Multi-agent robotic systems (MARS) build upon multi-agent systems by integrating physical and task-related constraints, increasing the complexity of action execution and agent coordination. However, despite the availability of advanced multi-agent frameworks, their real-world deployment on robots remains limited, hindering the advancement of MARS research in practice. To bridge this gap, we conducted two studies to investigate performance trade-offs of hierarchical multi-agent frameworks in a simulated real-world multi-robot healthcare scenario. In Study 1, using CrewAI, we iteratively refine the system's knowledge base, to systematically identify and categorize coordination failures (e.g., tool access violations, lack of timely handling of failure reports) not resolvable by providing contextual knowledge alone. In Study 2, using AutoGen, we evaluate a redesigned bidirectional communication structure and further measure the trade-offs between reasoning and non-reasoning models operating within the same robotic team setting. Drawing from our empirical findings, we emphasize the tension between autonomy and stability and the importance of edge-case testing to improve system reliability and safety for future real-world deployment. Supplementary materials, including codes, task agent setup, trace outputs, and annotated examples of coordination failures and reasoning behaviors, are available at: https://byc-sophie.github.io/mas-to-mars/.

While AI agents show potential in scientific ideation, most existing frameworks rely on single-agent refinement, limiting creativity due to bounded knowledge and perspective. Inspired by real-world research dynamics, this paper investigates whether structured multi-agent discussions can surpass solitary ideation. We propose a cooperative multi-agent framework for generating research proposals and systematically compare configurations including group size, leader-led versus leaderless structures, and team compositions varying in interdisciplinarity and seniority. To assess idea quality, we employ a comprehensive protocol with agent-based scoring and human review across dimensions such as novelty, strategic vision, and integration depth. Our results show that multi-agent discussions substantially outperform solitary baselines. A designated leader acts as a catalyst, transforming discussion into more integrated and visionary proposals. Notably, we find that cognitive diversity is a primary driver of quality, yet expertise is a non-negotiable prerequisite, as teams lacking a foundation of senior knowledge fail to surpass even a single competent agent. These findings offer actionable insights for designing collaborative AI ideation systems and shed light on how team structure influences creative outcomes.

We address the challenge of multi-robot autonomous hazard mapping in high-risk, failure-prone, communication-denied environments such as post-disaster zones, underground mines, caves, and planetary surfaces. In these missions, robots must explore and map hazards while minimizing the risk of failure due to environmental threats or hardware limitations. We introduce a behavior-adaptive, information-theoretic planning framework for multi-robot teams grounded in the concept of Behavioral Entropy (BE), that generalizes Shannon entropy (SE) to capture diverse human-like uncertainty evaluations. Building on this formulation, we propose the Behavior-Adaptive Path Planning (BAPP) framework, which modulates information gathering strategies via a tunable risk-sensitivity parameter, and present two planning algorithms: BAPP-TID for intelligent triggering of high-fidelity robots, and BAPP-SIG for safe deployment under high risk. We provide theoretical insights on the informativeness of the proposed BAPP framework and validate its effectiveness through both single-robot and multi-robot simulations. Our results show that the BAPP stack consistently outperforms Shannon-based and random strategies: BAPP-TID accelerates entropy reduction, while BAPP-SIG improves robot survivability with minimal loss in information gain. In multi-agent deployments, BAPP scales effectively through spatial partitioning, mobile base relocation, and role-aware heterogeneity. These findings underscore the value of behavior-adaptive planning for robust, risk-sensitive exploration in complex, failure-prone environments.

The dream to create AI assistants as capable and versatile as the fictional J.A.R.V.I.S from Iron Man has long captivated imaginations. With the evolution of (multi-modal) large language models ((M)LLMs), this dream is closer to reality, as (M)LLM-based Agents using computing devices (e.g., computers and mobile phones) by operating within the environments and interfaces (e.g., Graphical User Interface (GUI)) provided by operating systems (OS) to automate tasks have significantly advanced. This paper presents a comprehensive survey of these advanced agents, designated as OS Agents. We begin by elucidating the fundamentals of OS Agents, exploring their key components including the environment, observation space, and action space, and outlining essential capabilities such as understanding, planning, and grounding. We then examine methodologies for constructing OS Agents, focusing on domain-specific foundation models and agent frameworks. A detailed review of evaluation protocols and benchmarks highlights how OS Agents are assessed across diverse tasks. Finally, we discuss current challenges and identify promising directions for future research, including safety and privacy, personalization and self-evolution. This survey aims to consolidate the state of OS Agents research, providing insights to guide both academic inquiry and industrial development. An open-source GitHub repository is maintained as a dynamic resource to foster further innovation in this field. We present a 9-page version of our work, accepted by ACL 2025, to provide a concise overview to the domain.

Multi-agent systems (MAS) have demonstrated significant effectiveness in addressing complex problems through coordinated collaboration among heterogeneous agents. However, real-world environments and task specifications are inherently dynamic, characterized by frequent changes, uncertainty, and variability. Despite this, most existing MAS frameworks rely on static architectures with fixed agent capabilities and rigid task allocation strategies, which greatly limits their adaptability to evolving conditions. This inflexibility poses substantial challenges for sustaining robust and efficient multi-agent cooperation in dynamic and unpredictable scenarios. To address these limitations, we propose DRAMA: a Dynamic and Robust Allocation-based Multi-Agent System designed to facilitate resilient collaboration in rapidly changing environments. DRAMA features a modular architecture with a clear separation between the control plane and the worker plane. Both agents and tasks are abstracted as resource objects with well-defined lifecycles, while task allocation is achieved via an affinity-based, loosely coupled mechanism. The control plane enables real-time monitoring and centralized planning, allowing flexible and efficient task reassignment as agents join, depart, or become unavailable, thereby ensuring continuous and robust task execution. The worker plane comprises a cluster of autonomous agents, each with local reasoning, task execution, the ability to collaborate, and the capability to take over unfinished tasks from other agents when needed.

