With the widespread application of large AI models in various fields, the automation level of multi-agent systems has been continuously improved. However, in high-risk decision-making scenarios such as healthcare and finance, human participation and the alignment of intelligent systems with human intentions remain crucial. This paper focuses on the financial scenario and constructs a multi-agent brainstorming framework based on the BDI theory. A human-computer collaborative multi-agent financial analysis process is built using Streamlit. The system plans tasks according to user intentions, reduces users' cognitive load through real-time updated structured text summaries and the interactive Cothinker module, and reasonably integrates general and reasoning large models to enhance the ability to handle complex problems. By designing a quantitative analysis algorithm for the sentiment tendency of interview content based on LLMs and a method for evaluating the diversity of ideas generated by LLMs in brainstorming based on k-means clustering and information entropy, the system is comprehensively evaluated. The results of human factors testing show that the system performs well in terms of usability and user experience. Although there is still room for improvement, it can effectively support users in completing complex financial tasks. The research shows that the system significantly improves the efficiency of human-computer interaction and the quality of decision-making in financial decision-making scenarios, providing a new direction for the development of related fields.

Free-form protocols are essential for AI's task generalization but enable new threats like secret collusion and coordinated swarm attacks. Network effects can rapidly spread privacy breaches, disinformation, jailbreaks, and data poisoning, while multi-agent dispersion and stealth optimization help adversaries evade oversight--creating novel persistent threats at a systemic level. Despite their critical importance, these security challenges remain understudied, with research fragmented across disparate fields including AI security, multi-agent learning, complex systems, cybersecurity, game theory, distributed systems, and technical AI governance. We introduce multi-agent security, a new field dedicated to securing networks of decentralized AI agents against threats that emerge or amplify through their interactions--whether direct or indirect via shared environments--with each other, humans, and institutions, and characterise fundamental security-performance trade-offs. Our preliminary work (1) taxonomizes the threat landscape arising from interacting AI agents, (2) surveys security-performance tradeoffs in decentralized AI systems, and (3) proposes a unified research agenda addressing open challenges in designing secure agent systems and interaction environments. By identifying these gaps, we aim to guide research in this critical area to unlock the socioeconomic potential of large-scale agent deployment on the internet, foster public trust, and mitigate national security risks in critical infrastructure and defense contexts.Figure 1: Multi-agent threats demand multi-agent security: [Left] Two malicious AI agents (Mallory and Trudy) are interacting with a human user (Bob) through a shared message board seemingly innocuously to the overseer (magnifying glass).

Air traffic can be significantly disrupted by weather. Pathfinder operations involve assigning a designated aircraft to assess whether airspace that was previously impacted by weather can be safely traversed through. Despite relatively routine use in air traffic control, there is little research on the underlying multi-agent decision-making problem. We seek to address this gap herein by formulating decision models to capture the operational dynamics and implications of pathfinders. Specifically, we construct a Markov chain to represent the stochastic transitions between key operational states (e.g., pathfinder selection). We then analyze its steady-state behavior to understand long-term system dynamics. We also propose models to characterize flight-specific acceptance behaviors (based on utility trade-offs) and pathfinder selection strategies (based on sequential offer allocations). We then conduct a worst-case scenario analysis that highlights risks from collective rejection and explores how selfless behavior and uncertainty affect system resilience. Empirical analysis of data from the US Federal Aviation Administration demonstrates the real-world significance of pathfinder operations and informs future model calibration.

Multi-Agent Reinforcement Learning (MARL) has become a powerful framework for numerous real-world applications, modeling distributed decision-making and learning from interactions with complex environments. Resource Allocation Optimization (RAO) benefits significantly from MARL's ability to tackle dynamic and decentralized contexts. MARL-based approaches are increasingly applied to RAO challenges across sectors playing pivotal roles to Industry 4.0 developments. This survey provides a comprehensive review of recent MARL algorithms for RAO, encompassing core concepts, classifications, and a structured taxonomy. By outlining the current research landscape and identifying primary challenges and future directions, this survey aims to support researchers and practitioners in leveraging MARL's potential to advance resource allocation solutions.

Developing scalable and efficient reinforcement learning algorithms for cooperative multi-agent control has received significant attention over the past years. Existing literature has proposed inexact decompositions of local Q-functions based on empirical information structures between the agents. In this paper, we exploit inter-agent coupling information and propose a systematic approach to exactly decompose the local Q-function of each agent. We develop an approximate least square policy iteration algorithm based on the proposed decomposition and identify two architectures to learn the local Q-function for each agent. We establish that the worst-case sample complexity of the decomposition is equal to the centralized case and derive necessary and sufficient graphical conditions on the inter-agent couplings to achieve better sample efficiency. We demonstrate the improved sample efficiency and computational efficiency on numerical examples.

