Intensity-modulated radiation therapy (IMRT) is a crucial radiotherapy technique, which is often formulated as an optimization problem. However, when the constraints are too restrictive to provide a feasible solution, human planners resort to relaxing the optimization parameters and re-evaluating the problem until an acceptable solution is obtained. However, this process is laborious and time-consuming, which has prompted attempts to automate radiotherapy through inverse planning studies using reinforcement learning. Unfortunately, these studies face two major limitations. First, a separate sub-network must be designed for each organ, rendering it difficult to apply to patients with an inconsistent number of structures. Second, the low signal-to-noise input and discrete action space result in low training efficiency. To address these issues, we propose an organ-sharing network that contains a functional embedding layer to extract curve features of the dose-volume histogram. It outputs continuous actions that can adjust the optimization parameters, thereby automating the radiotherapy planning process. The results from a cervical cancer dataset demonstrate the feasibility and efficiency of the proposed model in real-world radiotherapy. The code is available on https://github.com/Cissise/FatPIN.
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
Survey data are common and invaluable in social science research for understanding population processes and supporting policymaking and planning. Depending on the nature and scale, survey data sharing comes with privacy risks, and data collectors and agencies are constrained by disclosure permissions, limiting usage across research groups and institutes. Previous methods for synthetic data generation and deidentification may not entirely prevent information disclosures, or they may sacrifice data quality and granularity. Using a large-scale national voter file at both national and state levels, this paper introduces an end-to-end pipeline to streamline synthetic data generation and evaluation for survey researchers. This study selects four generative approaches based on different statistical assumptions: the regression-based Synthpop, the generative deep learning-based CTGAN and TVAE, and the large language model-based REaLDTabFormer, and compares them to the baseline synthetic minority oversampling technique (SMOTE). We consider three key dimensions of evaluation (utility, fidelity, and privacy) to highlight the strengths and weaknesses of each approach, and systematically evaluate across various datasets and training sizes. The results reveal that Synthpop is optimized for general utility (i.e., fidelity), while TVAE excels in downstream applications (i.e., target-specific utility) but compromises on general utility and potentially risks data overfitting. REaLDTabFormer demonstrates a balanced performance in both general and target-specific utility, whereas CTGAN offers the best privacy protection. We recommend that future researchers select a generative method by considering the trade-offs between performance across various evaluation dimensions, training size, data type, and computational infrastructure.
In online advertising, advertisers commonly utilize auto-bidding services to bid for impression opportunities. A typical objective of the auto-bidder is to optimize the advertiser's cumulative value of winning impressions within specified budget constraints. However, such a problem is challenging due to the complex bidding environment faced by diverse advertisers. To address this challenge, we introduce ABPlanner, a few-shot adaptable budget planner designed to improve budget-constrained auto-bidding. ABPlanner is based on a hierarchical bidding framework that decomposes the bidding process into shorter, manageable stages. Within this framework, ABPlanner allocates the budget across all stages, allowing a low-level auto-bidder to bids based on the budget allocation plan. The adaptability of ABPlanner is achieved through a sequential decision-making approach, inspired by in-context reinforcement learning. For each advertiser, ABPlanner adjusts the budget allocation plan episode by episode, using data from previous episodes as prompt for current decisions. This enables ABPlanner to quickly adapt to different advertisers with few-shot data, providing a sample-efficient solution. Extensive simulation experiments and real-world A/B testing validate the effectiveness of ABPlanner, demonstrating its capability to enhance the cumulative value achieved by auto-bidders.
Spatial tensors have been extensively used in a wide range of applications, including remote sensing, geospatial information systems, conservation planning, and urban planning. We study the problem of Spatially Compact Dense (SCD) block mining in a spatial tensor, which targets for discovering dense blocks that cover small spatial regions. However, most of existing dense block mining (DBM) algorithms cannot solve the SCD-block mining problem since they only focus on maximizing the density of candidate blocks, so that the discovered blocks are spatially loose, i.e., covering large spatial regions. Therefore, we first formulate the problem of mining top-k Spatially Compact Dense blocks (SCD-blocks) in spatial tensors, which ranks SCD-blocks based on a new scoring function that takes both the density value and the spatial coverage into account. Then, we adopt a filter-refinement framework that first generates candidate SCD-blocks with good scores in the filtering phase and then uses the traditional DBM algorithm to further maximize the density values of the candidates in the refinement phase. Due to the NP-hardness of the problem, we develop two types of solutions in the filtering phase, namely the top-down solution and the bottom-up solution, which can find good candidate SCD-blocks by approximately solving the new scoring function. The evaluations on four real datasets verify that compared with the dense blocks returned by existing DBM algorithms, the proposed solutions are able to find SCD-blocks with comparable density values and significantly smaller spatial coverage.
