While AI excels at generating text, audio, images, and videos, creating interactive audio-visual content such as video games remains challenging. Current LLMs can generate JavaScript games and animations, but lack automated evaluation metrics and struggle with complex content that normally requires teams of humans working for many months (multi-shot, multi-agents) using assets made by artists. To tackle these issues, we built a new metric and a multi-agent system. We propose AVR-Eval, a relative metric for multimedia content quality using Audio-Visual Recordings (AVRs). An omni-modal model (processing text, video, and audio) compares the AVRs of two contents, with a text model reviewing evaluations to determine superiority. We show that AVR-Eval properly identifies good from broken or mismatched content. We built AVR-Agent, a multi-agent system generating JavaScript code from a bank of multimedia assets (audio, images, 3D models). The coding agent selects relevant assets, generates multiple initial codes, uses AVR-Eval to identify the best version, and iteratively improves it through omni-modal agent feedback from the AVR. We run experiments on games and animations with AVR-Eval (win rate of content A against B). We find that content generated by AVR-Agent has a significantly higher win rate against content made through one-shot generation. However, models struggle to leverage custom assets and AVR feedback effectively, showing no higher win rate. This reveals a critical gap: while humans benefit from high-quality assets and audio-visual feedback, current coding models do not seem to utilize these resources as effectively, highlighting fundamental differences between human and machine content creation approaches.

-- The rapid iteration of autonomous vehicle (A V) deployments leads to increasing needs for building realistic and scalable multi-agent traffic simulators for efficient evaluation. Recent advances in this area focus on closed-loop simulators that enable generating diverse and interactive scenarios. This paper introduces Neural Interactive Agents (NIV A), a probabilistic framework for multi-agent simulation driven by a hierarchical Bayesian model that enables closed-loop, observation-conditioned simulation through autoregressive sampling from a latent, finite mixture of Gaussian distributions. We demonstrate how NIV A unifies preexisting sequence-to-sequence trajectory prediction models and emerging closed-loop simulation models trained on Next-token Prediction (NTP) from a Bayesian inference perspective. Experiments on the Waymo Open Motion Dataset demonstrate that NIV A attains competitive performance compared to the existing method while providing embellishing control over intentions and driving styles.

We present a Collaborative Agent-Based Framework for Multi-Image Reasoning. Our approach tackles the challenge of interleaved multimodal reasoning across diverse datasets and task formats by employing a dual-agent system: a language-based PromptEngineer, which generates context-aware, task-specific prompts, and a VisionReasoner, a large vision-language model (LVLM) responsible for final inference. The framework is fully automated, modular, and training-free, enabling generalization across classification, question answering, and free-form generation tasks involving one or multiple input images. We evaluate our method on 18 diverse datasets from the 2025 MIRAGE Challenge (Track A), covering a broad spectrum of visual reasoning tasks including document QA, visual comparison, dialogue-based understanding, and scene-level inference. Our results demonstrate that LVLMs can effectively reason over multiple images when guided by informative prompts. Notably, Claude 3.7 achieves near-ceiling performance on challenging tasks such as TQA (99.13% accuracy), DocVQA (96.87%), and MMCoQA (75.28 ROUGE-L). We also explore how design choices-such as model selection, shot count, and input length-influence the reasoning performance of different LVLMs.

The fast development of Artificial Intelligence (AI) agents provides a promising way for the realization of intelligent and customized wireless networks. In this paper, we propose a Wireless Multi-Agent System (WMAS), which can provide intelligent and customized services for different user equipment (UEs). Note that orchestrating multiple agents carries the risk of malfunction, and multi-agent conversations may fall into infinite loops. It is thus crucial to design a conversation topology for WMAS that enables agents to complete UE task requests with high accuracy and low conversation overhead. To address this issue, we model the multi-agent conversation topology as a directed acyclic graph and propose a reinforcement learning-based algorithm to optimize the adjacency matrix of this graph. As such, WMAS is capable of generating and self-optimizing multi-agent conversation topologies, enabling agents to effectively and collaboratively handle a variety of task requests from UEs. Simulation results across various task types demonstrate that WMAS can achieve higher task performance and lower conversation overhead compared to existing multi-agent systems. These results validate the potential of WMAS to enhance the intelligence of future wireless networks.

With the development of large models and autonomous decision-making AI, agents are rapidly becoming the new entities of the internet, following mobile apps. However, existing internet infrastructure is primarily designed for human interaction, creating data silos, unfriendly interfaces, and high collaboration costs among agents, making it difficult to support the needs for large-scale agent interconnection and collaboration. The internet is undergoing a profound transformation, showing four core trends: agents replacing traditional software, universal agent interconnection, native protocol-based connections, and autonomous agent organization and collaboration. T o align with these trends, Agent Network Protocol (ANP) proposes a new generation of communication protocols for the Agentic Web. ANP adheres to AI-native design, maintains compatibility with existing internet protocols, adopts a modular composable architecture, follows minimalist yet extensible principles, and enables rapid deployment based on existing infrastructure.

