Dynamic pricing is pivotal for improving e-commerce efficiency and profitability. While offline reinforcement learning (RL) offers a data-driven approach to policy optimization, its practical adoption faces three core constraints: uninterpretable black-box policies, limited multi-level strategy abstraction, and distributional bias in static historical data. To address these issues, we propose SkillPrice, a hierarchical offline RL framework with automatic semantic skill discovery. SkillPrice extracts lifecycle-aware pricing skills from historical trajectories via discrete representation learning, iteratively refined through LLM-based semantic alignment to produce interpretable, reusable operational patterns. Building upon this structured skill space, SkillPrice constructs a two-level policy architecture, where the skill scheduler selects semantic skills, and the low-level policy executes atomic pricing actions under confidence-aware constraints with conservative regularization to ensure offline safety. Extensive experiments on real e-commerce datasets demonstrate SkillPrice consistently outperforms state-of-the-art baselines in both revenue optimization and interpretability, establishing a scalable and deployable paradigm for industrial dynamic pricing.

The large-scale deployment of unmanned aerial vehicle (UAV) swarms has created an urgent need for their safe and reliable operation. However, data privacy constraints, high communication costs, and heavy computational burdens with centralized training limit the applicability of existing methods to distributed collaborative anomaly detection (AD) in UAV swarms. To address this, we propose an unsupervised federated AD framework for UAV swarms with memory networks and contrastive learning enhanced spatiotemporal autoencoder (MN-CL-STAE). Specifically, we design a lightweight spatiotemporal encoder model based on a multi-scale temporal convolutional network (MSTCN) and a convolutional neural network (CNN) to fully capture complex spatiotemporal features in normal flight data. Building on this foundation, memory network enhancement strategy models prototypes of spatiotemporal encoded features, adaptively extracting key memory features to gate residual injection into the decoder. This improves the model’s ability to stably represent normal patterns and mitigates excessive anomaly reconstruction caused by random noise. Concurrently, multi-view contrastive learning constrains the model to learn locally invariant representations under normal patterns, promoting compact clustering of normal samples and thereby improving the separability and discriminability of anomalies. Overall, under the federated learning framework, this paper adopts the federated averaging (FedAvg) algorithm to aggregate client model parameters for global collaborative optimization, thereby realizing distributed AD for UAV swarms while protecting local data privacy. Extensive experimental results on the ALFA dataset demonstrate that the proposed method significantly outperforms various representative methods in AD tasks.

Despite achieving remarkable success in complex tasks, Deep Reinforcement Learning (DRL) is still suffering from critical issues in practical applications, such as low data efficiency, lack of interpretability, and limited cross-environment transferability. However, the learned policy generating actions based on states are sensitive to the environmental changes, struggling to guarantee behavioral safety and compliance. Recent research shows that integrating Large Language Models (LLMs) with symbolic planning is promising in addressing these challenges. Inspired by this, we introduce a novel LLM-driven closed-loop framework, which enables semantic-driven skill reuse and real-time constraint monitoring by mapping natural language instructions into executable rules and semantically annotating automatically created options. The proposed approach utilizes the general knowledge of LLMs to facilitate exploration efficiency and adapt to transferable options for similar environments, and provides inherent interpretability through semantic annotations. To validate the effectiveness of this framework, we conduct experiments on two domains, Office World and Montezuma's Revenge, respectively. The results demonstrate superior performance in data efficiency, constraint compliance, and cross-task transferability.

Learning physically consistent and robust manipulation policies from perceptual inputs remains a key challenge in robot learning. Most existing diffusion-based approaches condition only on raw point clouds or robot states, failing to exploit the underlying geometric relations that govern feasible object interactions. To address this gap, we propose GeoDiff, a geometry-conditioned diffusion policy for refined robotic trajectory generation. GeoDiff constructs object-centric geometric representations via clustering-based point cloud segmentation and encodes relational features capturing spatial dependencies between the robot and surrounding objects. Conditioned on these geometric features, the diffusion policy generates multiple stochastic trajectory candidates under consistent initial conditions. A physics-aware evaluation module then scores each candidate based on smoothness, goal accuracy, and collision safety, selecting the optimal physically valid trajectory. We leverage a composite loss combining denoising reconstruction and differentiable physical consistency to further enforces smooth, goal-directed, and collision-free motion generation. Extensive experiments across three well-known simulated manipulation benchmarks demonstrate that GeoDiff achieves over 15 % improvement in task success rate and motion smoothness compared with state-of-the-art diffusion and optimization-based baselines. Those results highlight the importance of geometric conditioning and physics-guided refinement for reliable diffusion-based robotic manipulation.