Recent learning-to-imitation methods have shown promise in planning by imitating within the observation-action space, yet they remain constrained in open environments, especially for long-horizon tasks. In contrast, while traditional symbolic planning excels in such tasks through logical reasoning over human-defined symbolic spaces, it struggles with high-dimensional visual inputs encountered in real-world scenarios. In this work, we draw inspiration from abductive learning and introduce a novel framework ABductive Imitation Learning (ABIL) that integrates the benefits of data-driven learning and symbolic-based reasoning, enabling long-horizon planning. Specifically, we employ abductive reasoning to understand the demonstrations in symbolic space and design the principles of sequential consistency to resolve the conflicts between perception and reasoning. ABIL generates predicate candidates to facilitate the perception from raw observations to symbolic space without laborious predicate annotations, providing a groundwork for symbolic planning. With the symbolic understanding, we develop a policy ensemble with base policies designed around different logical objectives, managed through symbolic reasoning. Experiments demonstrate that our method successfully comprehends observations with task-relevant symbolics to aid imitation learning. Importantly, ABIL demonstrates improved data efficiency and generalization across various long-horizon tasks, highlighting it as a promising solution for long-horizon planning. Project website: https://www.lamda.nju.edu.cn/shaojj/KDD25_ABIL/.
Large Language Model (LLM) based agents have garnered significant attention and are becoming increasingly popular. Furthermore, planning ability is a crucial component of an LLM-based agent, involving interaction with the environment and executing actions to complete a planning task, which generally entails achieving a desired goal from an initial state. This paper investigates enhancing the planning abilities of LLM-based agents through instruction tuning, referred to as agent training. Recent studies on agent training have demonstrated that utilizing expert-level trajectory data (sequences of action-observation pairs) for instruction-tuning LLMs effectively enhances their planning capabilities. However, existing work primarily focuses on synthesizing trajectories from manually designed planning tasks and environments. The labor-intensive nature of creating these environments and tasks impedes the generation of sufficiently varied and extensive trajectories for agent training. To address this limitation, this paper explores the automated synthesis of diverse environments and a gradual range of planning tasks, from easy to difficult. We introduce a framework, AgentGen, that leverages LLMs first to generate environments and subsequently generate planning tasks conditioned on these environments. Specifically, to improve environmental diversity, we propose using an inspiration corpus composed of various domain-specific text segments as the context for synthesizing environments. Moreover, to increase the difficulty diversity of generated planning tasks, we propose a bidirectional evolution method, Bi-Evol, that evolves planning tasks from easier and harder directions to synthesize a task set with a smoother difficulty curve, thereby enhancing the learning process of LLMs more effectively. These methods collectively contribute to the generation of diverse trajectory data for instruction-tuning. Based on AgentGen, we greatly expanded the number of environments and planning tasks available for agent training. The evaluation results from AgentBoard indicate that AgentGen greatly enhances the planning capabilities of LLMs. For instance, the AgentGen instruction-tuned Llama-3.1-8B outperforms GPT-3.5 in overall performance. Moreover, the AgentGen-tuned Llama-3.1-70B model achieves state-of-the-art results in planning tasks. Project page: https://agent-gen.github.io/.
