--Multi-Agent Systems have recently emerged as a promising paradigm for collaborative reasoning and solving complex tasks. However, the design of collaborative learning algorithms in multi-agent systems faces several challenges, including high communication overhead and insufficient agent-level person-alization. In this paper, we propose PE-MA (Parameter-Efficient Multi-Agent Co-Evolution), a novel collaboration framework that supports efficient, scalable, and personalized co-evolution in multi-agent systems. In PE-MA, each agent maintains a lightweight personalized adapter to support agent-specific behavior, while a shared adapter is collaboratively optimized across neighboring agents. Experiments show that PE-MA improves accuracy by 2%-5%, while reducing training and communication costs by 77% and 87%, respectively. N recent years, multi-agent systems (MAS) have gradually become an important research topic in the field of artificial intelligence due to breakthroughs in natural language understanding and generation. These systems organize multiple agents with communication capabilities into collaborative frameworks, enhancing their abilities in task decomposition, role allocation, and collective reasoning. This drives the paradigm of solving complex tasks toward greater intelligence and autonomy. It has been widely applied in intelligent dialogue systems [1; 2], automated decision-making [3], robotic collaboration [4; 5], and virtual assistants [6; 7], demonstrating significant application potential.

Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical user interfaces. We are now witnessing the emergence of \emph{Computer-Using Agents} (CUAs), capable of autonomously performing tasks such as navigating desktop applications, web pages, and mobile apps. However, as these agents grow in capability, they also introduce novel safety and security risks. Vulnerabilities in LLM-driven reasoning, with the added complexity of integrating multiple software components and multimodal inputs, further complicate the security landscape. In this paper, we present a systematization of knowledge on the safety and security threats of CUAs. We conduct a comprehensive literature review and distill our findings along four research objectives: \textit{\textbf{(i)}} define the CUA that suits safety analysis; \textit{\textbf{(ii)} } categorize current safety threats among CUAs; \textit{\textbf{(iii)}} propose a comprehensive taxonomy of existing defensive strategies; \textit{\textbf{(iv)}} summarize prevailing benchmarks, datasets, and evaluation metrics used to assess the safety and performance of CUAs. Building on these insights, our work provides future researchers with a structured foundation for exploring unexplored vulnerabilities and offers practitioners actionable guidance in designing and deploying secure Computer-Using Agents.

Robot swarms require cohesive collective behaviour to address diverse challenges, including shape formation and decision-making. Existing approaches often treat consensus in discrete and continuous decision spaces as distinct problems. We present DANCeRS, a unified, distributed algorithm leveraging Gaussian Belief Propagation (GBP) to achieve consensus in both domains. By representing a swarm as a factor graph our method ensures scalability and robustness in dynamic environments, relying on purely peer-to-peer message passing. We demonstrate the effectiveness of our general framework through two applications where agents in a swarm must achieve consensus on global behaviour whilst relying on local communication. In the first, robots must perform path planning and collision avoidance to create shape formations. In the second, we show how the same framework can be used by a group of robots to form a consensus over a set of discrete decisions. Experimental results highlight our method's scalability and efficiency compared to recent approaches to these problems making it a promising solution for multi-robot systems requiring distributed consensus. We encourage the reader to see the supplementary video demo.

With the increasing prevalence of multimodal content on social media, sentiment analysis faces significant challenges in effectively processing heterogeneous data and recognizing multi-label emotions. Existing methods often lack effective cross-modal fusion and external knowledge integration. We propose SentiMM, a novel multi-agent framework designed to systematically address these challenges. SentiMM processes text and visual inputs through specialized agents, fuses multimodal features, enriches context via knowledge retrieval, and aggregates results for final sentiment classification. We also introduce SentiMMD, a large-scale multimodal dataset with seven fine-grained sentiment categories. Extensive experiments demonstrate that SentiMM achieves superior performance compared to state-of-the-art baselines, validating the effectiveness of our structured approach.

Vision language model (VLM)-based mobile agents show great potential for assisting users in performing instruction-driven tasks. However, these agents typically struggle with personalized instructions -- those containing ambiguous, user-specific context -- a challenge that has been largely overlooked in previous research. In this paper, we define personalized instructions and introduce PerInstruct, a novel human-annotated dataset covering diverse personalized instructions across various mobile scenarios. Furthermore, given the limited personalization capabilities of existing mobile agents, we propose PerPilot, a plug-and-play framework powered by large language models (LLMs) that enables mobile agents to autonomously perceive, understand, and execute personalized user instructions. PerPilot identifies personalized elements and autonomously completes instructions via two complementary approaches: memory-based retrieval and reasoning-based exploration. Experimental results demonstrate that PerPilot effectively handles personalized tasks with minimal user intervention and progressively improves its performance with continued use, underscoring the importance of personalization-aware reasoning for next-generation mobile agents. The dataset and code are available at: https://github.com/xinwang-nwpu/PerPilot

