论文检索

Taqiya Ehsan, Shuren Xia, Jorge Ortiz

Embodied agents must reason causally, as correlation-based models fail under intervention and distribution shift. This challenge arises in domains like robotics and cyber-physical systems, where agents balance efficiency and comfort under uncertainty. We introduce POLICYGRID, unifying causal discovery and control by treating each action as both decision and experiment. Leveraging constraint-based search, neural causal models, and language model priors with interventional validation, POLICYGRID yields adaptive, interpretable policies. Across synthetic, real-world, and live deployments, it achieves superior causal recovery (F1 = 0.89) and 2.8× better multi-objective performance than correlation-based baselines, demonstrating safe, generalizable decision-making.

Soumyajit Dev, Malay Bhattacharyya

Dismantling interdependent directed networks to obtain the largest mutually strongly connected component (MSCC) is an NP-hard problem. To address this, we propose a novel method, Disassembling Directed Interdependent Networks (DDIN), by synergizing Reinforcement Learning (RL) and Graph Neural Networks (GNN). We introduce asymmetric GNNs to capture the asymmetry of in/out-degree and multi-relational attention to model directed inter-layer dependencies, integrated with prioritized RL for efficient node selection in large action spaces. Our contributions include (i) a directed GraphSAGE encoder separating in/out aggregations for asymmetry, (ii) multi-relational attention fusing layer semantics, and (iii) sum-tree prioritized n-step Deep Q-Network (DQN) for efficient policy search. DDIN is evaluated on 5 directed multiplexes from biological, social, and economic domains, achieving 16-23% lower AUDC compared to known baseline heuristics.

Mayank Kejriwal

Online human trafficking investigations generate vast amounts of noisy, heterogeneous, and deliberately obfuscated data, making traditional search and analytics tools ineffective for supporting law enforcement. This paper discusses the deployment of the Domain-Specific Insight Graphs (DIG) system, an AI-powered investigative search engine that was operationally used by over 200 U.S. law enforcement agencies for more than five years in the pre-COVID period. The system integrates advanced research conducted over the years in information extraction, knowledge graph construction, and entity-centric search to enable investigators to formulate queries without technical background, aggregate evidence, and uncover latent relationships among entities such as phone numbers, emails, and locations. Beyond technical innovation, the deployment required sustained attention to usability, explainability, and policy compliance, ensuring trust in high-stakes legal contexts. We report measurable benefits in investigative efficiency, case initiation, and prosecutorial support, as well as lessons learned from long-term maintenance and adaptation to evolving online platforms. Since 2020, work conducted in this domain has also had significant policy and advocacy ramifications. The system's generalized design has also allowed it to be prototyped for adjacent illicit domains, including securities fraud and illegal firearm sales, demonstrating the broader applicability of AI-driven investigative tools. We contribute a rare case study of an AI system that has transitioned from research to sustained real-world impact in a socially critical domain.

Fu Feng, Jing Wang, Xu Yang, Xin Geng

Biological intelligence has driven significant progress in artificial intelligence (AI), but a critical gap remains: biological systems inherit innate abilities from genes, with brains initialized by blueprints refined over 3.5 billion years of evolution, while machines rely heavily on inefficient, data-driven learning from scratch. This gap arises from the lack of a genetic mechanism in machines to transfer and accumulate inheritable knowledge across generations. To bridge this gap, we propose learngenes, network fragments that act as inheritable 'genes' for machines. Unlike conventional knowledge transfer methods, learngenes enable efficient and universal knowledge transfer by selectively encapsulating task-agnostic knowledge. To facilitate the transfer and accumulation of task-agnostic knowledge across generations, we introduce Genetic Reinforcement Learning (GRL), a framework that simulates the learning and evolution of organisms in intelligent agents following Lamarckian principles. Through GRL, we identify learngenes as network fragments within agents' policy networks, equipping newborn agents with innate abilities for rapid adaptation to novel tasks. We demonstrate the advantages of learngene-based knowledge transfer over evolution-based search and traditional pre-trained models, and show how learngenes evolve through the accumulation of task-agnostic knowledge. Overall, this work establishes a novel paradigm for knowledge transfer and model initialization in AI, offering new possibilities for more adaptive, efficient, and scalable learning systems.

