Abstract--LLM-based agents have shown promise in various cooperative and strategic reasoning tasks, but their effectiveness in competitive multi-agent environments remains underexplored. T o address this gap, we introduce PillagerBench, a novel framework for evaluating multi-agent systems in real-time competitive team-vs-team scenarios in Minecraft. It provides an extensible API, multi-round testing, and rule-based built-in opponents for fair, reproducible comparisons. We also propose T actiCrafter, an LLM-based multi-agent system that facilitates teamwork through human-readable tactics, learns causal dependencies, and adapts to opponent strategies. Our evaluation demonstrates that T actiCrafter outperforms baseline approaches and showcases adaptive learning through self-play. Additionally, we analyze its learning process and strategic evolution over multiple game episodes. T o encourage further research, we have open-sourced PillagerBench, fostering advancements in multi-agent AI for competitive environments. Witnessing rapid advancements, Large Language Models (LLMs) have emerged as powerful tools for complex reasoning, decision-making, and facilitating multi-agent collaboration [27, 20, 22]. This has driven increasing interest in developing cooperative multi-agent systems [3, 7], leading to the creation of benchmarks based on diverse cooperative games such as Minecraft [4] and Overcooked [1]. Minecraft, in particular, has become an important platform due to its open-ended environment and rich state and action spaces [19, 25]. However, current Minecraft-based benchmarks mainly address cooperative tasks characterized by stationary dynamics and fixed objectives, making them insufficient for evaluating adaptability and strategic decision-making in competitive, dynamic environments. Traditional reinforcement learning benchmarks like StarCraft Multi-Agent Challenge (SMAC) [16] and Lux AI Challenge [18] introduce instability and nonstationarity through competitive adversaries but lack the rich, open-ended interactions found in Minecraft. Bridging this gap by integrating both cooperative and competitive elements within a single dynamic environment is essential to rigorously assess the adaptability and generalizability of advanced multi-agent systems.

Multi-agent reinforcement learning (MARL) has achieved significant progress in solving complex multi-player games through self-play. However, training effective adversarial policies requires millions of experience samples and substantial computational resources. Moreover, these policies lack interpretability, hindering their practical deployment. Recently, researchers have successfully leveraged Large Language Models (LLMs) to generate programmatic policies for single-agent tasks, transforming neural network-based policies into interpretable rule-based code with high execution efficiency. Inspired by this, we propose PolicyEvolve, a general framework for generating programmatic policies in multi-player games. PolicyEvolve significantly reduces reliance on manually crafted policy code, achieving high-performance policies with minimal environmental interactions. The framework comprises four modules: Global Pool, Local Pool, Policy Planner, and Trajectory Critic. The Global Pool preserves elite policies accumulated during iterative training. The Local Pool stores temporary policies for the current iteration; only sufficiently high-performing policies from this pool are promoted to the Global Pool. The Policy Planner serves as the core policy generation module. It samples the top three policies from the Global Pool, generates an initial policy for the current iteration based on environmental information, and refines this policy using feedback from the Trajectory Critic. Refined policies are then deposited into the Local Pool. This iterative process continues until the policy achieves a sufficiently high average win rate against the Global Pool, at which point it is integrated into the Global Pool. The Trajectory Critic analyzes interaction data from the current policy, identifies vulnerabilities, and proposes directional improvements to guide the Policy Planner

Game-based interactive driving simulations have emerged as versatile platforms for advancing decision-making algorithms in road transport mobility. While these environments offer safe, scalable, and engaging settings for testing driving strategies, ensuring both realism and robust performance amid dynamic and diverse scenarios remains a significant challenge. Recently, the integration of game-based techniques with advanced learning frameworks has enabled the development of adaptive decision-making models that effectively manage the complexities inherent in varied driving conditions. These models outperform traditional simulation methods, especially when addressing scenario-specific challenges, ranging from obstacle avoidance on highways and precise maneuvering during on-ramp merging to navigation in roundabouts, unsignalized intersections, and even the high-speed demands of autonomous racing. Despite numerous innovations in game-based interactive driving, a systematic review comparing these approaches across different scenarios is still missing. This survey provides a comprehensive evaluation of game-based interactive driving methods by summarizing recent advancements and inherent roadway features in each scenario. Furthermore, the reviewed algorithms are critically assessed based on their adaptation of the standard game model and an analysis of their specific mechanisms to understand their impact on decision-making performance. Finally, the survey discusses the limitations of current approaches and outlines promising directions for future research.

With the evolution of generative AI, multi - agent systems leveraging large - language models(LLMs) have emerged as a powerful tool for complex tasks. However, these systems face challenges in quantifying agent performance and lack mechanisms to assess agent credibility. To address these issues, we introduce DRF, a dynamic reputation filtering framework. DRF constructs an interactive rating network to quantify agent performance, designs a reputation scoring mechanism to measure agent honesty and capability, and integrates an Upper Confidence Bound - based strategy to enhance agent selection efficiency. Experiments show that DRF significantly improves task completion quality and collaboration efficiency in logical reasoning and code - generation tasks, offering a new approach for multi - agent systems to handle large - scale tasks.

