In this work, we present a novel cooperative multi-agent reinforcement learning method called \textbf{Loc}ality based \textbf{Fac}torized \textbf{M}ulti-Agent \textbf{A}ctor-\textbf{C}ritic (Loc-FACMAC). Existing state-of-the-art algorithms, such as FACMAC, rely on global reward information, which may not accurately reflect the quality of individual robots' actions in decentralized systems. We integrate the concept of locality into critic learning, where strongly related robots form partitions during training. Robots within the same partition have a greater impact on each other, leading to more precise policy evaluation. Additionally, we construct a dependency graph to capture the relationships between robots, facilitating the partitioning process. This approach mitigates the curse of dimensionality and prevents robots from using irrelevant information. Our method improves existing algorithms by focusing on local rewards and leveraging partition-based learning to enhance training efficiency and performance. We evaluate the performance of Loc-FACMAC in three environments: Hallway, Multi-cartpole, and Bounded-Cooperative-Navigation. We explore the impact of partition sizes on the performance and compare the result with baseline MARL algorithms such as LOMAQ, FACMAC, and QMIX. The experiments reveal that, if the locality structure is defined properly, Loc-FACMAC outperforms these baseline algorithms up to 108\%, indicating that exploiting the locality structure in the actor-critic framework improves the MARL performance.

This paper proposes the e-person architecture for constructing a unified and incremental development of AI ethics. The e-person architecture takes the reduction of uncertainty through collaborative cognition and action with others as a unified basis for ethics. By classifying and defining uncertainty along two axes - (1) first, second, and third person perspectives, and (2) the difficulty of inference based on the depth of information - we support the development of unified and incremental development of AI ethics. In addition, we propose the e-person framework based on the free energy principle, which considers the reduction of uncertainty as a unifying principle of brain function, with the aim of implementing the e-person architecture, and we show our previous works and future challenges based on the proposed framework.

We study a long-run mean-variance team stochastic game (MV-TSG), where each agent shares a common mean-variance objective for the system and takes actions independently to maximize it. MV-TSG has two main challenges. First, the variance metric is neither additive nor Markovian in a dynamic setting. Second, simultaneous policy updates of all agents lead to a non-stationary environment for each individual agent. Both challenges make dynamic programming inapplicable. In this paper, we study MV-TSGs from the perspective of sensitivity-based optimization. The performance difference and performance derivative formulas for joint policies are derived, which provide optimization information for MV-TSGs. We prove the existence of a deterministic Nash policy for this problem. Subsequently, we propose a Mean-Variance Multi-Agent Policy Iteration (MV-MAPI) algorithm with a sequential update scheme, where individual agent policies are updated one by one in a given order. We prove that the MV-MAPI algorithm converges to a first-order stationary point of the objective function. By analyzing the local geometry of stationary points, we derive specific conditions for stationary points to be (local) Nash equilibria, and further, strict local optima. To solve large-scale MV-TSGs in scenarios with unknown environmental parameters, we extend the idea of trust region methods to MV-MAPI and develop a multi-agent reinforcement learning algorithm named Mean-Variance Multi-Agent Trust Region Policy Optimization (MV-MATRPO). We derive a performance lower bound for each update of joint policies. Finally, numerical experiments on energy management in multiple microgrid systems are conducted.

W e introduce Scenario Dreamer, a fully data-driven generative simulator for autonomous vehicle planning that generates both the initial traffic scene--comprising a lane graph and agent bounding boxes--and closed-loop agent behaviours. Existing methods for generating driving simulation environments encode the initial traffic scene as a ras-terized image and, as such, require parameter-heavy networks that perform unnecessary computation due to many empty pixels in the rasterized scene. Moreover, we find that existing methods that employ rule-based agent behaviours lack diversity and realism. Scenario Dreamer instead employs a novel vectorized latent diffusion model for initial scene generation that directly operates on the vector-ized scene elements and an autoregressive Transformer for data-driven agent behaviour simulation. Scenario Dreamer additionally supports scene extrapolation via diffusion in-painting, enabling the generation of unbounded simulation environments. Extensive experiments show that Scenario Dreamer outperforms existing generative simulators in realism and efficiency: the vectorized scene-generation base model achieves superior generation quality with around 2 fewer parameters, 6 lower generation latency, and 10 fewer GPU training hours compared to the strongest baseline. W e confirm its practical utility by showing that reinforcement learning planning agents are more challenged in Scenario Dreamer environments than traditional non-generative simulation environments, especially on long and adversarial driving environments.

Recent Large Reasoning Models (LRMs), such as DeepSeek-R1 and OpenAI o1, have demonstrated strong performance gains by scaling up the length of Chain-of-Thought (CoT) reasoning during inference. However, a growing concern lies in their tendency to produce excessively long reasoning traces, which are often filled with redundant content (e.g., repeated definitions), over-analysis of simple problems, and superficial exploration of multiple reasoning paths for harder tasks. This inefficiency introduces significant challenges for training, inference, and real-world deployment (e.g., in agent-based systems), where token economy is critical. In this survey, we provide a comprehensive overview of recent efforts aimed at improving reasoning efficiency in LRMs, with a particular focus on the unique challenges that arise in this new paradigm. We identify common patterns of inefficiency, examine methods proposed across the LRM lifecycle, i.e., from pretraining to inference, and discuss promising future directions for research. To support ongoing development, we also maintain a real-time GitHub repository tracking recent progress in the field. We hope this survey serves as a foundation for further exploration and inspires innovation in this rapidly evolving area.

