While game-theoretic planning frameworks are effective at modeling multi-agent interactions, they require solving large optimization problems where the number of variables increases with the number of agents, resulting in long computation times that limit their use in large-scale, real-time systems. To address this issue, we propose 1) PSN Game: a learning-based, game-theoretic prediction and planning framework that reduces runtime by learning a Player Selection Network (PSN); and 2) a Goal Inference Network (GIN) that makes it possible to use the PSN in incomplete information games where agents' intentions are unknown. A PSN outputs a player selection mask that distinguishes influential players from less relevant ones, enabling the ego player to solve a smaller, masked game involving only selected players. By reducing the number of players in the game, and therefore reducing the number of variables in the corresponding optimization problem, PSN directly lowers computation time. The PSN Game framework is more flexible than existing player selection methods as it 1) relies solely on observations of players' past trajectories, without requiring full state, action, or other game-specific information; and 2) requires no online parameter tuning. Experiments in both simulated scenarios and human trajectory datasets demonstrate that PSNs outperform baseline selection methods in 1) prediction accuracy; and 2) planning safety. PSNs also generalize effectively to real-world scenarios in which agents' objectives are unknown without fine-tuning. By selecting only the most relevant players for decision-making, PSN Game offers a general mechanism for reducing planning complexity that can be seamlessly integrated into existing multi-agent planning frameworks.

The Finite Element Method (FEM) is widely used in engineering and scientific computing, but its pre-processing, solver configuration, and post-processing stages are often time-consuming and require specialized knowledge. This paper proposes an automated solution framework, MooseAgent, for the multi-physics simulation framework MOOSE, which combines large-scale pre-trained language models (LLMs) with a multi-agent system. The framework uses LLMs to understand user-described simulation requirements in natural language and employs task decomposition and multi-round iterative verification strategies to automatically generate MOOSE input files. To improve accuracy and reduce model hallucinations, the system builds and utilizes a vector database containing annotated MOOSE input cards and function documentation. We conducted experimental evaluations on several typical cases, including heat transfer, mechanics, phase field, and multi-physics coupling. The results show that MooseAgent can automate the MOOSE simulation process to a certain extent, especially demonstrating a high success rate when dealing with relatively simple single-physics problems. The main contribution of this research is the proposal of a multi-agent automated framework for MOOSE, which validates its potential in simplifying finite element simulation processes and lowering the user barrier, providing new ideas for the development of intelligent finite element simulation software. The code for the MooseAgent framework proposed in this paper has been open-sourced and is available at https://github.com/taozhan18/MooseAgent

Over the past two decades, researchers have made significant steps in simulating agent-based human crowds, yet most efforts remain focused on low-level tasks such as collision avoidance, path following, and flocking. Realistic simulations, however, require modeling high-level behaviors that emerge from agents interacting with each other and with their environment over time. We introduce Generative Crowds (Gen-C), a generative framework that produces crowd scenarios capturing agent-agent and agent-environment interactions, shaping coherent high-level crowd plans. To avoid the labor-intensive process of collecting and annotating real crowd video data, we leverage large language models (LLMs) to bootstrap synthetic datasets of crowd scenarios. We propose a time-expanded graph representation, encoding actions, interactions, and spatial context. Gen-C employs a dual Variational Graph Autoencoder (VGAE) architecture that jointly learns connectivity patterns and node features conditioned on textual and structural signals, overcoming the limitations of direct LLM generation to enable scalable, environment-aware multi-agent crowd simulations. We demonstrate the effectiveness of Gen-C on scenarios with diverse behaviors such as a University Campus and a Train Station, showing that it generates heterogeneous crowds, coherent interactions, and high-level decision-making patterns consistent with real-world crowd dynamics.

