual-viewpoint temporal modeling using only the target mask, depth map, and proprioceptive state, enabling closed-loop action outputs without reliance on privileged data. Extensive experiments on DQ-Bench demonstrate that DQ-Net achieves robust dynamic objects grasping across multiple task settings, substantially outperforming baseline methods in both success rate and responsiveness. We will release our codebase and benchmark publicly.
论文检索
输入标题、作者或关键词，从 3,752 篇学术成果中精准定位
Task scheduling has become increasingly critical for embodied AI, where agents need to follow natural language instructions and execute actions efficiently in 3D physical worlds. Existing datasets for task planning in 3D environments often simplify the problem, lacking operations research knowledge for task scheduling and 3D grounding for real-world applications. In this work, we propose Operations Research Knowledge-based 3D Grounded Task Scheduling (OKS3D), a new task that requires synerization of language understanding, 3D grounding, and efficiency optimization for embodied agents. OKS3D reflects real-world demands by requiring agents to generate efficient, step-by-step schedules that are grounded in 3D space. To facilitate research on OKS3D, we construct a large-scale dataset called OKS3D-60K, comprising 60K tasks across 4K real-world scenes. Furthermore, we propose GRANT, an embodied multi-modal large language model equipped with a simple yet effective scheduling token mechanism to generate efficient task schedules and grounded actions. Extensive experiments on the OKS3D-60K dataset validate the effectiveness of GRANT across language understanding, 3D grounding, and scheduling efficiency.
Lightweight Adaptive Topological Layout and Semantic Mapping in Vision-and-Language Navigation on Websites
PDF ↗Vision-and-Language navigation on websites requires agents to navigate target webpages and answer questions based on human instructions. Current web agents primarily leverage Large Language Models (LLMs) for semantic understanding and reasoning, but still suffer from limited navigation performance and slow inference speed. Constructing a global map across webpages can effectively enhance both navigation accuracy and efficiency, however, this is challenged by the open structure of web navigation graphs and the dynamic nature of web layouts. In this paper, we propose ATLAS: Adaptive Topological Layout And Semantic mapping, a framework that adaptively constructs a time-varying, unbounded topological map across webpages and unifies heterogeneous elements through semantic representation. This enables both global path planning and local element selection for web-based navigation and question answering. As a lightweight approach, ATLAS significantly outperforms existing state-of-the-art methods on the WebVLN benchmark with a 10% improvement in success rate, and achieves the highest average task success rate on both the Mind2Web and WebArena benchmarks.
PhyPlan: Learning to Plan Tasks with Generalizable and Rapid Physical Reasoning for Embodied Manipulation
PDF ↗Given the task of landing a ball in a goal region beyond direct reach, humans can often throw, slide, or rebound objects against the wall to attain the goal. Enabling robots to replicate such reasoning is non-trivial as it requires multi-step planning and involves a mixture of discrete and continuous action spaces, a sparse and sensitive reward structure, computationally expensive simulations, and an incomplete understanding of the environment's physics. We present PhyPlan, a physics-informed and adaptable planning framework for efficient multi-step physical reasoning. At its core, PhyPlan comprises of Generative Flow Networks (GFlowNets) and Monte Carlo Tree Search (MCTS) to explore and evaluate sequences of object interactions. GFlowNets sample discrete action sequences in proportion to their associated reward, enabling broad and reward-driven exploration of the discrete planning space. MCTS complements this by adaptively balancing the use of a fast but approximate pre-trained physics-informed dynamics predictor and costly but accurate environment rollouts, ensuring both speed and precision in planning. The known and actual physics discrepancy is captured using Gaussian Process Regression. Experiments on benchmark simulated tasks requiring composition of collisions, slides, and rebounds demonstrate that PhyPlan achieves a 45\% higher success rate and up to 3× efficiency gains over state-of-the-art model-based reinforcement learning approaches.