Aspect Sentiment Triplet Extraction (ASTE) aims to extract all sentiment triplets of aspect terms, opinion terms, and sentiment polarities from a sentence. Existing methods are typically trained on individual datasets in isolation, failing to jointly capture the common feature representations shared across domains. Moreover, data privacy constraints prevent centralized data aggregation. To address these challenges, we propose Prototype-based Cross-Domain Span Prototype extraction (PCD-SpanProto), a prototype-regularized federated learning framework to enable distributed clients to exchange class-level prototypes instead of full model parameters. Specifically, we design a weighted performance-aware aggregation strategy and a contrastive regularization module to improve the global prototype under domain heterogeneity and the promotion between intra-class compactness and inter-class separability across clients. Extensive experiments on four ASTE datasets demonstrate that our method outperforms baselines and reduces communication costs, validating the effectiveness of prototype-based cross-domain knowledge transfer.

Addressing large-scale planning problems has become one of the central challenges in the planning community, deriving from the state-space explosion caused by growing objects and actions. Recently, researchers have explored the effectiveness of leveraging Large Language Models (LLMs) to generate helpful actions and states to prune the search space. However, prior works have largely overlooked integrating LLMs with domain-specific knowledge to ensure valid plans. In this paper, we propose a novel LLM-assisted planner integrated with problem decomposition, which first decomposes large planning problems into multiple simpler sub-tasks with dependency construction and conflict detection. Then we explore two novel paradigms to utilize LLMs, i.e., LLM4Inspire and LLM4Predict, to assist problem decomposition, where LLM4Inspire provides heuristic guidance according to general knowledge and LLM4Predict employs domain-specific knowledge to infer intermediate conditions. We empirically validate the effectiveness of our planner across multiple domains, demonstrating the ability of search space partition when solving large-scale planning problems. The experimental results show that LLMs effectively locate feasible solutions when pruning the search space, where infusing domain-specific knowledge into LLMs, i.e., LLM4Predict, holds particular promise compared with LLM4Inspire, which offers general knowledge within LLMs.

In this paper, we present fixed-parameter tractability algorithms for both the undirected and directed versions of the Spanning Tree Isomorphism Problem, parameterized by the size k of a redundant set. A redundant set is a collection of edges whose removal transforms the graph into a spanning tree. For the undirected version, our algorithm achieves a time complexity of O(n^2 log n · 2^k log k). For the directed version, we propose a more efficient algorithm with a time complexity of O(n^2 · 2^4k-3), where n is the number of vertices.

With feature size shrinking and design complexity increasing, detailed routing has become a crucial challenge in VLSI design. Although detailed routers have been proposed to judiciously handle hard-to-access pins and various design rules, their performances are sensitive to the order of nets to be routed, especially for those sequential routers with ripup-and-reroute scheme. In the published literature, net ordering strategies mainly rely on experts' knowledge to design heuristics to guarantee their performances. In this paper, we propose a novel transformer-based reinforcement learning framework for net ordering in detailed routing, aiming at automatically gaining failure/success routing experiences and building net order policies to guide detailed routing. Our experimental results show that our framework can effectively reduce the number of design rule violations and routing cost with comparable wirelength and via count, with comparison to state-of-the-art approaches.

Navigating multi-agent reinforcement learning (MARL) environments with sparse rewards is notoriously difficult, particularly in suboptimal settings where exploration can be prematurely halted. To tackle these challenges, we introduce Hierarchical Symbolic Multi-Agent Reinforcement Learning (HS-MARL), a novel approach that incorporates hierarchical knowledge into MARL to effectively reduce the exploration space. We design intermediate states to decompose the state space into a hierarchical structure, represented using the Hierarchical Domain Definition Language (HDDL) and the option framework, forming domain knowledge and a symbolic option set. We leverage pyHIPOP+, an enhanced hierarchical task network (HTN) planner, to generate action sequences. A high-level meta-controller then assigns these symbolic options as policy functions, guiding low-level agents in their exploration of the environment. During this process, the meta-controller computes intrinsic rewards from the environmental rewards collected, which are used to train the symbolic option policies and refine pyHIPOP+'s heuristic function, thereby optimizing future action sequences. We evaluate HS-MARL with comparison to 15 state-of-the-art algorithms across two types of environments: four with sparse rewards and suboptimal conditions, and a real-world scenario involving a football match. Additionally, we perform an ablation study on HS-MARL's intrinsic reward mechanism and pyHIPOP+, along with a sensitivity analysis of intrinsic reward hyperparameters. Our results show that HS-MARL significantly outperforms other methods in environments with sparse rewards and suboptimal conditions, underscoring the critical role of its intrinsic reward design and the pyHIPOP+ component. The code is available at: https://github.com/Mxc666/HS-MARL.git.