Multimodal Large Language Models (MLLMs) have demonstrated significant capabilities in joint visual and linguistic tasks. However, existing Visual Question Answering (VQA) benchmarks often fail to evaluate deep semantic understanding, particularly in complex domains like visual art analysis. Confined to simple syntactic structures and surface-level attributes, these questions fail to capture the diversity and depth of human visual inquiry. This limitation incentivizes models to exploit statistical shortcuts rather than engage in visual reasoning. To address this gap, we introduce VQArt-Bench, a new, large-scale VQA benchmark for the cultural heritage domain. This benchmark is constructed using a novel multi-agent pipeline where specialized agents collaborate to generate nuanced, validated, and linguistically diverse questions. The resulting benchmark is structured along relevant visual understanding dimensions that probe a model's ability to interpret symbolic meaning, narratives, and complex visual relationships. Our evaluation of 14 state-of-the-art MLLMs on this benchmark reveals significant limitations in current models, including a surprising weakness in simple counting tasks and a clear performance gap between proprietary and open-source models.

With advancements in reasoning capabilities, Large Language Models (LLMs) are increasingly employed for automated judgment tasks. While LLMs-as-Judges offer promise in automating evaluations, current approaches often rely on simplistic aggregation methods (e.g., majority voting), which can fail even when individual agents provide correct answers. To address this, we propose a multi-agent debate judge framework where agents collaboratively reason and iteratively refine their responses. We formalize the debate process mathematically, analyzing agent interactions and proving that debate amplifies correctness compared to static ensembles. To enhance efficiency, we introduce a stability detection mechanism that models judge consensus dynamics via a time-varying Beta-Binomial mixture, with adaptive stopping based on distributional similarity (Kolmogorov-Smirnov test). This mechanism models the judges' collective correct rate dynamics using a time-varying mixture of Beta-Binomial distributions and employs an adaptive stopping criterion based on distributional similarity (Kolmogorov-Smirnov statistic). Experiments across multiple benchmarks and models demonstrate that our framework improves judgment accuracy over majority voting while maintaining computational efficiency.

Recent advances in embodied AI highlight the potential of vision language models (VLMs) as agents capable of perception, reasoning, and interaction in complex environments. However, top-performing systems rely on large-scale models that are costly to deploy, while smaller VLMs lack the necessary knowledge and skills to succeed. To bridge this gap, we present \textit{Embodied Reasoning Agent (ERA)}, a two-stage framework that integrates prior knowledge learning and online reinforcement learning (RL). The first stage, \textit{Embodied Prior Learning}, distills foundational knowledge from three types of data: (1) Trajectory-Augmented Priors, which enrich existing trajectory data with structured reasoning generated by stronger models; (2) Environment-Anchored Priors, which provide in-environment knowledge and grounding supervision; and (3) External Knowledge Priors, which transfer general knowledge from out-of-environment datasets. In the second stage, we develop an online RL pipeline that builds on these priors to further enhance agent performance. To overcome the inherent challenges in agent RL, including long horizons, sparse rewards, and training instability, we introduce three key designs: self-summarization for context management, dense reward shaping, and turn-level policy optimization. Extensive experiments on both high-level planning (EB-ALFRED) and low-level control (EB-Manipulation) tasks demonstrate that ERA-3B surpasses both prompting-based large models and previous training-based baselines. Specifically, it achieves overall improvements of 8.4\% on EB-ALFRED and 19.4\% on EB-Manipulation over GPT-4o, and exhibits strong generalization to unseen tasks. Overall, ERA offers a practical path toward scalable embodied intelligence, providing methodological insights for future embodied AI systems.

We present a novel framework for human-robot \emph{logical} interaction that enables robots to reliably satisfy (infinite horizon) temporal logic tasks while effectively collaborating with humans who pursue independent and unknown tasks. The framework combines two key capabilities: (i) \emph{maximal adaptation} enables the robot to adjust its strategy \emph{online} to exploit human behavior for cooperation whenever possible, and (ii) \emph{minimal tunable feedback} enables the robot to request cooperation by the human online only when necessary to guarantee progress. This balance minimizes human-robot interference, preserves human autonomy, and ensures persistent robot task satisfaction even under conflicting human goals. We validate the approach in a real-world block-manipulation task with a Franka Emika Panda robotic arm and in the Overcooked-AI benchmark, demonstrating that our method produces rich, \emph{emergent} cooperative behaviors beyond the reach of existing approaches, while maintaining strong formal guarantees.