Road traffic forecasting is crucial in real-world intelligent transportation scenarios like traffic dispatching and path planning in city management and personal traveling. Spatio-temporal graph neural networks (STGNNs) stand out as the mainstream solution in this task. Nevertheless, the quadratic complexity of remarkable dynamic spatial modeling-based STGNNs has become the bottleneck over large-scale traffic data. From the spatial data management perspective, we present a novel Transformer framework called PatchSTG to efficiently and dynamically model spatial dependencies for large-scale traffic forecasting with interpretability and fidelity. Specifically, we design a novel irregular spatial patching to reduce the number of points involved in the dynamic calculation of Transformer. The irregular spatial patching first utilizes the leaf K-dimensional tree (KDTree) to recursively partition irregularly distributed traffic points into leaf nodes with a small capacity, and then merges leaf nodes belonging to the same subtree into occupancy-equaled and non-overlapped patches through padding and backtracking. Based on the patched data, depth and breadth attention are used interchangeably in the encoder to dynamically learn local and global spatial knowledge from points in a patch and points with the same index of patches. Experimental results on four real world large-scale traffic datasets show that our PatchSTG achieves train speed and memory utilization improvements up to 10x and 4x with the state-of-the-art performance.
Unmanned Aerial Vehicles (UAVs) and Automated Guided Vehicles (AGVs) increasingly collaborate in logistics, surveillance, inspection tasks and etc. However, existing simulators often focus on a single domain, limiting cross-domain study. This paper presents the SkyRover, a modular simulator for UAV-AGV multi-agent pathfinding (MAPF). SkyRover supports realistic agent dynamics, configurable 3D environments, and convenient APIs for external solvers and learning methods. By unifying ground and aerial operations, it facilitates cross-domain algorithm design, testing, and benchmarking. Experiments highlight SkyRover’s capacity for efficient pathfinding and high-fidelity simulations in UAV-AGV coordination. We believe the SkyRover fills a key gap in MAPF research. Project is available at https://sites.google.com/view/mapf3d/home.
We formulate a Coverage Path Planning (CPP) problem for a helicopter or a UAV tasked with mapping ground-level radiation while avoiding radiation that is too strong. We introduce a simulation environment that incorporates digital elevation models, altitude-dependent measurement footprints and realistic flight constraints, as well as state-of-the-art radiation scenario simulations, such as nuclear explosions, provided by the German Federal Office for Radiation Protection. We highlight the complexity of radiological survey missions and demonstrate the necessity for new CPP approaches that address these unique challenges. The code to our simulation environment can be found under https://github.com/JohannBlake/Aerial-Coverage-Path-Planning-in-Nuclear-Emergencies.
In this demonstration, we present a system that automates regression testing for video games using automated planning techniques. Traditional test scripts are a common method for testing both video games and software in general. While effective, they require manual creation and frequent updates throughout development, making the process labor-intensive. Our system eliminates this burden by automatically generating and maintaining test scripts. The test engineer only needs to define the game’s rules using the Planning Domain Definition Language (PDDL) and specify initial states and goals for individual test cases. This significantly reduces human effort while ensuring test scripts remain up to date. Additionally, our system integrates with game engine editors—supporting both Unity and Unreal to execute and evaluate test cases directly within the game. It collects detailed logs, telemetry data, and video recordings, allowing users to review test results efficiently.
Here I summarise some results from my thesis which are relevant to artificial intelligence (AI) and machine learning (ML). The key contribution is a theory of optimally sample and energy efficient learning, which is supported by mathematical proofs and experimental results.
Explain It as Simple as Possible, but No Simpler – Explanation via Model Simplification for Addressing Inferential Gap (Abstract Reprint)
PDF ↗One of the core challenges of explaining decisions made by modern AI systems is the need to address the potential gap in the inferential capabilities of the system generating the decision and the user trying to make sense of it. This inferential capability gap becomes even more critical when it comes to explaining sequential decisions. While there have been some isolated efforts at developing explanation methods suited for complex decision-making settings, most of these current efforts are limited in scope. In this paper, we introduce a general framework for generating explanations in the presence of inferential capability gaps. A framework that is grounded in the generation of simplified representations of the agent model through the application of a sequence of model simplifying transformations. This framework not only allows us to develop an extremely general explanation generation algorithm, but we see that many of the existing works in this direction could be seen as specific instantiations of our more general method. While the ideas presented in this paper are general enough to be applied to any decision-making framework, we will focus on instantiating the framework in the context of stochastic planning problems. As a part of this instantiation, we will also provide an exhaustive characterization of explanatory queries and an analysis of various classes of applicable transformations. We will evaluate the effectiveness of transformation-based explanations through both synthetic experiments and user studies.
