Although discourse around the risks of Artificial Intelligence (AI) has grown, it often lacks a comprehensive, multidimensional framework, and concrete causal pathways mapping hazard to harm. This paper aims to bridge this gap by examining six commonly discussed AI catastrophic risks: CBRN, cyber offense, sudden loss of control, gradual loss of control, environmental risk, and geopolitical risk. First, we characterize these risks across seven key dimensions, namely intent, competency, entity, polarity, linearity, reach, and order. Next, we conduct risk pathway modeling by mapping step-by-step progressions from the initial hazard to the resulting harms. The dimensional approach supports systematic risk identification and generalizable mitigation strategies, while risk pathway models help identify scenario-specific interventions. Together, these methods offer a more structured and actionable foundation for managing catastrophic AI risks across the value chain.

We introduce Unsupervised Partner Design (UPD) - a population-free, multi-agent reinforcement learning framework for robust ad-hoc teamwork that adaptively generates training partners without requiring pretrained partners or manual parameter tuning. UPD constructs diverse partners by stochastically mixing an ego agent's policy with biased random behaviours and scores them using a variance-based learnability metric that prioritises partners near the ego agent's current learning frontier. We show that UPD can be integrated with unsupervised environment design, resulting in the first method enabling fully unsupervised curricula over both level and partner distributions in a cooperative setting. Through extensive evaluations on Overcooked-AI and the Overcooked Generalisation Challenge, we demonstrate that this dynamic partner curriculum is highly effective: UPD consistently outperforms both population-based and population-free baselines as well as ablations. In a user study, we further show that UPD achieves higher returns than all baselines and was perceived as significantly more adaptive, more human-like, a better collaborator, and less frustrating.

Generative models, especially diffusion and flow-based models, have been promising in offline multi-agent reinforcement learning. However, integrating powerful generative models into this framework poses unique challenges. In particular, diffusion and flow-based policies suffer from low sampling efficiency due to their iterative generation processes, making them impractical in time-sensitive or resource-constrained settings. To tackle these difficulties, we propose OM2P (Offline Multi-Agent Mean-Flow Policy), a novel offline MARL algorithm to achieve efficient one-step action sampling. To address the misalignment between generative objectives and reward maximization, we introduce a reward-aware optimization scheme that integrates a carefully-designed mean-flow matching loss with Q-function supervision. Additionally, we design a generalized timestep distribution and a derivative-free estimation strategy to reduce memory overhead and improve training stability. Empirical evaluations on Multi-Agent Particle and MuJoCo benchmarks demonstrate that OM2P achieves superior performance, with up to a 3.8x reduction in GPU memory usage and up to a 10.8x speed-up in training time. Our approach represents the first to successfully integrate mean-flow model into offline MARL, paving the way for practical and scalable generative policies in cooperative multi-agent settings.

This work leverages adaptive social learning to estimate partially observable global states in multi-agent reinforcement learning (MARL) problems. Unlike existing methods, the proposed approach enables the concurrent operation of social learning and reinforcement learning. Specifically, it alternates between a single step of social learning and a single step of MARL, eliminating the need for the time- and computation-intensive two-timescale learning frameworks. Theoretical guarantees are provided to support the effectiveness of the proposed method. Simulation results verify that the performance of the proposed methodology can approach that of reinforcement learning when the true state is known.

Large Language Models (LLMs) have recently demonstrated impressive action sequence prediction capabilities but often struggle with dynamic, long-horizon tasks such as real-time strategic games. In a game such as StarCraftII (SC2), agents need to manage resource constraints and adapt to evolving battlefield situations in a partially observable environment. This often overwhelms exisiting LLM-based approaches. To address these challenges, we propose a hierarchical multi-agent framework that employs specialized imitation learning agents under a meta-controller called Strategic Planner (SP). By expert demonstrations, each specialized agent learns a distinctive strategy, such as aerial support or defensive maneuvers, and produces coherent, structured multistep action sequences. The SP then orchestrates these proposals into a single, environmentally adaptive plan that ensures local decisions aligning with long-term strategies. We call this HIMA (Hierarchical Imitation Multi-Agent). We also present TEXTSCII-ALL, a comprehensive SC2 testbed that encompasses all race match combinations in SC2. Our empirical results show that HIMA outperforms state of the arts in strategic clarity, adaptability, and computational efficiency, underscoring the potential of combining specialized imitation modules with meta-level orchestration to develop more robust, general-purpose AI agents.