Data collection is crucial for learning robust world models in model-based reinforcement learning. The most prevalent strategies are to actively collect trajectories by interacting with the environment during online training or training on offline datasets. At first glance, the nature of learning task-agnostic environment dynamics makes world models a good candidate for effective offline training. However, the effects of online vs. offline data on world models and thus on the resulting task performance have not been thoroughly studied in the literature. In this work, we investigate both paradigms in model-based settings, conducting experiments on 31 different environments. First, we showcase that online agents outperform their offline counterparts. We identify a key challenge behind performance degradation of offline agents: encountering Out-Of-Distribution states at test time. This issue arises because, without the self-correction mechanism in online agents, offline datasets with limited state space coverage induce a mismatch between the agent's imagination and real rollouts, compromising policy training. We demonstrate that this issue can be mitigated by allowing for additional online interactions in a fixed or adaptive schedule, restoring the performance of online training with limited interaction data. We also showcase that incorporating exploration data helps mitigate the performance degradation of offline agents. Based on our insights, we recommend adding exploration data when collecting large datasets, as current efforts predominantly focus on expert data alone.

Foundation models face growing compute and memory bottlenecks, hindering deployment on resource-limited platforms. While compression techniques such as pruning and quantization are widely used, most rely on uniform heuristics that ignore architectural and runtime heterogeneity. Profiling tools expose per-layer latency, memory, and compute cost, yet are rarely integrated into automated pipelines. We propose ProfilingAgent, a profiling-guided, agentic approach that uses large language models (LLMs) to automate compression via structured pruning and post-training dynamic quantization. Our modular multi-agent system reasons over static metrics (MACs, parameter counts) and dynamic signals (latency, memory) to design architecture-specific strategies. Unlike heuristic baselines, ProfilingAgent tailors layer-wise decisions to bottlenecks. Experiments on ImageNet-1K, CIFAR-10, and CIFAR-100 with ResNet-101, ViT-B/16, Swin-B, and DeiT-B/16 show pruning maintains competitive or improved accuracy (about 1% drop on ImageNet-1K, +2% gains for ViT-B/16 on smaller datasets), while quantization achieves up to 74% memory savings with <0.5% accuracy loss. Our quantization also yields consistent inference speedups of up to 1.74 times faster. Comparative studies with GPT-4o and GPT-4-Turbo highlight the importance of LLM reasoning quality for iterative pruning. These results establish agentic systems as scalable solutions for profiling-guided model optimization.

Autonomous microrobots in blood vessels could enable minimally invasive therapies, but navigation is challenged by dense, moving obstacles. We propose a real-time path planning framework that couples an analytic geometry global planner (AGP) with two reactive local escape controllers, one based on rules and one based on reinforcement learning, to handle sudden moving obstacles. Using real-time imaging, the system estimates the positions of the microrobot, obstacles, and targets and computes collision-free motions. In simulation, AGP yields shorter paths and faster planning than weighted A* (WA*), particle swarm optimization (PSO), and rapidly exploring random trees (RRT), while maintaining feasibility and determinism. We extend AGP from 2D to 3D without loss of speed. In both simulations and experiments, the combined global planner and local controllers reliably avoid moving obstacles and reach targets. The average planning time is 40 ms per frame, compatible with 25 fps image acquisition and real-time closed-loop control. These results advance autonomous microrobot navigation and targeted drug delivery in vascular environments.

Realistic visual renderings of street-design scenarios are essential for public engagement in active transportation planning. Traditional approaches are labor-intensive, hindering collective deliberation and collaborative decision-making. While AI-assisted generative design shows transformative potential by enabling rapid creation of design scenarios, existing generative approaches typically require large amounts of domain-specific training data and struggle to enable precise spatial variations of design/configuration in complex street-view scenes. We introduce a multi-agent system that edits and redesigns bicycle facilities directly on real-world street-view imagery. The framework integrates lane localization, prompt optimization, design generation, and automated evaluation to synthesize realistic, contextually appropriate designs. Experiments across diverse urban scenarios demonstrate that the system can adapt to varying road geometries and environmental conditions, consistently yielding visually coherent and instruction-compliant results. This work establishes a foundation for applying multi-agent pipelines to transportation infrastructure planning and facility design.

We introduce SasAgent, a multi-agent AI system powered by large language models (LLMs) that automates small-angle scattering (SAS) data analysis by leveraging tools from the SasView software and enables user interaction via text input. SasAgent features a coordinator agent that interprets user prompts and delegates tasks to three specialized agents for scattering length density (SLD) calculation, synthetic data generation, and experimental data fitting. These agents utilize LLM-friendly tools to execute tasks efficiently. These tools, including the model data tool, Retrieval-Augmented Generation (RAG) documentation tool, bump fitting tool, and SLD calculator tool, are derived from the SasView Python library. A user-friendly Gradio-based interface enhances user accessibility. Through diverse examples, we demonstrate SasAgent's ability to interpret complex prompts, calculate SLDs, generate accurate scattering data, and fit experimental datasets with high precision. This work showcases the potential of LLM-driven AI systems to streamline scientific workflows and enhance automation in SAS research.

Traditional fixed architectures struggle to cope with dynamic and unpredictable environments, leading to inefficiencies in energy consumption and connectivity. This paper addresses this gap by proposing an adaptive architecture for drone swarms, leveraging a Large Language Model (LLM) to dynamically select the optimal architecture--centralized, hierarchical, or holonic--based on real-time mission parameters such as task complexity, swarm size, and communication stability. Our system addresses the challenges of scalability, adaptability, and robustness, ensuring efficient energy consumption and maintaining connectivity under varying conditions. Extensive simulations demonstrate that our adaptive architecture outperforms traditional static models in terms of scalability, energy efficiency, and connectivity. These results highlight the potential of our approach to provide a scalable, adaptable, and resilient solution for real-world disaster response scenarios.