Accurate trajectory prediction is vital for autonomous driving, robotics, and intelligent decision-making systems, yet traditional models typically rely on fixed-length output predictions, limiting their adaptability to dynamic real-world scenarios. In this paper, we introduce the FlexiSteps Network (FSN), a novel framework that dynamically adjusts prediction output time steps based on varying contextual conditions. Inspired by recent advancements addressing observation length discrepancies and dynamic feature extraction, FSN incorporates an pre-trained Adaptive Prediction Module (APM) to evaluate and adjust the output steps dynamically, ensuring optimal prediction accuracy and efficiency. To guarantee the plug-and-play of our FSN, we also design a Dynamic Decoder(DD). Additionally, to balance the prediction time steps and prediction accuracy, we design a scoring mechanism, which not only introduces the Fréchet distance to evaluate the geometric similarity between the predicted trajectories and the ground truth trajectories but the length of predicted steps is also considered. Extensive experiments conducted on benchmark datasets including Argoverse and INTERACTION demonstrate the effectiveness and flexibility of our proposed FSN framework.

The Open RAN movement has catalyzed a transformation toward programmable, interoperable cellular infrastructures. Yet, today's deployments still rely heavily on static control and manual operations. To move beyond this limitation, we introduce AgenRAN, an AI-native, Open RAN-aligned agentic framework that generates and orchestrates a fabric of distributed AI agents based on Natural Language (NL) intents. Unlike traditional approaches that require explicit programming, AgentRAN's LLM-powered agents interpret natural language intents, negotiate strategies through structured conversations, and orchestrate control loops across the network. AgentRAN instantiates a self-organizing hierarchy of agents that decompose complex intents across time scales (from sub-millisecond to minutes), spatial domains (cell to network-wide), and protocol layers (PHY/MAC to RRC). A central innovation is the AI-RAN Factory, an automated synthesis pipeline that observes agent interactions and continuously generates new agents embedding improved control algorithms, effectively transforming the network from a static collection of functions into an adaptive system capable of evolving its own intelligence. We demonstrate AgentRAN through live experiments on 5G testbeds where competing user demands are dynamically balanced through cascading intents. By replacing rigid APIs with NL coordination, AgentRAN fundamentally redefines how future 6G networks autonomously interpret, adapt, and optimize their behavior to meet operator goals.

Multi-agent reinforcement learning in mixed-motive settings presents a fundamental challenge: agents must balance individual interests with collective goals, which are neither fully aligned nor strictly opposed. To address this, reward restructuring methods such as gifting and intrinsic motivation have been proposed. However, these approaches primarily focus on promoting cooperation by managing the trade-off between individual and collective returns, without explicitly addressing fairness with respect to the agents' task-specific rewards. In this paper, we propose an adaptive conflict-aware gradient adjustment method that promotes cooperation while ensuring fairness in individual rewards. The proposed method dynamically balances policy gradients derived from individual and collective objectives in situations where the two objectives are in conflict. By explicitly resolving such conflicts, our method improves collective performance while preserving fairness across agents. We provide theoretical results that guarantee monotonic non-decreasing improvement in both the collective and individual objectives and ensure fairness. Empirical results in sequential social dilemma environments demonstrate that our approach outperforms baselines in terms of social welfare while ensuring fairness among agents.

Recent advances in the intrinsic reasoning capabilities of large language models (LLMs) have given rise to LLM-based agent systems that exhibit near-human performance on a variety of automated tasks. However, although these systems share similarities in terms of their use of LLMs, different reasoning frameworks of the agent system steer and organize the reasoning process in different ways. In this survey, we propose a systematic taxonomy that decomposes agentic reasoning frameworks and analyze how these frameworks dominate framework-level reasoning by comparing their applications across different scenarios. Specifically, we propose an unified formal language to further classify agentic reasoning systems into single-agent methods, tool-based methods, and multi-agent methods. After that, we provide a comprehensive review of their key application scenarios in scientific discovery, healthcare, software engineering, social simulation, and economics. We also analyze the characteristic features of each framework and summarize different evaluation strategies. Our survey aims to provide the research community with a panoramic view to facilitate understanding of the strengths, suitable scenarios, and evaluation practices of different agentic reasoning frameworks.

The real value of knowledge lies not just in its accumulation, but in its potential to be harnessed effectively to conquer the unknown. Although recent multimodal large language models (MLLMs) exhibit impressing multimodal capabilities, they often fail in rarely encountered domain-specific tasks due to limited relevant knowledge. T o explore this, we adopt visual game cognition as a testbed and select "Monster Hunter: W orld" as the target to construct a multimodal knowledge graph (MH-MMKG), which incorporates multi-modalities and intricate entity relations. W e also design a series of challenging queries based on MH-MMKG to evaluate the models' ability for complex knowledge retrieval and reasoning. Furthermore, we propose a multi-agent retriever that enables a model to autonomously search relevant knowledge without additional training. Experimental results show that our approach significantly enhances the performance of MLLMs, providing a new perspective on multimodal knowledge-augmented reasoning and laying a solid foundation for future research.