CureGraph: Contrastive Multi-Modal Graph Representation Learning for Urban Living Circle Health Profiling and Prediction (Abstract Reprint)
PDF ↗The early detection and prediction of health status decline among the elderly at the neighborhood level are of great significance for urban planning and public health policymaking. While existing studies affirm the connection between living environments and health outcomes, most rely on single data modalities or simplistic feature concatenation of multi-modal information, limiting their ability to comprehensively profile the health-oriented urban environments. To fill this gap, we propose CureGraph, a contrastive multi-modal representation learning framework for urban health prediction that employs graph-based techniques to infer the prevalence of common chronic diseases among the elderly within the urban living circles of each neighborhood. CureGraph leverages rich multi-modal information, including photos and textual reviews of residential areas and their surrounding points of interest, to generate urban neighborhood embeddings. By integrating pre-trained visual and textual encoders with graph modeling techniques, CureGraph captures cross-modal spatial dependencies, offering a comprehensive understanding of urban environments tailored to elderly health considerations. Extensive experiments on real-world datasets demonstrate that CureGraph improves the best baseline by 28% on average in terms of across elderly disease risk prediction tasks. Moreover, the model enables the identification of stage-wise chronic disease progression and supports comparative public health analysis across neighborhoods, offering actionable insights for sustainable urban development and enhanced quality of life. The code is publicly available at https://github.com/jinlin2021/CureGraph.
CADS: A Systematic Literature Review on the Challenges of Abstractive Dialogue Summarization (Abstract Reprint)
PDF ↗Abstractive dialogue summarization is the task of distilling conversations into informative and concise summaries. Although focused reviews have been conducted on this topic, there is a lack of comprehensive work that details the core challenges of dialogue summarization, unifies the differing understanding of the task, and aligns proposed techniques, datasets, and evaluation metrics with the challenges. This article summarizes the research on Transformer-based abstractive summarization for English dialogues by systematically reviewing 1262 unique research papers published between 2019 and 2024, relying on the Semantic Scholar and DBLP databases. We cover the main challenges present in dialog summarization (i.e., language, structure, comprehension, speaker, salience, and factuality) and link them to corresponding techniques such as graph-based approaches, additional training tasks, and planning strategies, which typically overly rely on BART-based encoder-decoder models. Recent advances in training methods have led to substantial improvements in language-related challenges. However, challenges such as comprehension, factuality, and salience remain difficult and present significant research opportunities. We further investigate how these approaches are typically analyzed, covering the datasets for the subdomains of dialogue (e.g., meeting, customer service, and medical), the established automatic metrics (e.g., ROUGE), and common human evaluation approaches for assigning scores and evaluating annotator agreement. We observe that only a few datasets (i.e., SAMSum, AMI, DialogSum) are widely used. Despite its limitations, the ROUGE metric is the most commonly used, while human evaluation, considered the gold standard, is frequently reported without sufficient detail on the inter-annotator agreement and annotation guidelines. Additionally, we discuss the possible implications of the recently explored large language models and conclude that our described challenge taxonomy remains relevant despite a potential shift in relevance and difficulty.
Decoupled Search for the Masses: A Novel Task Transformation for Classical Planning (Extended Abstract)
PDF ↗Classical planning provides a framework for solving sequential decision-making problems, i.e., finding a sequence of actions that transforms the current state of the world into a state that satisfies a desired goal condition. Planning tasks are modeled in a logic that describes the environment and its dynamics. It is well known that the specific problem formulation can significantly affect the performance of planning systems solving problems like the Rubik's Cube or finding algorithms for matrix multiplication. In this work, we propose a domain-general problem reformulation that embodies decoupled search, a search-reduction technique from classical planning and model checking. Decoupled search decomposes a given problem to exploit its structure, achieving exponential reductions over other search techniques. We show that decoupled search can be captured exactly as a task reformulation and that, on many benchmark domains, it performs as good and sometimes even better than a native decoupled-search implementation.
