Autonomy is a double-edged sword for AI agents, simultaneously unlocking transformative possibilities and serious risks. How can agent developers calibrate the appropriate levels of autonomy at which their agents should operate? We argue that an agent's level of autonomy can be treated as a deliberate design decision, separate from its capability and operational environment. In this work, we define five levels of escalating agent autonomy, characterized by the roles a user can take when interacting with an agent: operator, collaborator, consultant, approver, and observer. Within each level, we describe the ways by which a user can exert control over the agent and open questions for how to design the nature of user-agent interaction. We then highlight a potential application of our framework towards AI autonomy certificates to govern agent behavior in single- and multi-agent systems. We conclude by proposing early ideas for evaluating agents' autonomy. Our work aims to contribute meaningful, practical steps towards responsibly deployed and useful AI agents in the real world.

Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these systems be trusted to follow deployment policies in realistic environments, especially under attack? To investigate, we ran the largest public red-teaming competition to date, targeting 22 frontier AI agents across 44 realistic deployment scenarios. Participants submitted 1.8 million prompt-injection attacks, with over 60,000 successfully eliciting policy violations such as unauthorized data access, illicit financial actions, and regulatory noncompliance. We use these results to build the Agent Red Teaming (ART) benchmark - a curated set of high-impact attacks - and evaluate it across 19 state-of-the-art models. Nearly all agents exhibit policy violations for most behaviors within 10-100 queries, with high attack transferability across models and tasks. Importantly, we find limited correlation between agent robustness and model size, capability, or inference-time compute, suggesting that additional defenses are needed against adversarial misuse. Our findings highlight critical and persistent vulnerabilities in today's AI agents. By releasing the ART benchmark and accompanying evaluation framework, we aim to support more rigorous security assessment and drive progress toward safer agent deployment.

The rapid growth of crypto markets has opened new opportunities for investors, but at the same time exposed them to high volatility. To address the challenge of managing dynamic portfolios in such an environment, this paper presents a practical application of a multi-agent system designed to autonomously construct and evaluate crypto-asset allocations. Using data on daily frequencies of the ten most capitalized cryptocurrencies from 2020 to 2025, we compare two automated investment strategies. These are a static equal weighting strategy and a rolling-window optimization strategy, both implemented to maximize the evaluation metrics of the Modern Portfolio Theory (MPT), such as Expected Return, Sharpe and Sortino ratios, while minimizing volatility. Each step of the process is handled by dedicated agents, integrated through a collaborative architecture in Crew AI. The results show that the dynamic optimization strategy achieves significantly better performance in terms of risk-adjusted returns, both in-sample and out-of-sample. This highlights the benefits of adaptive techniques in portfolio management, particularly in volatile markets such as cryptocurrency markets. The following methodology proposed also demonstrates how multi-agent systems can provide scalable, auditable, and flexible solutions in financial automation.

Many real-world systems, such as transportation systems, ecological systems, and Internet systems, are complex systems. As an important tool for studying complex systems, computational experiments can map them into artificial society models that are computable and reproducible within computers, thereby providing digital and computational methods for quantitative analysis. In current research, the construction of individual agent models often ignores the long-term accumulative effect of memory mechanisms in the development process of agents, which to some extent causes the constructed models to deviate from the real characteristics of real-world systems. To address this challenge, this paper proposes an individual agent model based on a memory-learning collaboration mechanism, which implements hierarchical modeling of the memory mechanism and a multi-indicator evaluation mechanism. Through hierarchical modeling of the individual memory repository, the group memory repository, and the memory buffer pool, memory can be effectively managed, and knowledge sharing and dissemination between individuals and groups can be promoted. At the same time, the multi-indicator evaluation mechanism enables dynamic evaluation of memory information, allowing dynamic updates of information in the memory set and promoting collaborative decision-making between memory and learning. Experimental results show that, compared with existing memory modeling methods, the agents constructed by the proposed model demonstrate better decision-making quality and adaptability within the system. This verifies the effectiveness of the individual agent model based on the memory-learning collaboration mechanism proposed in this paper in improving the quality of individual-level modeling in artificial society modeling and achieving anthropomorphic characteristics.

Document Understanding (DU) in long-contextual scenarios with complex layouts remains a significant challenge in vision-language research. Although Large Vision-Language Models (LVLMs) excel at short-context DU tasks, their performance declines in long-context settings. A key limitation is the scarcity of fine-grained training data, particularly for low-resource languages such as Arabic. Existing state-of-the-art techniques rely heavily on human annotation, which is costly and inefficient. We propose a fully automated, multi-agent interactive framework to generate long-context questions efficiently. Our approach efficiently generates high-quality single- and multi-page questions for extensive English and Arabic documents, covering hundreds of pages across diverse domains. This facilitates the development of LVLMs with enhanced long-context understanding ability. Experimental results in this work have shown that our generated English and Arabic questions (\textbf{AraEngLongBench}) are quite challenging to major open- and close-source LVLMs. The code and data proposed in this work can be found in https://github.com/wangk0b/Multi_Agentic_QA_Long_Doc.git. Sample Question and Answer (QA) pairs and structured system prompts can be found in the Appendix.

