Dynamic Scene Graphs (DSGs) provide a structured representation of hierarchical, interconnected environments, but current approaches struggle to capture stochastic dynamics, partial observability, and multi-agent activity. These aspects are critical for embodied AI, where agents must act under uncertainty and delayed perception. We introduce FOGMACHINE , an open-source framework that fuses DSGs with discrete-event simulation to model object dynamics, agent observations, and interactions at scale. This setup enables the study of uncertainty propagation, planning under limited perception, and emergent multi-agent behavior. Experiments in urban scenarios illustrate realistic temporal and spatial patterns while revealing the challenges of belief estimation under sparse observations. By combining structured representations with efficient simulation, FOGMACHINE establishes an effective tool for benchmarking, model training, and advancing embodied AI in complex, uncertain environments.

Multi-agent pathfinding (MAPF) remains a critical problem in robotics and autonomous systems, where agents must navigate shared spaces efficiently while avoiding conflicts. Traditional centralized algorithms that have global information, such as Conflict-Based Search (CBS), provide high-quality solutions but become computationally expensive in large-scale scenarios due to the combinatorial explosion of conflicts that need resolution. Conversely, distributed approaches that have local information, particularly learning-based methods, offer better scalability by operating with relaxed information availability, yet often at the cost of solution quality. To address these limitations, we propose a hybrid framework that combines decentralized path planning with a lightweight centralized coordinator. Our framework leverages reinforcement learning (RL) for decentralized planning, enabling agents to adapt their planning based on minimal, targeted alerts--such as static conflict-cell flags or brief conflict tracks--that are dynamically shared information from the central coordinator for effective conflict resolution. We empirically study the effect of the information available to an agent on its planning performance. Our approach reduces the inter-agent information sharing compared to fully centralized and distributed methods, while still consistently finding feasible, collision-free solutions--even in large-scale scenarios having higher agent counts.

We close open theoretical gaps in Multi-Agent Imitation Learning (MAIL) by characterizing the limits of non-interactive MAIL and presenting the first interactive algorithm with near-optimal sample complexity. In the non-interactive setting, we prove a statistical lower bound that identifies the all-policy deviation concentrability coefficient as the fundamental complexity measure, and we show that Behavior Cloning (BC) is rate-optimal. For the interactive setting, we introduce a framework that combines reward-free reinforcement learning with interactive MAIL and instantiate it with an algorithm, MAIL-WARM. It improves the best previously known sample complexity from $\mathcal{O}(\varepsilon^{-8})$ to $\mathcal{O}(\varepsilon^{-2}),$ matching the dependence on $\varepsilon$ implied by our lower bound. Finally, we provide numerical results that support our theory and illustrate, in environments such as grid worlds, where Behavior Cloning fails to learn.

Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents: small errors compound across steps, and even state-of-the-art models often hallucinate or lose coherence. We identify context management as the central bottleneck -- extended histories cause agents to overlook critical evidence or become distracted by irrelevant information, thus failing to replan or reflect from previous mistakes. To address this, we propose COMPASS (Context-Organized Multi-Agent Planning and Strategy System), a lightweight hierarchical framework that separates tactical execution, strategic oversight, and context organization into three specialized components: (1) a Main Agent that performs reasoning and tool use, (2) a Meta-Thinker that monitors progress and issues strategic interventions, and (3) a Context Manager that maintains concise, relevant progress briefs for different reasoning stages. Across three challenging benchmarks -- GAIA, BrowseComp, and Humanity's Last Exam -- COMPASS improves accuracy by up to 20% relative to both single- and multi-agent baselines. We further introduce a test-time scaling extension that elevates performance to match established DeepResearch agents, and a post-training pipeline that delegates context management to smaller models for enhanced efficiency.

Artificial Intelligence (AI) is starting to transform the research process as we know it by automating the discovery of new solutions. Given a task, the typical AI-driven approach is (i) to generate a set of diverse solutions, and then (ii) to verify these solutions and select one that solves the problem. Crucially, this approach assumes the existence of a reliable verifier, i.e., one that can accurately determine whether a solution solves the given problem. We argue that systems research, long focused on designing and evaluating new performance-oriented algorithms, is particularly well-suited for AI-driven solution discovery. This is because system performance problems naturally admit reliable verifiers: solutions are typically implemented in real systems or simulators, and verification reduces to running these software artifacts against predefined workloads and measuring performance. We term this approach as AI-Driven Research for Systems (ADRS), which iteratively generates, evaluates, and refines solutions. Using penEvolve, an existing open-source ADRS instance, we present case studies across diverse domains, including load balancing for multi-region cloud scheduling, Mixture-of-Experts inference, LLM-based SQL queries, and transaction scheduling. In multiple instances, ADRS discovers algorithms that outperform state-of-the-art human designs (e.g., achieving up to 5.0x runtime improvements or 50% cost reductions). We distill best practices for guiding algorithm evolution, from prompt design to evaluator construction, for existing frameworks. We then discuss the broader implications for the systems community: as AI assumes a central role in algorithm design, we argue that human researchers will increasingly focus on problem formulation and strategic guidance. Our results highlight both the disruptive potential and the urgent need to adapt systems research practices in the age of AI.