Grounding Open-Domain Knowledge from LLMs to Real-World Reinforcement Learning Tasks: A Survey
PDF ↗Grounding open-domain knowledge from large language models (LLMs) into real-world reinforcement learning (RL) tasks represents a transformative frontier in developing intelligent agents capable of advanced reasoning, adaptive planning, and robust decision-making in dynamic environments. In this paper, we introduce the LLM-RL Grounding Taxonomy, a systematic framework that categorizes emerging methods for integrating LLMs into RL systems by bridging their open-domain knowledge and reasoning capabilities with the task-specific dynamics, constraints, and objectives inherent to real-world RL environments. This taxonomy encompasses both training-free approaches, which leverage the zero-shot and few-shot generalization capabilities of LLMs without fine-tuning, and fine-tuning paradigms that adapt LLMs to environment-specific tasks for improved performance. We critically analyze these methodologies, highlight practical examples of effective knowledge grounding, and examine the challenges of alignment, generalization, and real-world deployment. Our work not only illustrates the potential of LLM-RL agents for enhanced decision-making, but also offers actionable insights for advancing the design of next-generation RL systems that integrate open-domain knowledge with adaptive learning.
Embodied multi-agent systems (EMAS) have attracted growing attention for their potential to address complex, real-world challenges in areas such as logistics and robotics. Recent advances in foundation models pave the way for generative agents capable of richer communication and adaptive problem-solving. This survey provides a systematic examination of how EMAS can benefit from these generative capabilities. We propose a taxonomy that categorizes EMAS by system architectures and embodiment modalities, emphasizing how collaboration spans both physical and virtual contexts. Central building blocks, perception, planning, communication, and feedback, are then analyzed to illustrate how generative techniques bolster system robustness and flexibility. Through concrete examples, we demonstrate the transformative effects of integrating foundation models into embodied, multi-agent frameworks. Finally, we discuss challenges and future directions, underlining the significant promise of EMAS to reshape the landscape of AI-driven collaboration.
Reinforcement learning (RL) has shown impressive results in sequential decision-making tasks. Large Language Models (LLMs) and Vision-Language Models (VLMs) have recently emerged, exhibiting impressive capabilities in multimodal understanding and reasoning. These advances have led to a surge of research integrating LLMs and VLMs into RL. This survey reviews representative works in which LLMs and VLMs are used to overcome key challenges in RL, such as lack of prior knowledge, long-horizon planning, and reward design. We present a taxonomy that categorizes these LLM/VLM-assisted RL approaches into three roles: agent, planner, and reward. We conclude by exploring open problems, including grounding, bias mitigation, improved representations, and action advice. By consolidating existing research and identifying future directions, this survey establishes a framework for integrating LLMs and VLMs into RL, advancing approaches that unify natural language and visual understanding with sequential decision-making.
Accurate planning models are a prerequisite for the appropriate functioning of AI planning applications. Creating these models is, however, a tedious and error-prone task -- even for planning experts. This makes the provision of automated modeling support essential. In this work, we differentiate between approaches that learn models from scratch (called domain model acquisition) and those that repair flawed or incomplete ones. We survey approaches for the latter, including those that can be used for domain repair but have been developed for other applications, discuss possible optimization metrics (i.e., which repaired model to aim at), and conclude with lines of research we believe deserve more attention.
Reinforcement Learning for Hybrid Charging Stations Planning and Operation Considering Fixed and Mobile Chargers
PDF ↗efficient and adaptable charging infrastructure. Fixed-location charging stations often suffer from underutilization or congestion due to fluctuating demand, while mobile chargers offer flexibility by relocating as needed. This paper studies the optimal planning and operation of hybrid charging infrastructures that combine both fixed and mobile chargers within urban road networks. We formulate the Hybrid Charging Station Planning and Operation (HCSPO) problem, jointly optimizing the placement of fixed stations and the scheduling of mobile chargers. A charging demand prediction model based on Model Predictive Control (MPC) supports dynamic decision-making. To solve the HCSPO problem, we propose a deep reinforcement learning approach enhanced with heuristic scheduling. Experiments on real-world urban scenarios show that our method improves infrastructure availability—achieving up to 244.4% increase in coverage—and reduces user inconvenience with up to 79.8% shorter waiting times, compared to existing solutions.