Generative agents are rapidly advancing in sophistication, raising urgent questions about how they might coordinate when deployed in online ecosystems. This is particularly consequential in information operations (IOs), influence campaigns that aim to manipulate public opinion on social media. While traditional IOs have been orchestrated by human operators and relied on manually crafted tactics, agentic AI promises to make campaigns more automated, adaptive, and difficult to detect. This work presents the first systematic study of emergent coordination among generative agents in simulated IO campaigns. Using generative agent-based modeling, we instantiate IO and organic agents in a simulated environment and evaluate coordination across operational regimes, from simple goal alignment to team knowledge and collective decision-making. As operational regimes become more structured, IO networks become denser and more clustered, interactions more reciprocal and positive, narratives more homogeneous, amplification more synchronized, and hashtag adoption faster and more sustained. Remarkably, simply revealing to agents which other agents share their goals can produce coordination levels nearly equivalent to those achieved through explicit deliberation and collective voting. Overall, we show that generative agents, even without human guidance, can reproduce coordination strategies characteristic of real-world IOs, underscoring the societal risks posed by increasingly automated, self-organizing IOs.

Assessing scenario coverage is crucial for evaluating the robustness of autonomous agents, yet existing methods rely on expensive human annotations or computationally intensive Large Vision-Language Models (LVLMs). These approaches are impractical for large-scale deployment due to cost and efficiency constraints. To address these shortcomings, we propose SCOUT (Scenario Coverage Oversight and Understanding Tool), a lightweight surrogate model designed to predict scenario coverage labels directly from an agent's latent sensor representations. SCOUT is trained through a distillation process, learning to approximate LVLM-generated coverage labels while eliminating the need for continuous LVLM inference or human annotation. By leveraging precomputed perception features, SCOUT avoids redundant computations and enables fast, scalable scenario coverage estimation. We evaluate our method across a large dataset of real-life autonomous navigation scenarios, demonstrating that it maintains high accuracy while significantly reducing computational cost. Our results show that SCOUT provides an effective and practical alternative for large-scale coverage analysis. While its performance depends on the quality of LVLM-generated training labels, SCOUT represents a major step toward efficient scenario coverage oversight in autonomous systems.

Practical deployment of Multi-Agent Systems (MAS) demands strong test-time performance, motivating methods that guide inference-time search and selectively spend compute to improve quality. We present the Multi-Agent System Process Reward Model (MASPRM). It assigns per-action, per-agent values to partial inter-agent transcripts and acts as an inference-time controller. MASPRM is trained from multi-agent Monte Carlo Tree Search (MCTS) rollouts without requiring step-level human annotations, by propagating returns to local targets. At inference, MASPRM guides step-level beam search and MCTS, focusing computation on promising branches and pruning early. On GSM8K and MATH, MASPRM-guided decoding with an outcome reward model (ORM) applied to the final answer, improves exact match (EM) over a single straight-through MAS pass by $+30.7$ and $+22.9$ points, respectively. A MASPRM trained on GSM8K transfers zero-shot to MATH without retraining, adding $8.4$ EM points at the same budget. MASPRM is a plug-in value model that estimates per-agent progress and complements verifier-style decoders, enabling more reliable, compute-aware multi-agent reasoning. Code: https://github.com/milad1378yz/MASPRM

Unlike static architectures, it enables agents to evolve via an entropy-guided, memory-aware online learning mechanism, retrieving high-value prior cases from an episodic memory bank and exploring diverse historical contexts.

As Electric Vehicle (EV) adoption accelerates in urban environments, optimizing charging infrastructure is vital for balancing user satisfaction, energy efficiency, and financial viability. This study advances beyond static models by proposing a digital twin framework that integrates agent-based decision support with embedded optimization to dynamically simulate EV charging behaviors, infrastructure layouts, and policy responses across scenarios. Applied to a localized urban site (a university campus) in Hanoi, Vietnam, the model evaluates operational policies, EV station configurations, and renewable energy sources. The interactive dashboard enables seasonal analysis, revealing a 20% drop in solar efficiency from October to March, with wind power contributing under 5% of demand, highlighting the need for adaptive energy management. Simulations show that real-time notifications of newly available charging slots improve user satisfaction, while gasoline bans and idle fees enhance slot turnover with minimal added complexity. Embedded metaheuristic optimization identifies near-optimal mixes of fast (30kW) and standard (11kW) solar-powered chargers, balancing energy performance, profitability, and demand with high computational efficiency. This digital twin provides a flexible, computation-driven platform for EV infrastructure planning, with a transferable, modular design that enables seamless scaling from localized to city-wide urban contexts.