Aerial Visual Object Search (AVOS) tasks in urban environments require Unmanned Aerial Vehicles (UAVs) to autonomously search for and identify target objects based on visual inputs without external guidance. Existing approaches struggle in complex urban environments due to redundant semantic processing, similar object ambiguity, and the exploration-exploitation dilemma. To advance research and support the AVOS task, we introduce CityAVOS, the first benchmark dataset for autonomous search of static urban objects. It features 2,420 tasks of varying difficulty across six object categories, designed to rigorously evaluate UAV search strategies. To solve the AVOS task, we also propose PRPSearcher (Perception-Reasoning-Planning Searcher), a novel agentic method powered by multi-modal large language models (MLLMs) that enables a UAV agent to think and reason like humans on visual cues when searching for objects. Specifically, PRPSearcher constructs three specialized maps: an object-centric dynamic semantic map enhancing spatial perception, a 3D cognitive map based on semantic "attraction" values for target reasoning, and a 3D uncertainty map for balanced exploration-exploitation search. Moreover, we propose a denoising mechanism to mitigate interference from similar objects and design an Inspiration Promote Thought prompting mechanism for adaptive action planning. Experimental results on CityAVOS demonstrate that PRPSearcher surpasses existing baselines in both success rate and search efficiency (on average: +37.69% SR, +28.96% SPL, -30.69% MSS, and -46.40% NE). Our work paves the way for future advances in embodied visual target search.
We present RENEW, a novel global path planning framework for Autonomous Surface Vehicle (ASV) operating in dynamic environments with external disturbances (e.g., water currents). These disturbances significantly affect both the risk and energy cost of navigation, particularly in constrained coastal waterways, by dynamically reshaping the navigable area. RENEW addresses this challenging scenario through a unified, risk- and energy-aware planning strategy that guarantees safety by explicitly identifying states at risk of entering non-navigable regions and enforcing adaptive safety constraints. Our planner incorporates a best-effort strategy under worst-case scenarios, inspired by contingency planning concepts from maritime domains, to ensure feasible control actions even under adverse conditions. RENEW employs a hierarchical architecture: a high-level planner explores topologically distinct paths via constrained triangulation, while a low-level planner selects an energy-efficient and kinematically feasible trajectory within a safe corridor. We validate our approach through extensive simulations using both custom realistic scenarios and real-world ocean current data. To our knowledge, this is the first global planning framework to jointly address the adaptive identification of non-navigable areas and topological diversity within a risk-aware paradigm, enabling robust navigation in maritime environments.
GraphCoT-VLA: A 3D Spatial-Aware Reasoning Vision-Language-Action Model for Robotic Manipulation with Ambiguous Instructions
PDF ↗Vision-language-action models have emerged as a crucial paradigm in robotic manipulation. However, existing VLA models exhibit notable limitations in handling ambiguous language instructions and unknown environmental states. Furthermore, their perception is largely constrained to static two-dimensional observations, lacking the capability to model three-dimensional interactions between the robot and its environment. To address these challenges, this paper proposes GraphCoT-VLA, an efficient end-to-end model. To enhance the model's ability to interpret ambiguous instructions and improve task planning, we design a structured Chain-of-Thought reasoning module that integrates high-level task understanding and planning, failed task feedback, and low-level imaginative reasoning about future object positions and robot actions. Additionally, we construct a real-time updatable 3D Pose-Object graph, which captures the spatial configuration of robot joints and the topological relationships between objects in 3D space, enabling the model to better understand and manipulate their interactions. We further integrates a dropout hybrid reasoning strategy to achieve efficient control outputs. Experimental results across multiple real-world robotic tasks demonstrate that GraphCoT-VLA significantly outperforms existing methods in terms of task success rate and response speed, exhibiting strong generalization and robustness in open environments and under uncertain instructions.
We introduce LOG-Nav, an efficient layout-aware object-goal navigation approach designed for complex multi-room indoor environments. By planning hierarchically leveraging a global topologigal map with layout information and local imperative approach with detailed scene representation memory, LOG-Nav achieves both efficient and effective navigation. The process is managed by an LLM-powered agent, ensuring seamless effective planning and navigation, without the need for human interaction, complex rewards, or costly training. Our experimental results on the MP3D benchmark achieves 85% object navigation success rate (SR) and 79% success rate weighted by path length (SPL) (over 40% point improvement in SR and 60% improvement in SPL compared to exsisting methods). Furthermore, we validate the robustness of our approach through virtual agent and real-world robotic deployment, showcasing its capability in practical scenarios.
