The emergence of large language models (LLMs) enables the development of intelligent agents capable of engaging in complex and multi-turn dialogues. However, multi-agent collaboration faces critical safety challenges, such as hallucination amplification and error injection and propagation. This paper presents GUARDIAN, a unified method for detecting and mitigating multiple safety concerns in GUARDing Intelligent Agent collaboratioNs. By modeling the multi-agent collaboration process as a discrete-time temporal attributed graph, GUARDIAN explicitly captures the propagation dynamics of hallucinations and errors. The unsupervised encoder-decoder architecture incorporating an incremental training paradigm learns to reconstruct node attributes and graph structures from latent embeddings, enabling the identification of anomalous nodes and edges with unparalleled precision. Moreover, we introduce a graph abstraction mechanism based on the Information Bottleneck Theory, which compresses temporal interaction graphs while preserving essential patterns. Extensive experiments demonstrate GUARDIAN's effectiveness in safeguarding LLM multi-agent collaborations against diverse safety vulnerabilities, achieving state-of-the-art accuracy with efficient resource utilization. The code is available at https://github.com/JialongZhou666/GUARDIAN

Driving simulation plays a crucial role in developing reliable driving agents by providing controlled, evaluative environments. To enable meaningful assessments, a high-quality driving simulator must satisfy several key requirements: multi-modal sensing capabilities (e.g., camera and LiDAR) with realistic scene rendering to minimize observational discrepancies; closed-loop evaluation to support free-form trajectory behaviors; highly diverse traffic scenarios for thorough evaluation; multi-agent cooperation to capture interaction dynamics; and high computational efficiency to ensure affordability and scalability. However, existing simulators and benchmarks fail to comprehensively meet these fundamental criteria. To bridge this gap, this paper introduces RealEngine, a novel driving simulation framework that holistically integrates 3D scene reconstruction and novel view synthesis techniques to achieve realistic and flexible closed-loop simulation in the driving context. By leveraging real-world multi-modal sensor data, RealEngine reconstructs background scenes and foreground traffic participants separately, allowing for highly diverse and realistic traffic scenarios through flexible scene composition. This synergistic fusion of scene reconstruction and view synthesis enables photorealistic rendering across multiple sensor modalities, ensuring both perceptual fidelity and geometric accuracy. Building upon this environment, RealEngine supports three essential driving simulation categories: non-reactive simulation, safety testing, and multi-agent interaction, collectively forming a reliable and comprehensive benchmark for evaluating the real-world performance of driving agents.

Stochastic games have become a prevalent framework for studying long-term multi-agent interactions, especially in the context of multi-agent reinforcement learning. In this work, we comprehensively investigate the concept of constant-memory strategies in stochastic games. We first establish some results on best responses and Nash equilibria for behavioral constant-memory strategies, followed by a discussion on the computational hardness of best responding to mixed constant-memory strategies. Those theoretic insights are later verified on several sequential decision-making testbeds, including the $\textit{Iterated Prisoner's Dilemma}$, the $\textit{Iterated Traveler's Dilemma}$, and the $\textit{Pursuit}$ domain. This work aims to enhance the understanding of theoretical issues in single-agent planning under multi-agent systems, and uncover the connection between decision models in single-agent and multi-agent contexts. The code is available at $\texttt{https://github.com/Fernadoo/Const-Mem.}$

Large Language Models (LLMs) show potential for complex reasoning, yet their capacity for emergent coordination in Multi-Agent Systems (MAS) when operating under strict swarm-like constraints-limited local perception and communication-remains largely unexplored. Existing benchmarks often do not fully capture the unique challenges of decentralized coordination when agents operate with incomplete spatio-temporal information. To bridge this gap, we introduce SwarmBench, a novel benchmark designed to systematically evaluate the swarm intelligence capabilities of LLMs acting as decentralized agents. SwarmBench features five foundational MAS coordination tasks (Pursuit, Synchronization, Foraging, Flocking, Transport) within a configurable 2D grid environment, forcing agents to rely solely on local sensory input ($k\times k$ view) and local communication. We propose metrics for coordination effectiveness and analyze emergent group dynamics. Zero-shot evaluations of leading LLMs (e.g., deepseek-v3, o4-mini) reveal significant task-dependent performance variations. While some rudimentary coordination is observed, our results indicate that current LLMs significantly struggle with robust long-range planning and adaptive strategy formation under the uncertainty inherent in these decentralized scenarios. Assessing LLMs under such swarm-like constraints is crucial for understanding their utility in future decentralized intelligent systems. We release SwarmBench as an open, extensible toolkit-built on a customizable physical system-providing environments, prompts, evaluation scripts, and comprehensive datasets. This aims to foster reproducible research into LLM-based MAS coordination and the theoretical underpinnings of emergent collective behavior under severe informational decentralization. Our code repository is available at https://github.com/x66ccff/swarmbench.

The increasing number of satellites and orbital debris has made space congestion a critical issue, threatening satellite safety and sustainability. Challenges such as collision avoidance, station-keeping, and orbital maneuvering require advanced techniques to handle dynamic uncertainties and multi-agent interactions. Reinforcement learning (RL) has shown promise in this domain, enabling adaptive, autonomous policies for space operations; however, many existing RL frameworks rely on custom-built environments developed from scratch, which often use simplified models and require significant time to implement and validate the orbital dynamics, limiting their ability to fully capture real-world complexities. To address this, we introduce OrbitZoo, a versatile multi-agent RL environment built on a high-fidelity industry standard library, that enables realistic data generation, supports scenarios like collision avoidance and cooperative maneuvers, and ensures robust and accurate orbital dynamics. The environment is validated against a real satellite constellation, Starlink, achieving a Mean Absolute Percentage Error (MAPE) of 0.16% compared to real-world data. This validation ensures reliability for generating high-fidelity simulations and enabling autonomous and independent satellite operations.