Prehistoric humans invented stone tools for specialized tasks by not just maximizing the tool's immediate goal-completion accuracy, but also increasing their confidence in the tool for later use under similar settings. This factor contributed to the increased robustness of the tool, i.e., the least performance deviations under environmental uncertainties. However, the current autonomous tool design frameworks solely rely on performance optimization, without considering the agent's confidence in tool use for repeated use. Here, we take a step towards filling this gap by i) defining an optimization framework for task-conditioned autonomous hand tool design for robots, where ii) we introduce a neuro-inspired control confidence term into the optimization routine that helps the agent to design tools with higher robustness. Through rigorous simulations using a robotic arm, we show that tools designed with control confidence as the objective function are more robust to environmental uncertainties during tool use than a pure accuracy-driven objective. We further show that adding control confidence to the objective function for tool design provides a balance between the robustness and goal accuracy of the designed tools under control perturbations. Finally, we show that our CMAES-based evolutionary optimization strategy for autonomous tool design outperforms other state-of-the-art optimizers by designing the optimal tool within the fewest iterations. Code: https://github.com/ajitham123/Tool_design_control_confidence.

Context: Modern Systems of Systems (SoSs) increasingly operate in dynamic environments (e.g., smart cities, autonomous vehicles) where runtime composition -- the on-the-fly discovery, integration, and coordination of constituent systems (CSs)--is crucial for adaptability. Despite growing interest, the literature lacks a cohesive synthesis of runtime composition in dynamic SoSs. Objective: This study synthesizes research on runtime composition in dynamic SoSs and identifies core challenges, solution strategies, supporting tools, and evaluation methods. Methods: We conducted a Systematic Literature Review (SLR), screening 1,774 studies published between 2019 and 2024 and selecting 80 primary studies for thematic analysis (TA). Results: Challenges fall into four categories: modeling and analysis, resilient operations, system orchestration, and heterogeneity of CSs. Solutions span seven areas: co-simulation and digital twins, semantic ontologies, integration frameworks, adaptive architectures, middleware, formal methods, and AI-driven resilience. Service-oriented frameworks for composition and integration dominate tooling, while simulation platforms support evaluation. Interoperability across tools, limited cross-toolchain workflows, and the absence of standardized benchmarks remain key gaps. Evaluation approaches include simulation-based, implementation-driven, and human-centered studies, which have been applied in domains such as smart cities, healthcare, defense, and industrial automation. Conclusions: The synthesis reveals tensions, including autonomy versus coordination, the modeling-reality gap, and socio-technical integration. It calls for standardized evaluation metrics, scalable decentralized architectures, and cross-domain frameworks. The analysis aims to guide researchers and practitioners in developing and implementing dynamically composable SoSs.

The competitive and cooperative forces of natural selection have driven the evolution of intelligence for millions of years, culminating in nature's vast biodiversity and the complexity of human minds. Inspired by this process, we propose a novel multi-agent reinforcement learning framework where each agent is assigned a genotype and where reward functions are modelled after the concept of inclusive fitness. An agent's genetic material may be shared with other agents, and our inclusive reward function naturally accounts for this. We study the resulting social dynamics in two types of network games with prisoner's dilemmas and find that our results align with well-established principles from biology, such as Hamilton's rule. Furthermore, we outline how this framework can extend to more open-ended environments with spatial and temporal structure, finite resources, and evolving populations. We hypothesize the emergence of an arms race of strategies, where each new strategy is a gradual improvement over earlier adaptations of other agents, effectively producing a multi-agent autocurriculum analogous to biological evolution. In contrast to the binary team-based structures prevalent in earlier research, our gene-based reward structure introduces a spectrum of cooperation ranging from full adversity to full cooperativeness based on genetic similarity, enabling unique non team-based social dynamics. For example, one agent having a mutual cooperative relationship with two other agents, while the two other agents behave adversarially towards each other. We argue that incorporating inclusive fitness in agents provides a foundation for the emergence of more strategically advanced and socially intelligent agents.