Sequential-Horizon Vision-and-Language Navigation (SH-VLN) presents a challenging scenario where agents should sequentially execute multi-task trajectory navigation guided by complex, long-horizon natural language instructions. Current vision-and-language navigation models exhibit significant performance degradation with such instructions, as information overload impairs the agent's ability to attend to observationally relevant details. To address this problem, we propose SeqWalker, a novel navigation model built on a hierarchical planning framework. Our SeqWalker features: (1) A High-Level Planner that dynamically selects global instructions into contextually relevant sub-instructions based on the agent's current visual observations, thus reducing cognitive load; (2) A Low-Level Planner incorporating an Exploration-Verification strategy that leverages the inherent logical structure of instructions for trajectory error correction. To evaluate SH-VLN performance, we also extend the IVLN dataset and establish a new benchmark. Extensive experiments are performed to demonstrate the effectiveness and superiority of SeqWalker.
Diffusion policies have recently shown great promise for generating actions in robotic manipulation. However, existing approaches often rely on global instructions to produce short-term control signals, which can result in misalignment in action generation. We conjecture that the primitive skills, referred to as fine-grained, short-horizon manipulations, such as "move up" and "open the gripper", provide a more intuitive and effective interface for robot learning. To bridge this gap, we propose SDP, a skill-conditioned diffusion policy that integrates interpretable skill learning with conditional action planning. SDP abstracts eight reusable primitive skills across tasks and employs a vision-language model to extract discrete representations from visual observations and language instructions. Based on the representations, a lightweight router network is designed to assign a desired primitive skill for each state, which helps construct a single-skill policy to generate skill-aligned actions. By decomposing complex tasks into a sequence of primitive skills and selecting a single-skill policy, the proposed SDP ensures skill-consistent behavior across diverse tasks. Extensive experiments on two challenging simulation benchmarks and real-world robot deployments demonstrate that SDP consistently outperforms state-of-the-art methods, providing a new paradigm for skill-based robot learning with diffusion policies.
Scalable and generalizable analysis of brain activity is essential for advancing both clinical diagnostics and cognitive research. Electroencephalography (EEG), a non-invasive modality with high temporal resolution, has been widely used for brain states analysis. However, most exiting EEG models are usually tailored for single specific tasks, limiting their utility in realistic scenarios where EEG analysis often involves multi-task and continuous reasoning. In this work, we introduce EEG Agent, a general-purpose framework that leverages large language models (LLMs) to schedule and plan multiple tools to automatically complete EEG-related tasks. EEG Agent is capable of performing the key functions: EEG basic information perception, spatiotemporal EEG exploration, EEG event detection, interaction with users, and EEG report generation. To realize the capabilities, we design a toolbox composed of different tools for EEG preprocessing, feature extraction, event detection, etc. These capabilities were evaluated on public datasets, and our EEG Agent can support flexible and interpretable EEG analysis, highlighting its potential for real-world clinical applications.
Augmented Reality (AR) navigation has emerged as a transformative tool for spatial intelligence, enabling users to interactively explore complex environments through wearable and mobile AR devices. However, current AR navigation systems struggle with low indoor localization accuracy, weak semantic understanding, and limited long-term memory, which severely limits their adaptability in dynamic, multi-floor, and large-scale real-world settings. To address these challenges, we present AR-Nav benchmark, a novel dataset with corresponding suite that leverages vision and language for AR navigation. First, to construct this benchmark, we proposed an Augmented Reality Visual-Language Memory Model (AR‑VLM²), which generates structured, semantically rich, and temporally indexed representations for long-term AR navigation. Second, we design a lightweight navigation intent recommending module with hierarchical topological reasoning and language-grounded path planning, called ARN‑Pilot, enabling low-latency and personalized route selection. Third, we introduce a closed-loop AR interaction module that supports real-time multi-modal feedback, dynamic memory updates, and human-in-the-loop query refinement. Extensive experiments in indoor multi-floor and outdoor parking scenarios show that AR-Nav suite significantly outperforms state-of-the-art AR navigation methods.
Generating behaviors that align with human expectations is a key requirement for human-robot collaboration. Potential behavior misalignment could lead to the robot performing actions with unanticipated, potentially dangerous side effects even while pursuing human goals. In this paper, we introduce a novel metric called Goal State Divergence (GSD) which quantifies the difference between the state a robot achieved in response to a human-specified goal and what the human expected. In cases where GSD cannot be directly calculated, we show how it can be approximated using maximal and minimal bounds. We then leverage GSD in our novel human-robot goal alignment design (HRGAD) problem, which identifies a minimal set of environment modifications that can reduce such mismatches. We show the effectiveness of our method in reducing the goal state divergence by empirically evaluating our approach on several planning benchmarks.