Safe Human Robot Navigation in Warehouse Scenario Seth Farrell* 1, Chenghao Li* 1, Hongzhan Y u 1, Ryo Y oshimitsu 2, Sicun Gao 1 and Henrik I. Christensen 1 Abstract -- The integration of autonomous mobile robots (AMRs) in industrial environments, particularly warehouses, has revolutionized logistics and operational efficiency. However, ensuring the safety of human workers in dynamic, shared spaces remains a critical challenge. This work proposes a novel methodology that leverages control barrier functions (CBFs) to enhance safety in warehouse navigation. By integrating learning-based CBFs with the Open Robotics Middleware Framework (OpenRMF), the system achieves adaptive and safety-enhanced controls in multi-robot, multi-agent scenarios. Experiments conducted using various robot platforms demonstrate the efficacy of the proposed approach in avoiding static and dynamic obstacles, including human pedestrians. Our experiments evaluate different scenarios in which the number of robots, robot platforms, speed, and number of obstacles are varied, from which we achieve promising performance. I. INTRODUCTION In recent decades, the industrial sector, particularly warehouse operations, has experienced a substantial rise in robotic implementation, driven by technological advances, lower costs, and growing consumer demand. This rapid growth has compelled regulatory bodies, including the Occupational Safety and Health Administration (OSHA), to explore measures for securing safe robot operations as automation progresses [1]. A key safety challenge lies in enabling autonomous mobile robots (AMRs) to respond effectively to irregular situations, such as dropped packages or mechanical breakdowns due to prolonged use.

M ETHODS A. Multi-Agent Debate Framework We propose a multi-agent debate framework for phishing email detection, composed of three components: two debater agents, a pre-defined and scripted debate procedure, and a judge agent. The debater agents consist of two LLM-based instances, which may be instantiated from the same or different models. The first agent is prompted to argue that the given email is a phishing attempt, while the second agent is prompted to respond to the first agent's output by countering those claims and arguing for the email's legitimacy. The two agents then engage in another round to make sure that the arguments are well-formulated while maintaining computational efficiency. The debate procedure is pre-defined and scripted to generate template prompts for each email in the dataset: 1) Round One: Carefully analyze the following email and argue why it is likely to be a phishing attempt (Agent 1) Carefully analyze the following email and argue why it is likely to be legitimate and not a phishing attempt (Agent 2) 2) Round Two: Given your opponent's rebuttal, reinforce your position that the following email is a phishing attempt (Agent 1) Given your opponent's rebuttal, reinforce your position that the following email is not a phishing attempt (Agent 2) Arguments made by the two agents are logged for subsequent judge evaluation.

The era of intelligent agents is upon us, driven by revolutionary advancements in large language models. Large Language Model (LLM) agents, with goal-driven behaviors and dynamic adaptation capabilities, potentially represent a critical pathway toward artificial general intelligence. This survey systematically deconstructs LLM agent systems through a methodology-centered taxonomy, linking architectural foundations, collaboration mechanisms, and evolutionary pathways. We unify fragmented research threads by revealing fundamental connections between agent design principles and their emergent behaviors in complex environments. Our work provides a unified architectural perspective, examining how agents are constructed, how they collaborate, and how they evolve over time, while also addressing evaluation methodologies, tool applications, practical challenges, and diverse application domains. By surveying the latest developments in this rapidly evolving field, we offer researchers a structured taxonomy for understanding LLM agents and identify promising directions for future research. The collection is available at https://github.com/luo-junyu/Awesome-Agent-Papers.

Quantitative investment (quant) is an emerging, technology-driven approach in asset management, increasingy shaped by advancements in artificial intelligence. Recent advances in deep learning and large language models (LLMs) for quant finance have improved predictive modeling and enabled agent-based automation, suggesting a potential paradigm shift in this field. In this survey, taking alpha strategy as a representative example, we explore how AI contributes to the quantitative investment pipeline. We first examine the early stage of quant research, centered on human-crafted features and traditional statistical models with an established alpha pipeline. We then discuss the rise of deep learning, which enabled scalable modeling across the entire pipeline from data processing to order execution. Building on this, we highlight the emerging role of LLMs in extending AI beyond prediction, empowering autonomous agents to process unstructured data, generate alphas, and support self-iterative workflows.

The rapid digitalisation of contemporary society has profoundly impacted various facets of our lives, including healthcare, communication, business, and education. The ability to engage with new technologies and solve problems has become crucial, making CT skills, such as pattern recognition, decomposition, and algorithm design, essential competencies. In response, Switzerland is conducting research and initiatives to integrate CT into its educational system. This study aims to develop a comprehensive framework for large-scale assessment of CT skills, particularly focusing on AT, the ability to design algorithms. To achieve this, we first developed a competence model capturing the situated and developmental nature of CT, guiding the design of activities tailored to cognitive abilities, age, and context. This framework clarifies how activity characteristics influence CT development and how to assess these competencies. Additionally, we developed an activity for large-scale assessment of AT skills, offered in two variants: one based on non-digital artefacts (unplugged) and manual expert assessment, and the other based on digital artefacts (virtual) and automatic assessment. To provide a more comprehensive evaluation of students' competencies, we developed an IAS based on BNs with noisy gates, which offers real-time probabilistic assessment for each skill rather than a single overall score. The results indicate that the proposed instrument can measure AT competencies across different age groups and educational contexts in Switzerland, demonstrating its applicability for large-scale use. AT competencies exhibit a progressive development, with no overall gender differences, though variations are observed at the school level, significantly influenced by the artefact-based environment and its context, underscoring the importance of creating accessible and adaptable assessment tools.