This paper introduces MovieCORE, a novel video question answering (VQA) dataset designed to probe deeper cognitive understanding of movie content. Unlike existing datasets that focus on surface-level comprehension, MovieCORE emphasizes questions that engage System-2 thinking while remaining specific to the video material. We present an innovative agentic brainstorming approach, utilizing multiple large language models (LLMs) as thought agents to generate and refine high-quality question-answer pairs. To evaluate dataset quality, we develop a set of cognitive tests assessing depth, thought-provocation potential, and syntactic complexity. We also propose a comprehensive evaluation scheme for assessing VQA model performance on deeper cognitive tasks. To address the limitations of existing video-language models (VLMs), we introduce an agentic enhancement module, Agentic Choice Enhancement (ACE), which improves model reasoning capabilities post-training by up to 25%. Our work contributes to advancing movie understanding in AI systems and provides valuable insights into the capabilities and limitations of current VQA models when faced with more challenging, nuanced questions about cinematic content. Our project page, dataset and code can be found at https://joslefaure.github.io/assets/html/moviecore.html.

In mixed-traffic environments, autonomous vehicles must adapt to human-controlled vehicles and other unusual driving situations. This setting can be framed as a multi-agent reinforcement learning (MARL) environment with full cooperative reward among the autonomous vehicles. While methods such as Multi-agent Proximal Policy Optimization can be effective in training MARL tasks, they often fail to resolve local conflict between agents and are unable to generalize to stochastic events. In this paper, we propose a Local State Attention module to assist the input state representation. By relying on the self-attention operator, the module is expected to compress the essential information of nearby agents to resolve the conflict in traffic situations. Utilizing a simulated highway merging scenario with the priority vehicle as the unexpected event, our approach is able to prioritize other vehicles' information to manage the merging process. The results demonstrate significant improvements in merging efficiency compared to popular baselines, especially in high-density traffic settings.

Web agents powered by Large Language Models (LLMs) show promise for next-generation AI, but their limited reasoning in uncertain, dynamic web environments hinders robust deployment. In this paper, we identify key reasoning skills essential for effective web agents, i.e., reflection & lookahead, branching, and rollback, and curate trajectory data that exemplifies these abilities by reconstructing the agent's (inference-time) reasoning algorithms into chain-of-thought rationales. We conduct experiments in the agent self-improving benchmark, OpenWebVoyager, and demonstrate that distilling salient reasoning patterns into the backbone LLM via simple fine-tuning can substantially enhance its performance. Our approach yields significant improvements across multiple benchmarks, including WebVoyager, Mind2web-live, and SimpleQA (web search), highlighting the potential of targeted reasoning skill enhancement for web agents.

Competitive tasks have long served as benchmarks for progress in artificial intelligence. Landmark results have been achieved in domains such as Go [1], poker [2], and real-time strategy games [3], where agents learn to plan, adapt, and compete under structured rules. As research moves from virtual environments to the physical world, robot sports-structured, rule-based competitions involving physical agents-have emerged as a promising frontier for embodied intelligence. Examples include robot soccer [4, 5], table tennis [6, 7], and multi-drone pursuit-evasion [8], which combine high-level strategy with low-level motion control in physically grounded settings. In this paper, we tackle a new embodied competitive task proposed by the V olleyBots testbed [9]: 3v3 multi-drone volleyball. This task exemplifies the structure of a robot sport-well-defined objectives, explicit rules, and head-to-head competition-while presenting a set of unique and underex-plored challenges. Each team must coordinate three quadrotors to rally a ball over a net, switching roles dynamically between offense and defense in a turn-based fashion. The environment is highly dynamic and demands precise timing, agile 3D maneuvering, and strategic team-level behavior. The turn-based nature of ball exchange introduces long-horizon temporal dependencies; the multi-agent setting requires tightly coupled tactics; and the underactuated dynamics of quadrotors call for fine-grained, reactive motor skills.

This paper introduces the concept of a mean for trajectories and multi-object trajectories (defined as sets or multi-sets of trajectories) along with algorithms for computing them. Specifically, we use the Fréchet mean, and metrics based on the optimal sub-pattern assignment (OSPA) construct, to extend the notion of average from vectors to trajectories and multi-object trajectories. Further, we develop efficient algorithms to compute these means using greedy search and Gibbs sampling. Using distributed multi-object tracking as an application, we demonstrate that the Fréchet mean approach to multi-object trajectory consensus significantly outperforms state-of-the-art distributed multi-object tracking methods.