Zeel B Patel, Vinayak Rana, Nipun Batra

Air pollution is a leading global health threat, yet many developing countries lack the dense monitoring infrastructure needed for accurate exposure assessment and informed policy. Optimal Sensor Placement (OSP) is a foundational challenge in expanding monitoring capacity. While mutual information (MI) offers a principled criterion for selecting informative sensor locations, its computational cost grows with both the number of placements and the density of the candidate grid. We present a scalable, continuous optimization framework that treats sensor coordinates as differentiable parameters and directly maximizes MI. Unlike standard approaches, our method is computationally efficient—its runtime is independent of both the number of placements and the size of the search grid—making MI-based acquisition feasible over large spatial domains. On a continental-scale PM2.5 dataset, our method outperforms random placement and the widely-used Maximum Predictive Variance heuristic. In a focused regional study, it approaches the performance of greedy MI while being orders of magnitude faster. Our framework enables practical, information-theoretic sensor placement for real-world environmental monitoring.

Hongyi Li, Chengxuan Zhou, Chu Wang, Sicheng Liang, Yanting Chen, Qinlin Xie, Jiawei Ye, Jie Wu

Large Audio-language Models (LAMs) have recently enabled powerful speech-based interactions by coupling audio encoders with Large Language Models (LLMs). However, the security of LAMs under adversarial attacks remains underexplored, especially through audio jailbreaks that craft malicious audio prompts to bypass alignment. Existing efforts primarily rely on converting text-based attacks into speech or applying shallow signal-level perturbations, overlooking the impact of human speech’s expressive variations on LAM alignment robustness. To address this gap, we propose StyleBreak, a novel style-aware audio jailbreak framework that systematically investigates how diverse human speech attributes affect LAM alignment robustness. Specifically, StyleBreak employs a two-stage style-aware transformation pipeline that perturbs both textual content and audio to control linguistic, paralinguistic, and extralinguistic attributes. Furthermore, we develop a query-adaptive policy network that automatically searches for adversarial styles to enhance the efficiency of LAM jailbreak exploration. Extensive evaluations demonstrate that LAMs exhibit critical vulnerabilities when exposed to diverse human speech attributes. Moreover, StyleBreak achieves substantial improvements in attack effectiveness and efficiency across multiple attack paradigms, highlighting the urgent need for more robust alignment in LAMs.

Chen Wang, Yue-Jiao Gong, Zhiguang Cao, Zeyuan Ma

To relieve intensive human-expertise required to design optimization algorithms, recent Meta-Black-Box Optimization (MetaBBO) researches leverage generalization strength of meta-learning to train neural network-based algorithm design policies over a predefined training problem set, which automates the adaptability of the low-level optimizers on unseen problem instances. Currently, a common training problem set choice in existing MetaBBOs is well-known benchmark suites CoCo-BBOB. Although such choice facilitates the MetaBBO's development, problem instances in CoCo-BBOB are more or less limited in diversity, raising the risk of overfitting of MetaBBOs, which might further results in poor generalization. In this paper, we propose an instance generation approach, termed as LSRE, which could generate diverse training problem instances for MetaBBOs to learn more generalizable policies. LSRE first trains an autoencoder which maps high-dimensional problem features into a 2-dimensional latent space. Uniform-grid sampling in this latent space leads to hidden representations of problem instances with sufficient diversity. By leveraging a genetic-programming approach to search function formulas with minimal L2-distance to these hidden representations, LSRE reverse engineers a diversified problem set, termed as Diverse-BBO. We validate the effectiveness of LSRE by training various MetaBBOs on Diverse-BBO and observe their generalization performances on either synthetic or realistic scenarios. Extensive experimental results underscore the superiority of Diverse-BBO to existing training set choices in MetaBBOs. Further ablation studies not only demonstrate the effectiveness of design choices in LSRE, but also reveal interesting insights on instance diversity and MetaBBO's generalization.

Yukun Du, Haiyue Yu, Xiaotong Xie, Yan Zheng, Lixin Zhan, Yudong Du, Chongshuang Hu, Boxuan Wang, Jiang Jiang

Surrogate-Assisted Evolutionary Algorithms (SAEAs) are widely used for expensive Black-Box Optimization. However, their reliance on rigid, manually designed components such as infill criteria and evolutionary strategies during the search process limits their flexibility across tasks. To address these limitations, we propose Dual-Control Bi-Space Surrogate-Assisted Evolutionary Algorithm (DB-SAEA), a Meta-Black-Box Optimization (MetaBBO) framework tailored for multi-objective problems. DB-SAEA learns a meta-policy that jointly regulates candidate generation and infill criterion selection, enabling dual control. The bi-space Exploratory Landscape Analysis (ELA) module in DB-SAEA adopts an attention-based architecture to capture optimization states from both true and surrogate evaluation spaces, while ensuring scalability across problem dimensions, population sizes, and objectives. Additionally, we integrate TabPFN as the surrogate model for accurate and efficient prediction with uncertainty estimation. The framework is trained via reinforcement learning, leveraging parallel sampling and centralized training to enhance efficiency and transferability across tasks. Experimental results demonstrate that DB-SAEA not only outperforms state-of-the-art baselines across diverse benchmarks, but also exhibits strong zero-shot transfer to unseen tasks with higher-dimensional settings. This work introduces the first MetaBBO framework with dual-level control over SAEAs and a bi-space ELA that captures surrogate model information.