Despite substantial progress in applying neural networks (NN) to multi-agent reinforcement learning (MARL) areas, they still largely suffer from a lack of transparency and interoperability. However, its implicit cooperative mechanism is not yet fully understood due to black-box networks. In this work, we study an interpretable value decomposition framework via concept bottleneck models, which promote trustworthiness by conditioning credit assignment on an intermediate level of human-like cooperation concepts. To address this problem, we propose a novel value-based method, named Concepts learning for Multi-agent Q-learning (CMQ), that goes beyond the current performance-vs-interpretability trade-off by learning interpretable cooperation concepts. CMQ represents each cooperation concept as a supervised vector, as opposed to existing models where the information flowing through their end-to-end mechanism is concept-agnostic. Intuitively, using individual action value conditioning on global state embeddings to represent each concept allows for extra cooperation representation capacity. Empirical evaluations on the StarCraft II micromanagement challenge and level-based foraging (LBF) show that CMQ achieves superior performance compared with the state-of-the-art counterparts. The results also demonstrate that CMQ provides more cooperation concept representation capturing meaningful cooperation modes, and supports test-time concept interventions for detecting potential biases of cooperation mode and identifying spurious artifacts that impact cooperation.

The Stable Roommates problems are characterized by the preferences of agents over other agents as roommates. A solution is a partition of the agents into pairs that are acceptable to each other (i.e., they are in the preference lists of each other), and the matching is stable (i.e., there do not exist any two agents who prefer each other to their roommates, and thus block the matching). Motivated by real-world applications, and considering that stable roommates problems do not always have solutions, we continue our studies to compute "good-enough" matchings. In addition to the agents' habits and habitual preferences, we consider their networks of preferred friends, and introduce a method to generate personalized solutions to stable roommates problems. We illustrate the usefulness of our method with examples and empirical evaluations.

Software development is a complex, multi-phase process traditionally requiring collaboration among individuals with diverse expertise. We propose AgentMesh, a Python-based framework that uses multiple cooperating LLM-powered agents to automate software development tasks. In AgentMesh, specialized agents - a Planner, Coder, Debugger, and Reviewer - work in concert to transform a high-level requirement into fully realized code. The Planner agent first decomposes user requests into concrete subtasks; the Coder agent implements each subtask in code; the Debugger agent tests and fixes the code; and the Reviewer agent validates the final output for correctness and quality. We describe the architecture and design of these agents and their communication, and provide implementation details including prompt strategies and workflow orchestration. A case study illustrates AgentMesh handling a non-trivial development request via sequential task planning, code generation, iterative debugging, and final code review. We discuss how dividing responsibilities among cooperative agents leverages the strengths of large language models while mitigating single-agent limitations. Finally, we examine current limitations - such as error propagation and context scaling - and outline future work toward more robust, scalable multi-agent AI systems for software engineering automation.

Hand-eye calibration is an important task in vision-guided robotic systems and is crucial for determining the transformation matrix between the camera coordinate system and the robot end-effector. Existing methods, for multi-view robotic systems, usually rely on accurate geometric models or manual assistance, generalize poorly, and can be very complicated and inefficient. Therefore, in this study, we propose PlaneHEC, a generalized hand-eye calibration method that does not require complex models and can be accomplished using only depth cameras, which achieves the optimal and fastest calibration results using arbitrary planar surfaces like walls and tables. PlaneHEC introduces hand-eye calibration equations based on planar constraints, which makes it strongly interpretable and generalizable. PlaneHEC also uses a comprehensive solution that starts with a closed-form solution and improves it withiterative optimization, which greatly improves accuracy. We comprehensively evaluated the performance of PlaneHEC in both simulated and real-world environments and compared the results with other point-cloud-based calibration methods, proving its superiority. Our approach achieves universal and fast calibration with an innovative design of computational models, providing a strong contribution to the development of multi-agent systems and embodied intelligence.

This paper introduces a model for coordinating prosumers with heterogeneous distributed energy resources (DERs), participating in the local energy market (LEM) that interacts with the market-clearing entity. The proposed LEM scheme utilizes a data-driven, model-free reinforcement learning approach based on the multi-agent deep deterministic policy gradient (MADDPG) framework, enabling prosumers to make real-time decisions on whether to buy, sell, or refrain from any action while facilitating efficient coordination for optimal energy trading in a dynamic market. In addition, we investigate a price manipulation strategy using a variational auto encoder-generative adversarial network (VAE-GAN) model, which allows utilities to adjust price signals in a way that induces financial losses for the prosumers. Our results show that under adversarial pricing, heterogeneous prosumer groups, particularly those lacking generation capabilities, incur financial losses. The same outcome holds across LEMs of different sizes. As the market size increases, trading stabilizes and fairness improves through emergent cooperation among agents.