Neoclassical economics identifies preferences with choice s. That Alice prefers x to y means only that Alice chooses x when presented with the binary-choice problem "would you li ke x or y?" As a consequence of this view, and given the great availabi lity of choice data from various sources, economists have developed and used an extensi ve methodology for analyzing choice data. Choice data are used in estimating preferences, in predicting agents' behavior out of sample, and in conducting counterfactual analysis. Ther e is, however, a growing acceptance in the profession that preferences could be meaningful beyo nd their interpretation as choices. Many economists now think that non-choice data have a role to play in the estimation of preferences and the prediction of agents' behavior. Now, while t here is substantial interest in the use of non-choice data, there is not yet a mature statistical methodological body of work designed for working with economic non-choice data. Our paper presents progress towards such a methodology . W e develop empirical methodology to estimate preferences f rom choice and response-time data.

We develop information theory for the temporal behavior of memoryful agents moving through complex -- structured, stochastic -- environments. We introduce and explore information processes -- stochastic processes produced by cognitive agents in real-time as they interact with and interpret incoming stimuli. We provide basic results on the ergodicity and semantics of the resulting time series of Shannon information measures that monitor an agent's adapting view of uncertainty and structural correlation in its environment.

The main objective of this paper is to introduce a transfer learning-enhanced deep reinforcement learning (DRL) methodology that is able to optimise the geometry of any airfoil based on concomitant aerodynamic and structural integrity criteria. To showcase the method, we aim to maximise the lift-to-drag ratio $C_L/C_D$ while preserving the structural integrity of the airfoil -- as modelled by its maximum thickness -- and train the DRL agent using a list of different transfer learning (TL) strategies. The performance of the DRL agent is compared with Particle Swarm Optimisation (PSO), a traditional gradient-free optimisation method. Results indicate that DRL agents are able to perform purely aerodynamic and hybrid aerodynamic/structural shape optimisation, that the DRL approach outperforms PSO in terms of computational efficiency and aerodynamic improvement, and that the TL-enhanced DRL agent achieves performance comparable to the DRL one, while further saving substantial computational resources.

The increasing demand for automation and flexibility drives the widespread adoption of heterogeneous automated guided vehicles (AGVs). This work intends to investigate a new scheduling problem in a material transportation system consisting of attachable heterogeneous AGVs, namely carriers and shuttles. They can flexibly attach to and detach from each other to cooperatively execute complex transportation tasks. While such collaboration enhances operational efficiency, the attachment-induced synchronization and interdependence render the scheduling coupled and susceptible to deadlock. To tackle this challenge, Petri nets are introduced to model AGV schedules, well describing the concurrent and sequential task execution and carrier-shuttle synchronization. Based on Petri net theory, a firing-driven decoding method is proposed, along with deadlock detection and prevention strategies to ensure deadlock-free schedules. Furthermore, a Petri net-based metaheuristic is developed in an adaptive large neighborhood search framework and incorporates an effective acceleration method to enhance computational efficiency. Finally, numerical experiments using real-world industrial data validate the effectiveness of the proposed algorithm against the scheduling policy applied in engineering practice, an exact solver, and four state-of-the-art metaheuristics. A sensitivity analysis is also conducted to provide managerial insights.

--Modern cyber attacks unfold through multiple stages, requiring defenders to dynamically prioritize mitigations under uncertainty. While game-theoretic models capture attacker-defender interactions, existing approaches often rely on static assumptions and lack integration with real-time threat intelligence, limiting their adaptability. This paper presents Cy-GATE, a game-theoretic framework modeling attacker-defender interactions, using large language models (LLMs) with retrieval-augmented generation (RAG) to enhance tactic selection and patch prioritization. Applied to a two-agent scenario, CyGATE frames cyber conflicts as a partially observable stochastic game (POSG) across Cyber Kill Chain stages. Both agents use belief states to navigate uncertainty, with the attacker adapting tactics and the defender re-prioritizing patches based on evolving risks and observed adversary behavior . The framework's flexible architecture enables extension to multi-agent scenarios involving coordinated attackers, collaborative defenders, or complex enterprise environments with multiple stakeholders. The evolving cybersecurity landscape presents increasingly sophisticated threats that necessitate adaptive, proactive defense strategies. Patch management, a cornerstone of cyber defense, requires intelligent prioritization of vulnerabilities under resource constraints such as maintenance windows and operational cost [1] [2] . However, traditional scoring systems like common vulnerability scoring system (CVSS) [3] fail to capture the evolving nature of cyber threats, where attackers adapt their strategies based on defender actions. Game theory provides a structured framework for modeling attacker-defender interactions [4], with chained or multistage games particularly suited to representing complex attack progressions along the Cyber Kill Chain (CKC) [5][6][7]. These models allow defenders to reason about long-term risks and preempt cascading compromises. Despite these advancements, existing models remain constrained by fixed strategies, static payoff structures, and minimal integration of threat intelligence, failing to dynamically prioritize vulnerabilities based on evolving exploitation trends [8]. Traditional game-theoretical approaches typically use predefined rules to analyze strategies, hence are limited in dynamic cyber environments where adversaries continuously adapt, operate under uncertainty, and employ unpredictable tactics [9].