Yang You, Alex Schutz, Zhikun Li, Bruno Lacerda, Robert Skilton, Nick Hawes

Many high-level multi-agent planning problems, such as multi-robot navigation and path planning, can be modeled with deterministic actions and observations. In this work, we focus on such domains and introduce the class of Deterministic Decentralized POMDPs (Det-Dec-POMDPs)—a subclass of Dec-POMDPs with deterministic transitions and observations given the state and joint actions. We then propose a practical solver, Iterative Deterministic POMDP Planning (IDPP), based on the classic Joint Equilibrium Search for Policies framework, specifically optimized to handle large-scale Det-Dec-POMDPs that existing Dec-POMDP solvers cannot handle efficiently.

Rasmus G. Tollund, Álvaro Torralba

In many planning problems there are non-deterministic actions for which the outcome cannot be fully controlled by the planning agent. For critical tasks, we need to find a strategy that achieves the goal within a predictable time-frame and/or cost. Thus, we consider an adversarial planning setting and compute optimal policies that optimize the worst-case cost to reach the goal. In this work, we introduce domain-independent optimal heuristic search algorithms for this adversarial setting. To guide the search, we show how to leverage classical planning heuristics by applying single-outcome determinization. We also generalize dominance techniques, that analyse when a state is as good as another, to the non-deterministic setting and apply them to prune the search space. Our experimental analysis shows that both methods greatly help to compute optimal policies across multiple domains.

Tamir Shazman, Idan Lev-Yehudi, Ron Benchetrit, Vadim Indelman

Online planning in Markov Decision Processes (MDPs) enables agents to make sequential decisions by simulating future trajectories from the current state, making it well-suited for large-scale or dynamic environments. Sample-based methods such as Sparse Sampling and Monte Carlo Tree Search (MCTS) are widely adopted for their ability to approximate optimal actions using a generative model. However, in practical settings, the generative model is often learned from limited data, introducing approximation errors that can degrade performance or lead to unsafe behaviors. To address these challenges, Robust MDPs (RMDPs) offer a principled framework for planning under model uncertainty, yet existing approaches are typically computationally intensive and not suited for real-time use. In this work, we introduce Robust Sparse Sampling (RSS), the first online planning algorithm for RMDPs with finite-sample theoretical performance guarantees. Unlike Sparse Sampling, which estimates the nominal value function, RSS computes a robust value function by leveraging the efficiency and theoretical properties of Sample Average Approximation (SAA), enabling tractable robust policy computation in online settings. RSS is applicable to infinite or continuous state spaces, and its sample and computational complexities are independent of the state space size. We provide theoretical performance guarantees and empirically show that RSS outperforms standard Sparse Sampling in environments with uncertain dynamics.

Yishuai Cai, Xinglin Chen, Yunxin Mao, Kun Hu, Minglong Li

Behavior Trees (BTs) offer a powerful paradigm for designing modular and reactive robot controllers. BT planning, an emerging field, provides theoretical guarantees for the automated generation of reliable BTs. However, BT planning typically assumes that a well-designed BT system is already grounded—comprising high-level action models and low-level control policies—which often requires extensive expert knowledge and manual effort. In this paper, we formalize the BT Grounding problem: the automated construction of a complete and consistent BT system. We analyze its complexity and introduce CABTO (Context-Aware Behavior Tree grOunding), the first framework to efficiently solve this challenge. CABTO leverages pre-trained Large Models (LMs) to heuristically search the space of action models and control policies, guided by contextual feedback from BT planners and environmental observations. Experiments spanning seven task sets across three distinct robotic manipulation scenarios demonstrate CABTO’s effectiveness and efficiency in generating complete and consistent behavior tree systems.

