Actor-critic algorithms for deep multi-agent reinforcement learning (MARL) typically employ a policy update that responds to the current strategies of other agents. While being straightforward, this approach does not account for the updates of other agents at the same update step, resulting in miscoordination. In this paper, we introduce the $K$-Level Policy Gradient (KPG), a method that recursively updates each agent against the updated policies of other agents, speeding up the discovery of effective coordinated policies. We theoretically prove that KPG with finite iterates achieves monotonic convergence to a local Nash equilibrium under certain conditions. We provide principled implementations of KPG by applying it to the deep MARL algorithms MAPPO, MADDPG, and FACMAC. Empirically, we demonstrate superior performance over existing deep MARL algorithms in StarCraft II and multi-agent MuJoCo.

Personal use of this material is permitted. Abstract--Conventional autonomous trading systems struggle to balance computational efficiency and market responsiveness due to their fixed operating frequency. We propose Hi-DARTS, a hierarchical multi-agent reinforcement learning framework that addresses this trade-off. Hi-DARTS utilizes a meta-agent to analyze market volatility and dynamically activate specialized Time Frame Agents for high-frequency or low-frequency trading as needed. During back-testing on AAPL stock from January 2024 to May 2025, Hi-DARTS yielded a cumulative return of 25.17% with a Sharpe Ratio of 0.75. Our work demonstrates that dynamic, hierarchical agents can achieve superior risk-adjusted returns while maintaining high computational efficiency.

In high-stakes disaster scenarios, timely and informed decision-making is critical yet often challenged by uncertainty, dynamic environments, and limited resources. This paper presents a systematic review of Human-AI collaboration patterns that support decision-making across all disaster management phases. Drawing from 51 peer-reviewed studies, we identify four major categories: Human-AI Decision Support Systems, Task and Resource Coordination, Trust and Transparency, and Simulation and Training. Within these, we analyze sub-patterns such as cognitive-augmented intelligence, multi-agent coordination, explainable AI, and virtual training environments. Our review highlights how AI systems may enhance situational awareness, improves response efficiency, and support complex decision-making, while also surfacing critical limitations in scalability, interpretability, and system interoperability. We conclude by outlining key challenges and future research directions, emphasizing the need for adaptive, trustworthy, and context-aware Human-AI systems to improve disaster resilience and equitable recovery outcomes.

We show that coherent, long-form musical composition can emerge from a decentralized swarm of identical, frozen foundation models that coordinate via stigmergic, peer-to-peer signals, without any weight updates. We compare a centralized multi-agent system with a global critic to a fully decentralized swarm in which bar-wise agents sense and deposit harmonic, rhythmic, and structural cues, adapt short-term memory, and reach consensus. Across symbolic, audio, and graph-theoretic analyses, the swarm yields superior quality while delivering greater diversity and structural variety and leads across creativity metrics. The dynamics contract toward a stable configuration of complementary roles, and self-similarity networks reveal a small-world architecture with efficient long-range connectivity and specialized bridging motifs, clarifying how local novelties consolidate into global musical form. By shifting specialization from parameter updates to interaction rules, shared memory, and dynamic consensus, MusicSwarm provides a compute- and data-efficient route to long-horizon creative structure that is immediately transferable beyond music to collaborative writing, design, and scientific discovery.

Abstract-- Simulating hostile attacks of physical autonomous systems can be a useful tool to examine their robustness to attack and inform vulnerability-aware design. In this work, we examine this through the lens of multi-robot patrol, by presenting a machine learning-based adversary model that observes robot patrol behavior in order to attempt to gain undetected access to a secure environment within a limited time duration. Such a model allows for evaluation of a patrol system against a realistic potential adversary, offering insight into future patrol strategy design. We show that our new model outperforms existing baselines, thus providing a more stringent test, and examine its performance against multiple leading decentralized multi-robot patrol strategies. Security in automated and robotic systems is of increasing importance as these systems becomes more pervasive and integrated throughout society. Beyond the obvious considerations of cybersecurity and communication security, an important facet of this is physical security -- the robustness of these systems to interference in the real world from a hostile actor.

