Multi-agent reinforcement learning (MARL) holds substantial promise for intelligent decision-making in complex environments. However, it suffers from a coordination and scalability bottleneck as the number of agents increases. To address these issues, we propose the LLM-empowered expert demonstrations framework for multi-agent reinforcement learning (LEED). LEED consists of two components: a demonstration generation (DG) module and a policy optimization (PO) module. Specifically, the DG module leverages large language models to generate instructions for interacting with the environment, thereby producing high-quality demonstrations. The PO module adopts a decentralized training paradigm, where each agent utilizes the generated demonstrations to construct an expert policy loss, which is then integrated with its own policy loss. This enables each agent to effectively personalize and optimize its local policy based on both expert knowledge and individual experience. Experimental results show that LEED achieves superior sample efficiency, time efficiency, and robust scalability compared to state-of-the-art baselines.

With the growing adoption of Large Language Models (LLMs) in automating complex, multi-agent workflows, organizations face mounting risks from errors, emergent behaviors, and systemic failures that current evaluation methods fail to capture. We present AgentCompass, the first evaluation framework designed specifically for post-deployment monitoring and debugging of agentic workflows. AgentCompass models the reasoning process of expert debuggers through a structured, multi-stage analytical pipeline: error identification and categorization, thematic clustering, quantitative scoring, and strategic summarization. The framework is further enhanced with a dual memory system-episodic and semantic-that enables continual learning across executions. Through collaborations with design partners, we demonstrate the framework's practical utility on real-world deployments, before establishing its efficacy against the publicly available TRAIL benchmark. AgentCompass achieves state-of-the-art results on key metrics, while uncovering critical issues missed in human annotations, underscoring its role as a robust, developer-centric tool for reliable monitoring and improvement of agentic systems in production.

Recent studies have shown that carefully designed workflows coordinating large language models(LLMs) significantly enhance task-solving capabilities compared to using a single model. While an increasing number of works focus on autonomous workflow construction, most existing approaches rely solely on historical experience, leading to limitations in efficiency and adaptability. We argue that while historical experience is valuable, workflow construction should also flexibly respond to the unique characteristics of each task. To this end, we propose an a priori dynamic framework for automated workflow construction. Our framework first leverages Q-table learning to optimize the decision space, guiding agent decisions and enabling effective use of historical experience. At the same time, agents evaluate the current task progress and make a priori decisions regarding the next executing agent, allowing the system to proactively select the more suitable workflow structure for each given task. Additionally, we incorporate mechanisms such as cold-start initialization, early stopping, and pruning to further improve system efficiency. Experimental evaluations on four benchmark datasets demonstrate the feasibility and effectiveness of our approach. Compared to state-of-the-art baselines, our method achieves an average improvement of 4.05%, while reducing workflow construction and inference costs to only 30.68%-48.31% of those required by existing methods.

Capturing professionals' decision-making in creative workflows is essential for reflection, collaboration, and knowledge sharing, yet existing methods often leave rationales incomplete and implicit decisions hidden. To address this, we present CLEAR framework that structures reasoning into cognitive decision steps-linked units of actions, artifacts, and self-explanations that make decisions traceable. Building on this framework, we introduce ClearFairy, a think-aloud AI assistant for UI design that detects weak explanations, asks lightweight clarifying questions, and infers missing rationales to ease the knowledge-sharing burden. In a study with twelve creative professionals, 85% of ClearFairy's inferred rationales were accepted, increasing strong explanations from 14% to over 83% of decision steps without adding cognitive demand. The captured steps also enhanced generative AI agents in Figma, yielding next-action predictions better aligned with professionals and producing more coherent design outcomes. For future research on human knowledge-grounded creative AI agents, we release a dataset of captured 417 decision steps.

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.