Natural language processing (NLP) aims at investigating the interactions between agents and humans, processing and analyzing large amounts of natural language data. Large-scale language models play an important role in current natural language processing. However, the challenges of explainability and complexity come along with the developments of language models. One way is to introduce logical relations and rules into natural language processing models, such as making use of Automated Planning. Automated planning (AI planning) focuses on building symbolic domain models and synthesizing plans to transit initial states to goals based on domain models. Recently, there have been plenty of works related to these two fields, which have the abilities to generate explicit knowledge, e.g., preconditions and effects of action models, and learn from tacit knowledge, e.g., neural models, respectively. Integrating AI planning and natural language processing effectively improves the communication between human and intelligent agents. This paper outlines the commons and relations between AI planning and natural language processing, argues that each of them can effectively impact on the other one by five areas: (1) planning-based text understanding, (2) planning-based natural language processing, (3) planning-based explainability, (4) text-based human-robot interaction, and (5) applications. We also explore some potential future issues between AI planning and natural language processing. To the best of our knowledge, this survey is the first work that addresses the deep connections between AI planning and Natural language processing.

Learning causal relationships in directed acyclic graphs (DAGs) from multi-type event sequences is a challenging task, especially in large-scale telecommunication networks. Existing methods struggle with the exponentially growing search space and lack global exploration. Gradient-based approaches are limited by their reliance on local information and often fail to generalize. To address these issues, we propose TCCD, a framework that combines Monte Carlo Tree Search (MCTS) with continuous gradient optimization. TCCD balances global exploration and local optimization, overcoming the shortcomings of purely gradient-based methods and enhancing generalization. By unifying various causal structure learning approaches, TCCD offers a scalable and efficient solution for causal inference in complex networks. Extensive experiments validate its superior performance on both synthetic and real-world datasets. Code and Appendix are available at https://github.com/jzephyrl/TCCD.

Traditional Chinese Medicine (TCM) has a rich history of utilizing natural herbs to treat a diversity of illnesses. In practice, TCM diagnosis and treatment are highly personalized and organically holistic, requiring comprehensive consideration of the patient's state and symptoms over time. However, existing TCM recommendation approaches overlook the changes in patient status and only explore potential patterns between symptoms and prescriptions. In this paper, we propose a novel Sequential Condition Evolved Interaction Knowledge Graph (SCEIKG), a framework that treats the model as a sequential prescription-making problem by considering the dynamics of the patient's condition across multiple visits. In addition, we incorporate an interaction knowledge graph to enhance the accuracy of recommendations by considering the interactions between different herbs and the patient's condition. Experimental results on a real-world dataset demonstrate that our approach outperforms existing TCM recommendation methods, achieving state-of-the-art performance.

Plan synthesis aims to generate a course of actions or policies to transit given initial states to goal states, provided domain models that could be designed by experts or learnt from training data or interactions with the world. Intrigued by the claims of emergent planning capabilities in large language models (LLMs), works have been proposed to investigate the planning effectiveness of LLMs, without considering any utilization of off-the-shelf planning techniques in LLMs. In this paper, we aim to further study the insight of the planning capability of LLMs by investigating the roles of LLMs in off-the-shelf planning frameworks. To do this, we investigate the effectiveness of embedding LLMs into one of the well-known planning frameworks, graph-based planning, proposing a novel LLMs-based planning framework with LLMs embedded in two levels of planning graphs, i.e., mutual constraints generation level and constraints solving level. We empirically exhibit the effectiveness of our proposed framework in various planning domains.

With the development of autonomous equipment, hoist scheduling has become a bottleneck for applications in the electroplating industry. Although there are some approaches proposed for this challenging problem, they generally do not scale to large-scale problems. In this paper, we formulate the real-world electroplating scheduling problem as a temporal planning problem in the form of an adapted PDDL and propose a novel hierarchical temporal planning approach to solve the problem efficiently. In addition, we provide a series of real-life benchmark instances that can be used to evaluate the solution of this problem. We show that our approach can effectively find high-quality solutions for large-scale real-life benchmark instances compared to state-of-the-art benchmarks.

Multi-task Reinforcement Learning (MT-RL) faces key challenges in accomplishing complex long-horizon tasks, particularly related to scarce rewards, inefficient sample usage, and low transferability. These challenges are exacerbated in real world scenarios where tasks can often be done by completing different intermediate subtasks, complicating intermediate reward allocation. To address those issues, we introduce a novel framework integrating a strategic planner, a pre-trained language module, and a reinforcement learning policy. This framework strategically decomposes complex tasks into observable sub-task lists using the planner, adapting the plan based on sub-task completion, while the incorporation of the pre-trained language module aids in the task list understanding. We evaluated our framework in a single-agent overcooked environment, chosen for its relevance in the long-horizon tasks. Our results demonstrate notable improvements in time efficiency and adaptability, showcasing the framework's potential to enhance MT-RL applications.