We investigate reinforcement learning in the setting of Markov decision processes for a large number of exchangeable agents interacting in a mean field manner. Applications include, for example, the control of a large number of robots communicating through a central unit dispatching the optimal policy computed by maximizing an aggregate reward. An approximate solution is obtained by learning the optimal policy of a generic agent interacting with the statistical distribution of the states and actions of the other agents. We first provide a full analysis this discrete-time mean field control problem. We then rigorously prove the convergence of exact and model-free policy gradient methods in a mean-field linear-quadratic setting and establish bounds on the rates of convergence. We also provide graphical evidence of the convergence based on implementations of our algorithms.

Large language models and autonomous AI agents have evolved rapidly, resulting in a diverse array of evaluation benchmarks, frameworks, and collaboration protocols. However, the landscape remains fragmented and lacks a unified taxonomy or comprehensive survey. Therefore, we present a side-by-side comparison of benchmarks developed between 2019 and 2025 that evaluate these models and agents across multiple domains. In addition, we propose a taxonomy of approximately 60 benchmarks that cover general and academic knowledge reasoning, mathematical problem-solving, code generation and software engineering, factual grounding and retrieval, domain-specific evaluations, multimodal and embodied tasks, task orchestration, and interactive assessments. Furthermore, we review AI-agent frameworks introduced between 2023 and 2025 that integrate large language models with modular toolkits to enable autonomous decision-making and multi-step reasoning. Moreover, we present real-world applications of autonomous AI agents in materials science, biomedical research, academic ideation, software engineering, synthetic data generation, chemical reasoning, mathematical problem-solving, geographic information systems, multimedia, healthcare, and finance. We then survey key agent-to-agent collaboration protocols, namely the Agent Communication Protocol (ACP), the Model Context Protocol (MCP), and the Agent-to-Agent Protocol (A2A). Finally, we discuss recommendations for future research, focusing on advanced reasoning strategies, failure modes in multi-agent LLM systems, automated scientific discovery, dynamic tool integration via reinforcement learning, integrated search capabilities, and security vulnerabilities in agent protocols.

In the trajectory planning of automated driving, data-driven statistical artificial intelligence (AI) methods are increasingly established for predicting the emergent behavior of other road users. While these methods achieve exceptional performance in defined datasets, they usually rely on the independent and identically distributed (i.i.d.) assumption and thus tend to be vulnerable to distribution shifts that occur in the real world. In addition, these methods lack explainability due to their black box nature, which poses further challenges in terms of the approval process and social trustworthiness. Therefore, in order to use the capabilities of data-driven statistical AI methods in a reliable and trustworthy manner, the concept of TrustMHE is introduced and investigated in this paper. TrustMHE represents a complementary approach, independent of the underlying AI systems, that combines AI-driven out-of-distribution detection with control-driven moving horizon estimation (MHE) to enable not only detection and monitoring, but also intervention. The effectiveness of the proposed TrustMHE is evaluated and proven in three simulation scenarios.

Collaboration is ubiquitous and essential in day-to-day life -- from exchanging ideas, to delegating tasks, to generating plans together. This work studies how LLMs can adaptively collaborate to perform complex embodied reasoning tasks. To this end we introduce MINDcraft, an easily extensible platform built to enable LLM agents to control characters in the open-world game of Minecraft; and MineCollab, a benchmark to test the different dimensions of embodied and collaborative reasoning. An experimental study finds that the primary bottleneck in collaborating effectively for current state-of-the-art agents is efficient natural language communication, with agent performance dropping as much as 15% when they are required to communicate detailed task completion plans. We conclude that existing LLM agents are ill-optimized for multi-agent collaboration, especially in embodied scenarios, and highlight the need to employ methods beyond in-context and imitation learning. Our website can be found here: https://mindcraft-minecollab.github.io/

Rapid progress in intelligent unmanned systems has presented new opportunities for mobile crowd sensing (MCS). Today, heterogeneous air-ground collaborative multi-agent framework, which comprise unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs), have presented superior flexibility and efficiency compared to traditional homogeneous frameworks in complex sensing tasks. Within this context, task allocation among different agents always play an important role in improving overall MCS quality. In order to better allocate tasks among heterogeneous collaborative agents, in this paper, we investigated two representative complex multi-agent task allocation scenarios with dual optimization objectives: (1) For AG-FAMT (Air-Ground Few Agents More Tasks) scenario, the objectives are to maximize the task completion while minimizing the total travel distance; (2) For AG-MAFT (Air-Ground More Agents Few Tasks) scenario, where the agents are allocated based on their locations, has the optimization objectives of minimizing the total travel distance while reducing travel time cost. To achieve this, we proposed a Multi-Task Minimum Cost Maximum Flow (MT-MCMF) optimization algorithm tailored for AG-FAMT, along with a multi-objective optimization algorithm called W-ILP designed for AG-MAFT, with a particular focus on optimizing the charging path planning of UAVs. Our experiments based on a large-scale real-world dataset demonstrated that the proposed two algorithms both outperform baseline approaches under varying experimental settings, including task quantity, task difficulty, and task distribution, providing a novel way to improve the overall quality of mobile crowdsensing tasks.