Simulating Human-Like Counseling: A Path- and Scenario-Guided Framework for Psychological Support Dialogue
PDF ↗The growing demand for psychological support underscores the lack of high-quality counseling dialogue datasets, particularly in non-English contexts. We propose PGSim, a Path-Guided Simulation framework that mirrors real counseling processes—symptom description, problem identification, cause analysis, strategy planning, and iterative adjustment. PGSim models each user scenario as a fine-grained quadruple {Group, Psychological Problem, Problem Cause, Support Focus} and guides dialogue generation through expert-annotated strategy paths. Real counseling dialogues and expert-edited samples are used to fine-tune two language models: a Dialog Generator for strategy-aligned dialogue creation and a Dialog Modifier for expert-level refinement. After automated and human verification, we construct the Chinese Psychological support Dialogue Dataset (CPsDD), containing 68K dialogues across 13 groups, 16 problems, 13 causes, and 12 support focuses. We further present the Comprehensive Agent Dialogue Support System (CADSS), which integrates profiling, summarization, strategy planning, and empathetic response. Experiments on CPsDD and ESConv demonstrate that CADSS achieves state-of-the-art results on Strategy Prediction and Emotional Support Conversation tasks.
TRIPLE: Theory-Driven Integration of Planned and Habitual Behaviors for LLM-based Personalization
PDF ↗While large language model (LLM)-based user profiling offers significant potential for personalization, most existing approaches rely on empirical heuristics and lack grounding in the psychological mechanism that drive human behavior. In this paper, we introduce TRIPLE (Theory-guided Reasoning for Intent and habIt Profiling with LLMs for pErsonalization), a novel framework that systematically integrates dual-process theory from social psychology into LLM-based user modeling. TRIPLE (1) constructs a habitual behavior profile by identifying repeated patterns over time to model automatic responses; (2) builds an intentional behavior profile by inferring user attitudes, subjective norms and perceived behavioral control based on the Theory of Planned Behavior (TPB); and (3) generates behavioral rationale that reveal the interaction between habitual and intentional processes to predict user behavior in context-specific situations. We evaluate TRIPLE on five personalization tasks from the LaMP benchmark using multiple open-source LLMs. Results show that TRIPLE consistently outperforms existing in-context learning methods, with especially pronounced gains on complex generative tasks such as headline and title generation. Qualitative analyses further demonstrate that the profiles and reasoning paths generated by TRIPLE provide interpretable and psychologically grounded explanations of user behavior. These findings provide strong evidence that incorporating validated behavioral theories into LLM-based personalization enhances both predictive performance and interpretability, paving a way for theory-driven, socio-cognitively informed user modeling.
Pedestrian trajectory prediction is critical for ensuring safety in autonomous driving, surveillance systems, and urban planning applications. While early approaches primarily focus on one-hop pairwise relationships, recent studies attempt to capture high-order interactions by stacking multiple Graph Neural Network (GNN) layers. However, these approaches face a fundamental trade-off: insufficient layers may lead to under-reaching problems that limit the model's receptive field, while excessive depth can result in prohibitive computational costs. We argue that an effective model should be capable of adaptively modeling both explicit one-hop interactions and implicit high-order dependencies, rather than relying solely on architectural depth. To this end, we propose ViTE (Virtual graph Trajectory Expert router), a novel framework for pedestrian trajectory prediction. ViTE consists of two key modules: a Virtual Graph that introduces dynamic virtual nodes to model long-range and high-order interactions without deep GNN stacks, and an Expert Router that adaptively selects interaction experts based on social context using a Mixture-of-Experts design. This combination enables flexible and scalable reasoning across varying interaction patterns. Experiments on three benchmarks (ETH/UCY, NBA, and SDD) demonstrate that our method consistently achieves state-of-the-art performance, validating both its effectiveness and practical efficiency.