Valerio Borelli, Alfonso Gerevini, Enrico Scala, Ivan Serina

In this paper, we investigate the application of heuristics based on Graph Neural Networks (GNNs) to lifted numeric planning problems, an area that has been relatively unexplored. Building upon the GNN approach for learning general policies proposed by Ståhlberg, Bonet, and Geffner (2022b), we extend the architecture to make it sensitive to the numeric components inherent in the planning problems we address. We achieve this by observing that, although the state space of a numeric planning problem is infinite, the finite subgoal structure of the problem can be incorporated into the architecture, enabling the construction of a finite structure. Instead of learning general policies, we train our models to serve as heuristics within a best-first search algorithm. We explore various configurations of this architecture and demonstrate that the resulting heuristics are highly informative and, in certain domains, offer a better trade-off between guidance and computational cost compared to state-of-the-art heuristics.

Shuyang Jiang, Yusheng Liao, Zhe Chen, Ya Zhang, Yanfeng Wang, Yu Wang

Medical language models face critical barriers to real-world clinical reasoning applications. However, mainstream efforts, which fall short in task coverage, lack fine-grained supervision for intermediate reasoning steps, and rely on proprietary systems, are still far from a versatile, credible and efficient language model for clinical reasoning usage. To this end, we propose MedS3, a self-evolving framework that imparts robust reasoning capabilities to small, deployable models. Starting with 8,000 curated instances sampled via a curriculum strategy across five medical domains and 16 datasets, we use a small base policy model to conduct Monte Carlo Tree Search (MCTS) for constructing rule-verifiable reasoning trajectories. Self-explored reasoning trajectories ranked by node values are used to bootstrap the policy model via reinforcement fine-tuning and preference learning. Moreover, we introduce a soft dual process reward model that incorporates value dynamics: steps that degrade node value are penalized, enabling fine-grained identification of reasoning errors even when the final answer is correct. Experiments on eleven benchmarks show that MedS3 outperforms the previous state-of-the-art medical model by +6.45 accuracy points and surpasses 32B-scale general-purpose reasoning models by +8.57 points. Additional empirical analysis further demonstrates that MedS3 achieves robust and faithful reasoning behavior.

Yue Fang, Yuxin Guo, Jiaran Gao, Hongxin Ding, Xinke Jiang, Weibin Liao, Yongxin Xu, Yinghao Zhu, Zhibang Yang, Liantao Ma 等

Improving large language models (LLMs) for electronic health record (EHR) reasoning is essential for enabling accurate and generalizable clinical predictions. While LLMs excel at medical text understanding, they underperform on EHR-based prediction tasks due to challenges in modeling temporally structured, high-dimensional data. Existing approaches often rely on hybrid paradigms, where LLMs serve merely as frozen prior retrievers while downstream deep learning (DL) models handle prediction, failing to improve the LLM’s intrinsic reasoning capacity and inheriting the generalization limitations of DL models. To this end, we propose EAG-RL, a novel two-stage training framework designed to intrinsically enhance LLMs’ EHR reasoning ability through expert attention guidance, where expert EHR models refer to task-specific DL models trained on EHR data. Concretely, EAG-RL first constructs high-quality, stepwise reasoning trajectories using expert-guided Monte Carlo Tree Search to effectively initialize the LLM’s policy. Then, EAG-RL further optimizes the policy via reinforcement learning by aligning the LLM’s attention with clinically salient features identified by expert EHR models. Extensive experiments on two real-world EHR datasets show that EAG-RL improves the intrinsic EHR reasoning ability of LLMs by an average of 14.62%, while also enhancing robustness to feature perturbations and generalization to unseen clinical domains. These results demonstrate the practical potential of EAG-RL for real-world deployment in clinical prediction tasks.

Bingyu Yan, Xiaoming Zhang, Ziyi Zhou, Chaozhuo Li, Ruilin Zeng, Yirui Qi, Tianbo Wang, Litian Zhang

Large language model-based multi-agent systems (LLM-MAS) effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantial safety vulnerabilities. Existing attack methods targeting LLM-MAS either compromise agent internals or rely on direct and overt persuasion, which limit their effectiveness, adaptability, and stealthiness. In this paper, we propose MAST, a Multi-round Adaptive Stealthy Tampering framework designed to exploit communication vulnerabilities within the system. MAST integrates Monte Carlo Tree Search with Direct Preference Optimization to train an attack policy model that adaptively generates effective multi-round tampering strategies. Furthermore, to preserve stealthiness, we impose dual semantic and embedding similarity constraints during the tampering process. Comprehensive experiments across diverse tasks, communication architectures, and LLMs demonstrate that MAST consistently achieves high attack success rates while significantly enhancing stealthiness compared to baselines. These findings highlight the effectiveness, stealthiness, and adaptability of MAST, underscoring the need for robust communication safeguards in LLM-MAS.