Large language models enable agents to autonomously perform tasks in open web environments. However, as hidden threats within the web evolve, web agents face the challenge of balancing task performance with emerging risks during long-sequence operations. Although this challenge is critical, current research remains limited to single-objective optimization or single-turn scenarios, lacking the capability for collaborative optimization of both safety and utility in web environments. To address this gap, we propose HarmonyGuard, a multi-agent collaborative framework that leverages policy enhancement and objective optimization to jointly improve both utility and safety. HarmonyGuard features a multi-agent architecture characterized by two fundamental capabilities: (1) Adaptive Policy Enhancement: We introduce the Policy Agent within HarmonyGuard, which automatically extracts and maintains structured security policies from unstructured external documents, while continuously updating policies in response to evolving threats. Extensive evaluations on multiple benchmarks show that HarmonyGuard improves policy compliance by up to 38% and task completion by up to 20% over existing baselines, while achieving over 90% policy compliance across all tasks. Web agents based on Large Language Models (LLMs) have transformed how we interact with the web by enabling autonomous tasks through natural language instructions (OpenAI, 2025; Anthropic, 2025). These agents can perform diverse operations, such as online shopping or booking flights, significantly expanding the scope of web automation. As these agents take on increasingly complex tasks, a critical question emerges: Can we trust web agents to act both intelligently and safely?

Connected autonomous vehicles (CAVs) must simultaneously perform multiple tasks, such as object detection, semantic segmentation, depth estimation, trajectory prediction, motion prediction, and behaviour prediction, to ensure safe and reliable navigation in complex environments. Vehicle-to-everything (V2X) communication enables cooperative driving among CAVs, thereby mitigating the limitations of individual sensors, reducing occlusions, and improving perception over long distances. Traditionally, these tasks are addressed using distinct models, which leads to high deployment costs, increased computational overhead, and challenges in achieving real-time performance. Multi-task learning (MTL) has recently emerged as a promising solution that enables the joint learning of multiple tasks within a single unified model. This offers improved efficiency and resource utilization. To the best of our knowledge, this survey is the first comprehensive review focused on MTL in the context of CAVs. We begin with an overview of CAVs and MTL to provide foundational background. We then explore the application of MTL across key functional modules, including perception, prediction, planning, control, and multi-agent collaboration. Finally, we discuss the strengths and limitations of existing methods, identify key research gaps, and provide directions for future research aimed at advancing MTL methodologies for CAV systems.

The rise of LLMs such as ChatGPT and Claude fuels the need for AI agents capable of real-time task handling. However, migrating data-intensive, multi-modal edge workloads to cloud data centers, traditionally used for agent deployment, introduces significant latency. Deploying AI agents at the edge improves efficiency and reduces latency. However, edge environments present challenges due to limited and heterogeneous resources. Maintaining QoS for mobile users necessitates agent migration, which is complicated by the complexity of AI agents coordinating LLMs, task planning, memory, and external tools. This paper presents the first systematic deployment and management solution for LLM-based AI agents in dynamic edge environments. We propose a novel adaptive framework for AI agent placement and migration in edge intelligence systems. Our approach models resource constraints and latency/cost, leveraging ant colony algorithms and LLM-based optimization for efficient decision-making. It autonomously places agents to optimize resource utilization and QoS and enables lightweight agent migration by transferring only essential state. Implemented on a distributed system using AgentScope and validated across globally distributed edge servers, our solution significantly reduces deployment latency and migration costs.

We present Agent Lightning, a flexible and extensible framework that enables Reinforcement Learning (RL)-based training of Large Language Models (LLMs) for any AI agent. Unlike existing methods that tightly couple RL training with agent or rely on sequence concatenation with masking, Agent Lightning achieves complete decoupling between agent execution and training, allowing seamless integration with existing agents developed via diverse ways (e.g., using frameworks like LangChain, OpenAI Agents SDK, AutoGen, and building from scratch) with almost ZERO code modifications. By formulating agent execution as Markov decision process, we define an unified data interface and propose a hierarchical RL algorithm, LightningRL, which contains a credit assignment module, allowing us to decompose trajectories generated by ANY agents into training transition. This enables RL to handle complex interaction logic, such as multi-agent scenarios and dynamic workflows. For the system design, we introduce a Training-Agent Disaggregation architecture, and brings agent observability frameworks into agent runtime, providing a standardized agent finetuning interface. Experiments across text-to-SQL, retrieval-augmented generation, and math tool-use tasks demonstrate stable, continuous improvements, showcasing the framework's potential for real-world agent training and deployment.

A central research topic in robotics is how to use this system to interact with the physical world. Traditional manipulation tasks primarily focus on small objects. However, in factory or home environments, there is often a need for the movement of large objects, such as moving tables. These tasks typically require multi-robot systems to work collaboratively. Previous research lacks a framework that can scale to arbitrary sizes of robots and generalize to various kinds of tasks. In this work, we propose CollaBot, a generalist framework for simultaneous collaborative manipulation. First, we use SEEM for scene segmentation and point cloud extraction of the target object. Then, we propose a collaborative grasping framework, which decomposes the task into local grasp pose generation and global collaboration. Finally, we design a 2-stage planning module that can generate collision-free trajectories to achieve this task. Experiments show a success rate of 52% across different numbers of robots, objects, and tasks, indicating the effectiveness of the proposed framework.