ESCA: An Emotional Support Conversation Agent for Enhancing Reasonable Strategy Planning and Effective Expression
PDF ↗Emotional Support Conversation (ESC) aims to alleviate individuals’ negative emotions through multi-turn dialogues, where effective strategy planning and response generation are essential. However, existing methods often suffer from limitations in both planning reasonable support strategies and effectively expressing them in responses. To the end, we propose a novel LLM-based Emotional Support Conversation Agent (ESCA) with a plug-in strategy planner and a strategy-aligned prompt generator. The strategy planner cooperates with four aspects of the seeker’s state, including emotion intensity, trust degree, dialogue behavior, and stage of change, to enhance the rationality and effectiveness of the strategy prediction. To ensure that predicted strategies are better conveyed, the prompt generator integrates strategy-aligned instructions, knowledge, and context to generate the soft prompt for guiding the LLM to generate supportive responses. In addition to supervised fine-tuning, the prompt generator is further optimized by reinforcement learning. Experimental results demonstrate that ESCA significantly improves both response quality and the success rate of achieving the ESC task goal.
Cake-cutting algorithms, which aim to fairly allocate a continuous resource based on individual agent preferences, have seen significant progress over the past two decades. Much of the research has concentrated on fairness, with comparatively less attention given to other important aspects. In 2010, Chen et al. introduced an algorithm that, in addition to ensuring fairness, was strategyproof---meaning agents had no incentive to misreport their valuations. However, even in the absence of strategic incentives to misreport, agents may still hesitate to reveal their true preferences due to privacy concerns (e.g., when allocating advertising time between firms, revealing preferences could inadvertently expose planned marketing strategies or product launch timelines). In this work, we extend the strategyproof algorithm of Chen et al. by introducing a privacy-preserving dimension. To the best of our knowledge, we present the first private cake-cutting protocol, and, in addition, this protocol is also envy-free and strategyproof. Our approach replaces the algorithm’s centralized computation with a novel adaptation of cryptographic techniques, enabling privacy without compromising fairness or strategyproofness. Thus, our protocol encourages agents to report their true preferences not only because they are not incentivized to lie, but also because they are protected from having their preferences exposed.
In citizens' assemblies, a group of constituents is randomly selected to weigh in on policy issues. We study a two-stage sampling problem faced by practitioners in countries such as Germany, in which constituents' contact information is stored at a municipal level. As a result, practitioners can only select constituents from a bounded number of cities ex post, while ensuring equal selection probability for constituents ex ante. We develop several algorithms for this problem. Although minimizing the number of contacted cities is NP-hard, we provide a pseudo-polynomial time algorithm and an additive 1-approximation, both based on separation oracles for a linear programming formulation. Recognizing that practical objectives go beyond minimizing city count, we further introduce a simple and more interpretable greedy algorithm, which additionally satisfies an ex-post monotonicity property and achieves an additive 2-approximation. Finally, we explore a notion of ex-post proportionality, for which we propose two practical algorithms: an optimal algorithm based on column generation and integer linear programming and a simple heuristic creating particularly transparent distributions. We evaluate these algorithms on data from Germany, and plan to deploy them in cooperation with a leading nonprofit organization in this space.
Time-inconsistent behavior, such as procrastination or abandonment of long-term goals, arises when agents evaluate immediate outcomes disproportionately higher than future ones. This leads to globally suboptimal behavior, where plans are frequently revised or abandoned entirely. In the influential model of Kleinberg and Oren (2014) such behavior is modeled by a present-biased agent navigating a task graph toward a goal, making locally optimal decisions at each step based on discounted future costs. As a result, the agent may repeatedly deviate from initially intended plans. Recent work by Belova et al. (2024) introduced a two-agent extension of this model, where a fully-aware principal attempts to guide the present-biased agent through a specific set of critical tasks without causing abandonment. This captures a rich class of principal–agent dynamics in behavioral settings. In this paper, we provide a comprehensive algorithmic characterization of this problem. We analyze its computational complexity through the framework of parameterized algorithms, focusing on graph parameters that naturally emerge in this setting, such as treewidth, vertex cover, and feedback vertex set. Our main result is a fixed-parameter tractable algorithm when parameterized by the treewidth of the task graph and the number of distinct (v,t)-path costs. Our algorithm encaptures several input settings, such as bounded edge costs and restricted task graph structure. We demonstrate that our main result yields efficient algorithms for a number of such configurations. We complement this with tight hardness results, that highlight the extreme difficulty of the problem even on simplest graphs with bounded number of nodes and constant parameter values, and motivate our choice of parameters. We delineate tractable and intractable regions of the problem landscape, which include answers to open questions of Belova et al. (2024).