Facial expression recognition (FER) must remain robust under both cultural variation and perceptually degraded visual conditions, yet most existing evaluations assume homogeneous data and high-quality imagery. We introduce an agent-based, streaming benchmark that reveals how cross-cultural composition and progressive blurring interact to shape face recognition robustness. Each agent operates in a frozen CLIP feature space with a lightweight residual adapter trained online at sigma=0 and fixed during testing. Agents move and interact on a 5x5 lattice, while the environment provides inputs with sigma-scheduled Gaussian blur. We examine monocultural populations (Western-only, Asian-only) and mixed environments with balanced (5/5) and imbalanced (8/2, 2/8) compositions, as well as different spatial contact structures. Results show clear asymmetric degradation curves between cultural groups: JAFFE (Asian) populations maintain higher performance at low blur but exhibit sharper drops at intermediate stages, whereas KDEF (Western) populations degrade more uniformly. Mixed populations exhibit intermediate patterns, with balanced mixtures mitigating early degradation, but imbalanced settings amplify majority-group weaknesses under high blur. These findings quantify how cultural composition and interaction structure influence the robustness of FER as perceptual conditions deteriorate.

AI-powered browser assistants (also known as autonomous browsing agents or agentic AI browsers) are emerging tools that use LLMs to help users navigate and interact with web content. For example, an AI agent can be instructed to summarize a webpage or perform actions like clicking links and filling forms on behalf of the user. While these agents promise enhanced productivity, they also introduce new security risks. One major risk is prompt injection, where an attacker embeds malicious instructions into web content that the agent will process [5]. Crucially, such instructions can be hidden from the human user (e.g., invisible text, HTML comments) yet still parsed by the LLM, causing it to alter its behavior in unintended ways [10]. In effect, the agent can be tricked into executing the attacker's commands rather than the user's, leading to potentially severe consequences [2]. Indirect prompt injections have been demonstrated in real-world scenarios.

Language is fundamental to human cooperation, facilitating not only the exchange of information but also the coordination of actions through shared interpretations of situational contexts. This study explores whether the Generative Agent-Based Model (GABM) Concordia can effectively model Theory of Mind (ToM) within simulated real-world environments. Specifically, we assess whether this framework successfully simulates ToM abilities and whether GPT-4 can perform tasks by making genuine inferences from social context, rather than relying on linguistic memorization. Our findings reveal a critical limitation: GPT-4 frequently fails to select actions based on belief attribution, suggesting that apparent ToM-like abilities observed in previous studies may stem from shallow statistical associations rather than true reasoning. Additionally, the model struggles to generate coherent causal effects from agent actions, exposing difficulties in processing complex social interactions. These results challenge current statements about emergent ToM-like capabilities in LLMs and highlight the need for more rigorous, action-based evaluation frameworks.

Multi-Agent Deep Reinforcement Learning (MADRL) has shown potential for cooperative and competitive tasks such as autonomous driving and strategic gaming. However, models trained by MADRL are vulnerable to adversarial perturbations on states and actions. Therefore, it is essential to investigate the robustness of MADRL models from an attack perspective. Existing studies focus on either state-only attacks or action-only attacks, but do not consider how to effectively joint them. Simply combining state and action perturbations such as randomly perturbing states and actions does not exploit their potential synergistic effects. In this paper, we propose the State-Action Joint Attack (SAJA) framework that has a good synergistic effects. SAJA consists of two important phases: (1) In the state attack phase, a multi-step gradient ascent method utilizes both the actor network and the critic network to compute an adversarial state, and (2) in the action attack phase, based on the perturbed state, a second gradient ascent uses the critic network to craft the final adversarial action. Additionally, a heuristic regularizer measuring the distance between the perturbed actions and the original clean ones is added into the loss function to enhance the effectiveness of the critic's guidance. We evaluate SAJA in the Multi-Agent Particle Environment (MPE), demonstrating that (1) it outperforms and is more stealthy than state-only or action-only attacks, and (2) existing state or action defense methods cannot defend its attacks.

Collaborative machine learning enables multiple data owners to jointly train models for improved predictive performance. However, ensuring incentive compatibility and fair contribution-based rewards remains a critical challenge. Prior work by Sim and colleagues [9] addressed this by allocating model rewards, which are non-monetary and freely replicable, based on the Shapley value of each party's data contribution, measured via information gain. In this paper, we introduce a ratio-based Shapley value that replaces the standard additive formulation with a relative contribution measure. While our overall reward framework,including the incentive definitions and model-reward setting, remains aligned with that of Sim and colleagues, the underlying value function is fundamentally different. Our alternative valuation induces a different distribution of model rewards and offers a new lens through which to analyze incentive properties. We formally define the ratio-based value and prove that it satisfies the same set of incentive conditions as the additive formulation, including adapted versions of fairness, individual rationality, and stability. Like the original approach, our method faces the same fundamental trade-offs between these incentives. Our contribution is a mathematically grounded alternative to the additive Shapley framework, potentially better suited to contexts where proportionality among contributors is more meaningful than additive differences.