We study the problem of online Multi-Agent Pickup and Delivery (MAPD), where a team of agents must repeatedly serve dynamically appearing tasks on a shared map. Existing online methods either rely on simple heuristics, which result in poor decisions, or employ complex reasoning, which suffers from limited scalability under real-time constraints. In this work, we focus on the task assignment subproblem and formulate it as a minimum-cost flow over the environment graph. This eliminates the need for pairwise distance computations and allows agents to be simultaneously assigned to tasks and routed toward them. The resulting flow network also supports efficient guide path extraction to integrate with the planner and accelerates planning under real-time constraints. To improve solution quality, we introduce two congestion-aware edge cost models that incorporate real-time traffic estimates. This approach supports real-time execution and scales to over 20000 agents and 30000 tasks within 1-second planning time, outperforming existing baselines in both computational efficiency and assignment quality.

This paper proposes a novel framework for developing safe Artificial General Intelligence (AGI) by combining Active Inference principles with Large Language Models (LLMs). We argue that traditional approaches to AI safety, focused on post-hoc interpretability and reward engineering, have fundamental limitations. We present an architecture where safety guarantees are integrated into the system's core design through transparent belief representations and hierarchical value alignment. Our framework leverages natural language as a medium for representing and manipulating beliefs, enabling direct human oversight while maintaining computational tractability. The architecture implements a multi-agent system where agents self-organize according to Active Inference principles, with preferences and safety constraints flowing through hierarchical Markov blankets. We outline specific mechanisms for ensuring safety, including: (1) explicit separation of beliefs and preferences in natural language, (2) bounded rationality through resource-aware free energy minimization, and (3) compositional safety through modular agent structures. The paper concludes with a research agenda centered on the Abstraction and Reasoning Corpus (ARC) benchmark, proposing experiments to validate our framework's safety properties. Our approach offers a path toward AGI development that is inherently safer, rather than retrofitted with safety measures.

Organisations are starting to adopt LLM-based AI agents, with their deployments naturally evolving from single agents towards interconnected, multi-agent networks. Yet a collection of safe agents does not guarantee a safe collection of agents, as interactions between agents over time create emergent behaviours and induce novel failure modes. This means multi-agent systems require a fundamentally different risk analysis approach than that used for a single agent. This report addresses the early stages of risk identification and analysis for multi-agent AI systems operating within governed environments where organisations control their agent configurations and deployment. In this setting, we examine six critical failure modes: cascading reliability failures, inter-agent communication failures, monoculture collapse, conformity bias, deficient theory of mind, and mixed motive dynamics. For each, we provide a toolkit for practitioners to extend or integrate into their existing frameworks to assess these failure modes within their organisational contexts. Given fundamental limitations in current LLM behavioural understanding, our approach centres on analysis validity, and advocates for progressively increasing validity through staged testing across stages of abstraction and deployment that gradually increases exposure to potential negative impacts, while collecting convergent evidence through simulation, observational analysis, benchmarking, and red teaming. This methodology establishes the groundwork for robust organisational risk management as these LLM-based multi-agent systems are deployed and operated.

Interactive Narrative Systems (INS) have revolutionized digital experiences by empowering users to actively shape their stories, diverging from traditional passive storytelling. However, the field faces challenges due to fragmented research efforts and diverse system representations. This paper introduces a formal representation framework for INS, inspired by diverse approaches from the state of the art. By providing a consistent vocabulary and modeling structure, the framework facilitates the analysis, the description and comparison of INS properties. Experimental validations on the "Little Red Riding Hood" scenario highlight the usefulness of the proposed formalism and its impact on improving the evaluation of INS. This work aims to foster collaboration and coherence within the INS research community by proposing a methodology for formally representing these systems.

For the development and optimization of agent-based models (ABMs) and rational agent-based models (RABMs), optimization algorithms such as reinforcement learning are extensively used. However, assessing the performance of RL-based ABMs and RABMS models is challenging due to the complexity and stochasticity of the modeled systems, and the lack of well-standardized metrics for comparing RL algorithms. In this study, we are developing domain-driven metrics for RL, while building on state-of-the-art metrics. We demonstrate our ``Domain-driven-RL-metrics'' using policy optimization on a rational ABM disease modeling case study to model masking behavior, vaccination, and lockdown in a pandemic. Our results show the use of domain-driven rewards in conjunction with traditional and state-of-the-art metrics for a few different simulation scenarios such as the differential availability of masks.