Despite the superior performance of large language models to generate natural language texts, it is hard to generate texts with correct logic according to a given task, due to the difficulties for neural models to capture implied rules from free-form texts. In this paper, we propose a novel graph-based language model, Logical-GLM, to infuse logic into language models for more valid text generation and interpretability. Specifically, we first capture information from natural language instructions and construct logical bayes graphs that generally describe domains. Next, we generate logical skeletons to guide language model training, infusing domain knowledge into language models. Finally, we alternately optimize the searching policy of graphs and language models until convergence. The experimental results show that Logical-GLM is both effective and efficient compared with traditional language models, despite using smaller-scale training data and fewer parameters. Our approach can generate instructional texts with more correct logic owing to the internalized domain knowledge. Moreover, the usage of logical graphs reflects the inner mechanism of the language models, which improves the interpretability of black-box models.

In retrosynthetic planning, the huge number of possible routes to synthesize a complex molecule using simple building blocks leads to a combinatorial explosion of possibilities. Even experienced chemists often have difficulty to select the most promising transformations. The current approaches rely on human-defined or machine-trained score functions which have limited chemical knowledge or use expensive estimation methods for guiding. Here we an propose experience-guided Monte Carlo tree search (EG-MCTS) to deal with this problem. Instead of rollout, we build an experience guidance network to learn knowledge from synthetic experiences during the search. Experiments on benchmark USPTO datasets show that, EG-MCTS gains significant improvement over state-of-the-art approaches both in efficiency and effectiveness. In a comparative experiment with the literature, our computer-generated routes mostly matched the reported routes. Routes designed for real drug compounds exhibit the effectiveness of EG-MCTS on assisting chemists performing retrosynthetic analysis.

Modern High-Performance Computing (HPC) platforms usually consist of an intermediate high-throughput layer, Burst-Buffers (BBs), between computing nodes and underlying shared Parallel File System (PFS) to absorb the I/O bursts caused by concurrent I/O requests from different applications. As concurrent applications increase I/O demand, BBs may experience I/O contention due to its limited capacity. The existing probabilistic I/O scheduling method can schedule I/O under limited BBs’ capacity, which can sense BBs’ congestion via the Markov-Chain-based probability model. However, the probability model requires consistent I/O characteristics of applications, including similar I/O duration and longer application length, to obtain an accurate I/O load estimation. These consistency conditions do not often hold in realistic situations.In this paper, we proposed a probability I/O scheduling framework based on application clustering (PIOS) to eliminate the consistency requirement. The framework first clusters all applications by 1-D K-means according to their I/O phrase length. Next, the expected I/O workload of each cluster is calculated and then the BBs’s capacity is partitioned according to the expected I/O workload. Finally, the probabilistic I/O scheduling is applied to each application cluster. The simulation results demonstrate our framework can adapt to inconsistency and show more efficiency.

Large-scale pre-trained language models such as BERT have contributed significantly to the development of NLP. However, those models require large computational resources, making it difficult to be applied to mobile devices where computing power is limited. In this paper we aim to address the weakness of existing input-adaptive inference methods which fail to take full advantage of the structure of BERT. We propose Dynamic Planning in BERT, a novel fine-tuning strategy that can accelerate the inference process of BERT through selecting a subsequence of transformer layers list of backbone as a computational path for an input sample. To do this, our approach adds a planning module to the original BERT model to determine whether a layer is included or bypassed during inference. Experimental results on the GLUE benchmark exhibit that our method reduces latency to 75% while maintaining 98% accuracy, yielding a better accuracy-speed trade-off compared to state-of-the-art input-adaptive methods.

Dealing with planning problems with both logical relations and numeric changes in real-world dynamic environments is challenging. Existing numeric planning systems for the problem often discretize numeric variables or impose convex constraints on numeric variables, which harms the performance when solving problems, especially when the problems contain obstacles and non-linear numeric effects. In this work, we propose a novel algorithm framework to solve numeric planning problems mixed with logical relations and numeric changes based on gradient descent. We cast the numeric planning with logical relations and numeric changes as an optimization problem. Specifically, we extend the syntax to allow parameters of action models to be either objects or real-valued numbers, which enhances the ability to model real-world numeric effects. Based on the extended modeling language, we propose a gradient-based framework to simultaneously optimize numeric parameters and compute appropriate actions to form candidate plans. The gradient-based framework is composed of an algorithmic heuristic module based on propositional operations to select actions and generate constraints for gradient descent, an algorithmic transition module to update states to the next ones, and a loss module to compute loss. We repeatedly minimize loss by updating numeric parameters and compute candidate plans until it converges into a valid plan for the planning problem.