Thomy Phan, Sven Koenig

Multi-agent path finding (MAPF) is the challenging problem of finding conflict-free paths with minimal costs for multiple agents. While traditional MAPF solvers are centralized using heuristic search, reinforcement learning (RL) is becoming increasingly popular due to its potential to learn decentralized and generalizing policies. RL-based MAPF must cope with spatial coordination, which is often addressed by combining independent training with ad hoc measures like replanning and communication. Such ad hoc measures often complicate the approach and require knowledge beyond the actual accessible information in RL, such as the full map occupation or broadcast communication channels, which limits generalizability, effectiveness, and sample efficiency. In this paper, we propose Partitioned Attention-based Reverse Curricula for Enhanced Learning (PARCEL), considering a bounding region for each agent. PARCEL trains all agents with overlapping regions jointly via self-attention to avoid potential conflicts. By employing a reverse curriculum, where the bounding regions grow as the policies improve, all agents will eventually merge into a single coordinated group. We evaluate PARCEL in two simple coordination tasks and four MAPF benchmark maps. Compared with state-of-the-art RL-based MAPF methods, PARCEL demonstrates better effectiveness and sample efficiency without ad hoc measures.

Rishabh Jain, Keisuke Okumura, Michael Amir, Amanda Prorok

Finding near-optimal solutions for dense multi-agent pathfinding (MAPF) problems in real-time remains challenging even for state-of-the-art planners. To this end, we develop a hybrid framework that integrates a learned heuristic derived from MAGAT, a neural MAPF policy with a graph attention scheme, into a leading search-based algorithm, LaCAM. While prior work has explored learning-guided search in MAPF, such methods have historically underperformed. In contrast, our approach, termed LaGAT, outperforms both purely search-based and purely learning-based methods in dense scenarios. This is achieved through an enhanced MAGAT architecture, a pre-train–then–fine-tune strategy on maps of interest, and a deadlock detection scheme to account for imperfect neural guidance. Our results demonstrate that, when carefully designed, hybrid search offers a powerful solution for tightly coupled, challenging multi-agent coordination problems.

Saptarshi Nath, Christos Peridis, Eseoghene Benjamin, Xinran Liu, Soheil Kolouri, Peter Kinnell, Zexin Li, Cong Liu, Shirin Dora, Andrea Soltoggio

Agentic AI aims to create systems that set their own goals, adapt proactively to change, and refine behavior through continuous experience. Recent advances suggest that, when facing multiple and unforeseen tasks, agents could benefit from sharing machine-learned knowledge and reusing policies that have already been fully or partially learned by other agents. However, how to query, select, and retrieve policies from a pool of agents, and how to integrate such policies remains a largely unexplored area. This study explores how an agent decides what knowledge to select, from whom, and when and how to integrate it in its own policy in order to accelerate its own learning. The proposed algorithm, Modular Sharing and Composition in Collective Learning (MOSAIC), improves learning in agentic collectives by combining (1) knowledge selection using performance signals and cosine similarity on Wasserstein task embeddings, (2) modular and transferable neural representations via masks, and (3) policy integration, composition and fine-tuning. MOSAIC outperforms isolated learners and global sharing approaches in both learning speed and overall performance, and in some cases solves tasks that isolated agents cannot. The results also demonstrate that selective, goal-driven reuse leads to less susceptibility to task interference. We also observe the emergence of self-organization, where agents solving simpler tasks accelerate the learning of harder ones through shared knowledge.

Abdelouahed Ben Mhamed, Assia Kamal Idrissi, Amal Seghrouchni

Branch-and-Bound (B&B) is the dominant exact solution method for Mixed Integer Linear Programs (MILP), yet its exponential time complexity poses significant challenges for large-scale instances. The growing capabilities of machine learning have spurred efforts to improve B&B by learning data-driven branching policies. However, most existing approaches rely on Imitation Learning (IL), which tends to overfit to expert demonstrations and struggles to generalize to structurally diverse or unseen instances. In this work, we propose Tree-Gate Proximal Policy Optimization (TGPPO), a novel framework that employs Proximal Policy Optimization (PPO), a Reinforcement Learning (RL) algorithm, to train a branching policy aimed at improving generalization across heterogeneous MILP instances. Our approach builds on a parameterized state space representation that dynamically captures the evolving context of the search tree. Empirical evaluations show that TGPPO often outperforms existing learning-based policies in terms of reducing the number of nodes explored and improving p-Primal-Dual Integrals (PDI), particularly in out-of-distribution instances. These results highlight the potential of RL to develop robust and adaptable branching strategies for MILP solvers.