Healthcare and medicine are multimodal disciplines that deal with multimodal data for reasoning and diagnosing multiple diseases. Although some multimodal reasoning models have emerged for reasoning complex tasks in scientific domains, their applications in the healthcare domain remain limited and fall short in correct reasoning for diagnosis. To address the challenges of multimodal medical reasoning for correct diagnosis and assist the healthcare professionals, a novel temporal graph-based reasoning process modelled through a directed graph has been proposed in the current work. It helps in accommodating dynamic changes in reasons through backtracking, refining the reasoning content, and creating new or deleting existing reasons to reach the best recommendation or answer. Again, consideration of multimodal data at different time points can enable tracking and analysis of patient health and disease progression. Moreover, the proposed multi-agent temporal reasoning framework provides task distributions and a cross-validation mechanism to further enhance the accuracy of reasoning outputs. A few basic experiments and analysis results justify the novelty and practical utility of the proposed preliminary approach.

Visual documentation is an effective tool for reducing the cognitive barrier developers face when understanding unfamiliar code, enabling more intuitive comprehension. Compared to textual documentation, it provides a higher-level understanding of the system structure and data flow. Developers usually prefer visual representations over lengthy textual descriptions for large software systems. Visual documentation is both difficult to produce and challenging to evaluate. Manually creating it is time-consuming, and currently, no existing approach can automatically generate high-level visual documentation directly from code. Its evaluation is often subjective, making it difficult to standardize and automate. To address these challenges, this paper presents the first exploration of using agentic LLM systems to automatically generate visual documentation. We introduce VisDocSketcher, the first agent-based approach that combines static analysis with LLM agents to identify key elements in the code and produce corresponding visual representations. We propose a novel evaluation framework, AutoSketchEval, for assessing the quality of generated visual documentation using code-level metrics. The experimental results show that our approach can valid visual documentation for 74.4% of the samples. It shows an improvement of 26.7-39.8% over a simple template-based baseline. Our evaluation framework can reliably distinguish high-quality (code-aligned) visual documentation from low-quality (non-aligned) ones, achieving an AUC exceeding 0.87. Our work lays the foundation for future research on automated visual documentation by introducing practical tools that not only generate valid visual representations but also reliably assess their quality.

Current AI writing support tools are largely designed for individuals, complicating collaboration when co-writers must leave the shared workspace to use AI and then communicate and reintegrate results. We propose integrating AI agents directly into collaborative writing environments. Our prototype makes AI use transparent and customisable through two new shared objects: agent profiles and tasks. Agent responses appear in the familiar comment feature. In a user study (N=30), 14 teams worked on writing projects during one week. Interaction logs and interviews show that teams incorporated agents into existing norms of authorship, control, and coordination, rather than treating them as team members. Agent profiles were viewed as personal territory, while created agents and outputs became shared resources. We discuss implications for team-based AI interaction, highlighting opportunities and boundaries for treating AI as a shared resource in collaborative work.

Persian names present unique challenges for natural language processing applications, particularly in gender detection and digital identity creation, due to transliteration inconsistencies and cultural-specific naming patterns. Existing tools exhibit significant performance degradation on Persian names, while the scarcity of comprehensive datasets further compounds these limitations. To address these challenges, the present research introduces PNGT-26K, a comprehensive dataset of Persian names, their commonly associated gender, and their English transliteration, consisting of approximately 26,000 tuples. As a demonstration of how this resource can be utilized, we also introduce two frameworks, namely Open Gender Detection and Nominalist. Open Gender Detection is a production-grade, ready-to-use framework for using existing data from a user, such as profile photo and name, to give a probabilistic guess about the person's gender. Nominalist, the second framework introduced by this paper, utilizes agentic AI to help users choose a username for their social media accounts on any platform. It can be easily integrated into any website to provide a better user experience. The PNGT-26K dataset, Nominalist and Open Gender Detection frameworks are publicly available on Github.

Pogobots are a new type of open-source/open-hardware robots specifically designed for swarm robotics research. Their cost-effective and modular design, complemented by vibration-based and wheel-based locomotion, fast infrared communication and extensive software architecture facilitate the implementation of swarm intelligence algorithms. However, testing even simple distributed algorithms directly on robots is particularly labor-intensive. Scaling to more complex problems or calibrate user code parameters will have a prohibitively high strain on available resources. In this article we present Pogosim, a fast and scalable simulator for Pogobots, designed to reduce as much as possible algorithm development costs. The exact same code will be used in both simulation and to experimentally drive real robots. This article details the software architecture of Pogosim, explain how to write configuration files and user programs and how simulations approximate or differ from experiments. We describe how a large set of simulations can be launched in parallel, how to retrieve and analyze the simulation results, and how to optimize user code parameters using optimization algorithms.