The development and evaluation of social capabilities in AI agents require complex environments where competitive and cooperative behaviours naturally emerge. While game-theoretic properties can explain why certain teams or agent populations outperform others, more abstract behaviours, such as convention following, are harder to control in training and evaluation settings. The Melting Pot contest is a social AI evaluation suite designed to assess the cooperation capabilities of AI systems. In this paper, we apply a Bayesian approach known as Measurement Layouts to infer the capability profiles of multi-agent systems in the Melting Pot contest. We show that these capability profiles not only predict future performance within the Melting Pot suite but also reveal the underlying prosocial abilities of agents. Our analysis indicates that while higher prosocial capabilities sometimes correlate with better performance, this is not a universal trend-some lower-scoring agents exhibit stronger cooperation abilities. Furthermore, we find that top-performing contest submissions are more likely to achieve high scores in scenarios where prosocial capabilities are not required. These findings, together with reports that the contest winner used a hard-coded solution tailored to specific environments, suggest that at least one top-performing team may have optimised for conditions where cooperation was not necessary, potentially exploiting limitations in the evaluation framework. We provide recommendations for improving the annotation of cooperation demands and propose future research directions to account for biases introduced by different testing environments. Our results demonstrate that Measurement Layouts offer both strong predictive accuracy and actionable insights, contributing to a more transparent and generalisable approach to evaluating AI systems in complex social settings.

Multi-agent reinforcement learning (MARL) has emerged as a powerful paradigm for coordinating swarms of agents in complex decision-making, yet major challenges remain. In competitive settings such as pursuer-evader tasks, simultaneous adaptation can destabilize training; non-kinetic countermeasures often fail under adverse conditions; and policies trained in one configuration rarely generalize to environments with a different number of agents. To address these issues, we propose the Local-Canonicalization Equivariant Graph Neural Networks (LEGO) framework, which integrates seamlessly with popular MARL algorithms such as MAPPO. LEGO employs graph neural networks to capture permutation equivariance and generalization to different agent numbers, canonicalization to enforce E(n)-equivariance, and heterogeneous representations to encode role-specific inductive biases. Experiments on cooperative and competitive swarm benchmarks show that LEGO outperforms strong baselines and improves generalization. In real-world experiments, LEGO demonstrates robustness to varying team sizes and agent failure.

Web agents powered by large language models (LLMs) can autonomously perform complex, multistep tasks in dynamic web environments. However, current evaluations mostly focus on the overall success while overlooking intermediate errors. This limits insight into failure modes and hinders systematic improvement. This work analyzes existing benchmarks and highlights the lack of fine-grained diagnostic tools. To address this gap, we propose a modular evaluation framework that decomposes agent pipelines into interpretable stages for detailed error analysis. Using the SeeAct framework and the Mind2Web dataset as a case study, we show how this approach reveals actionable weaknesses missed by standard metrics - paving the way for more robust and generalizable web agents.

Professional sports teams pour millions of dollars into data analytics, using advanced tracking systems to study every sprint, pass, and decision on the field. The results of that analysis, however, are industry secrets, making many sports difficult for researchers to study. Now, two University of Waterloo researchers, Dr. David Radke and Kyle Tilbury, are using AI to level the playing field. By tapping into Google Research Football's reinforcement learning environment, the researchers developed a system that can simulate and record unlimited soccer matches. To get things started, they generated and saved data from 3,000 simulated soccer games, resulting in a rich and complex dataset of passes, goals, and player movements for researchers to study.

The challenge of aligning artificial intelligence (AI) with human values persists due to the abstract and often conflicting nature of moral principles and the opacity of existing approaches. This paper introduces CogniAlign, a multi-agent deliberation framework based on naturalistic moral realism, that grounds moral reasoning in survivability, defined across individual and collective dimensions, and operationalizes it through structured deliberations among discipline-specific scientist agents. Each agent, representing neuroscience, psychology, sociology, and evolutionary biology, provides arguments and rebuttals that are synthesized by an arbiter into transparent and empirically anchored judgments. We evaluate CogniAlign on classic and novel moral questions and compare its outputs against GPT-4o using a five-part ethical audit framework. Results show that CogniAlign consistently outperforms the baseline across more than sixty moral questions, with average performance gains of 16.2 points in analytic quality, 14.3 points in breadth, and 28.4 points in depth of explanation. In the Heinz dilemma, for example, CogniAlign achieved an overall score of 89.2 compared to GPT-4o's 69.2, demonstrating a decisive advantage in handling moral reasoning. By reducing black-box reasoning and avoiding deceptive alignment, CogniAlign highlights the potential of interdisciplinary deliberation as a scalable pathway for safe and transparent AI alignment.