The growing ubiquity of conversational AI highlights the need for frameworks that capture not only users' instrumental goals but also the situated, adaptive, and social practices through which they achieve them. Existing taxonomies of conversational behavior either overgeneralize, remain domain-specific, or reduce interactions to narrow dialogue functions. To address this gap, we introduce the Taxonomy of User Needs and Actions (TUNA), an empirically grounded framework developed through iterative qualitative analysis of 1193 human-AI conversations, supplemented by theoretical review and validation across diverse contexts. TUNA organizes user actions into a three-level hierarchy encompassing behaviors associated with information seeking, synthesis, procedural guidance, content creation, social interaction, and meta-conversation. By centering user agency and appropriation practices, TUNA enables multi-scale evaluation, supports policy harmonization across products, and provides a backbone for layering domain-specific taxonomies. This work contributes a systematic vocabulary for describing AI use, advancing both scholarly understanding and practical design of safer, more responsive, and more accountable conversational systems.

How should well-being be prioritised in society, and what trade-offs are people willing to make between fairness and personal well-being? We investigate these questions using a stated preference experiment with a nationally representative UK sample (n = 300), in which participants evaluated life satisfaction outcomes for both themselves and others under conditions of uncertainty. Individual-level utility functions were estimated using an Expected Utility Maximisation (EUM) framework and tested for sensitivity to the overweighting of small probabilities, as characterised by Cumulative Prospect Theory (CPT). A majority of participants displayed concave (risk-averse) utility curves and showed stronger aversion to inequality in societal life satisfaction outcomes than to personal risk. These preferences were unrelated to political alignment, suggesting a shared normative stance on fairness in well-being that cuts across ideological boundaries. The results challenge use of average life satisfaction as a policy metric, and support the development of nonlinear utility-based alternatives that more accurately reflect collective human values. Implications for public policy, well-being measurement, and the design of value-aligned AI systems are discussed.

Recent advances in generalist multi-agent systems (MAS) have largely followed a context-engineering plus centralized paradigm, where a planner agent coordinates multiple worker agents through unidirectional prompt passing. While effective under strong planner models, this design suffers from two critical limitations: (1) strong dependency on the planner's capability, which leads to degraded performance when a smaller LLM powers the planner; and (2) limited inter-agent communication, where collaboration relies on prompt concatenation rather than genuine refinement through structured discussions. To address these challenges, we propose Anemoi, a semi-centralized MAS built on the Agent-to-Agent (A2A) communication MCP server from Coral Protocol. Unlike traditional designs, Anemoi enables structured and direct inter-agent collaboration, allowing all agents to monitor progress, assess results, identify bottlenecks, and propose refinements in real time. This paradigm reduces reliance on a single planner, supports adaptive plan updates, and minimizes redundant context passing, resulting in more scalable execution. Evaluated on the GAIA benchmark, Anemoi achieved 52.73% accuracy with a small LLM (GPT-4.1-mini) as the planner, surpassing the strongest open-source baseline OWL (43.63%) by +9.09% under identical LLM settings. Our implementation is publicly available at https://github.com/Coral-Protocol/Anemoi.

By building and updating internal cognitive maps, animals exhibit extraordinary navigation abilities in complex, dynamic environments. Inspired by these biological mechanisms, we present a real time robotic navigation system grounded in the Active Inference Framework (AIF). Our model incrementally constructs a topological map, infers the agent's location, and plans actions by minimising expected uncertainty and fulfilling perceptual goals without any prior training. Integrated into the ROS2 ecosystem, we validate its adaptability and efficiency across both 2D and 3D environments (simulated and real world), demonstrating competitive performance with traditional and state of the art exploration approaches while offering a biologically inspired navigation approach.

We study a distributed learning problem in which learning agents are embedded in a directed acyclic graph (DAG). There is a fixed and arbitrary distribution over feature/label pairs, and each agent or vertex in the graph is able to directly observe only a subset of the features -- potentially a different subset for every agent. The agents learn sequentially in some order consistent with a topological sort of the DAG, committing to a model mapping observations to predictions of the real-valued label. Each agent observes the predictions of their parents in the DAG, and trains their model using both the features of the instance that they directly observe, and the predictions of their parents as additional features. We ask when this process is sufficient to achieve \emph{information aggregation}, in the sense that some agent in the DAG is able to learn a model whose error is competitive with the best model that could have been learned (in some hypothesis class) with direct access to \emph{all} features, despite the fact that no single agent in the network has such access. We give upper and lower bounds for this problem for both linear and general hypothesis classes. Our results identify the \emph{depth} of the DAG as the key parameter: information aggregation can occur over sufficiently long paths in the DAG, assuming that all of the relevant features are well represented along the path, and there are distributions over which information aggregation cannot occur even in the linear case, and even in arbitrarily large DAGs that do not have sufficient depth (such as a hub-and-spokes topology in which the spoke vertices collectively see all the features). We complement our theoretical results with a comprehensive set of experiments.