Large language models (LLMs) become increasingly integrated into data science workflows for automated system design. However, these LLM-driven data science systems rely solely on the internal reasoning of LLMs, lacking guidance from scientific and theoretical principles. This limits their trustworthiness and robustness, especially when dealing with noisy and complex real-world datasets. This paper provides VDSAgents, a multi-agent system grounded in the Predictability-Computability-Stability (PCS) principles proposed in the Veridical Data Science (VDS) framework. Guided by PCS principles, the system implements a modular workflow for data cleaning, feature engineering, modeling, and evaluation. Each phase is handled by an elegant agent, incorporating perturbation analysis, unit testing, and model validation to ensure both functionality and scientific auditability. We evaluate VDSAgents on nine datasets with diverse characteristics, comparing it with state-of-the-art end-to-end data science systems, such as AutoKaggle and DataInterpreter, using DeepSeek-V3 and GPT-4o as backends. VDSAgents consistently outperforms the results of AutoKaggle and DataInterpreter, which validates the feasibility of embedding PCS principles into LLM-driven data science automation.

The widespread adoption of Large Language Models (LLMs) raises critical concerns about the factual accuracy of their outputs, especially in high-risk domains such as biomedicine, law, and education. Existing evaluation methods for short texts often fail on long-form content due to complex reasoning chains, intertwined perspectives, and cumulative information. To address this, we propose a systematic approach integrating large-scale long-form datasets, multi-agent verification mechanisms, and weighted evaluation metrics. We construct LongHalluQA, a Chinese long-form factuality dataset; and develop MAD-Fact, a debate-based multi-agent verification system. We introduce a fact importance hierarchy to capture the varying significance of claims in long-form texts. Experiments on two benchmarks show that larger LLMs generally maintain higher factual consistency, while domestic models excel on Chinese content. Our work provides a structured framework for evaluating and enhancing factual reliability in long-form LLM outputs, guiding their safe deployment in sensitive domains.

Recent studies operationalize self-improvement through coding agents that edit their own codebases. They grow a tree of self-modifications through expansion strategies that favor higher software engineering benchmark performance, assuming that this implies more promising subsequent self-modifications. However, we identify a mismatch between the agent's self-improvement potential (metaproductivity) and its coding benchmark performance, namely the Metaproductivity-Performance Mismatch. Inspired by Huxley's concept of clade, we propose a metric ($\mathrm{CMP}$) that aggregates the benchmark performances of the descendants of an agent as an indicator of its potential for self-improvement. We show that, in our self-improving coding agent development setting, access to the true $\mathrm{CMP}$ is sufficient to simulate how the Gödel Machine would behave under certain assumptions. We introduce the Huxley-Gödel Machine (HGM), which, by estimating $\mathrm{CMP}$ and using it as guidance, searches the tree of self-modifications. On SWE-bench Verified and Polyglot, HGM outperforms prior self-improving coding agent development methods while using fewer allocated CPU hours. Last but not least, HGM demonstrates strong transfer to other coding datasets and large language models. The agent optimized by HGM on SWE-bench Verified with GPT-5-mini and evaluated on SWE-bench Lite with GPT-5 achieves human-level performance, matching the best officially checked results of human-engineered coding agents. Our code is publicly available at https://github.com/metauto-ai/HGM.

Large Language Models (LLMs) have evolved into AI agents that interact with external tools and environments to perform complex tasks. The Model Context Protocol (MCP) has become the de facto standard for connecting agents with such resources, but security has lagged behind: thousands of MCP servers execute with unrestricted access to host systems, creating a broad attack surface. In this paper, we introduce AgentBound, the first access control framework for MCP servers. AgentBound combines a declarative policy mechanism, inspired by the Android permission model, with a policy enforcement engine that contains malicious behavior without requiring MCP server modifications. We build a dataset containing the 296 most popular MCP servers, and show that access control policies can be generated automatically from source code with 80.9% accuracy. We also show that AgentBound blocks the majority of security threats in several malicious MCP servers, and that policy enforcement engine introduces negligible overhead. Our contributions provide developers and project managers with a practical foundation for securing MCP servers while maintaining productivity, enabling researchers and tool builders to explore new directions for declarative access control and MCP security.

Although large language models (LLMs) have revolutionized natural language processing capabilities, their practical implementation as autonomous multi-agent systems (MAS) for industrial problem-solving encounters persistent barriers. Conventional MAS architectures are fundamentally restricted by inflexible, hand-crafted graph topologies that lack contextual responsiveness, resulting in diminished efficacy across varied academic and commercial workloads. To surmount these constraints, we introduce AMAS, a paradigm-shifting framework that redefines LLM-based MAS through a novel dynamic graph designer. This component autonomously identifies task-specific optimal graph configurations via lightweight LLM adaptation, eliminating the reliance on monolithic, universally applied structural templates. Instead, AMAS exploits the intrinsic properties of individual inputs to intelligently direct query trajectories through task-optimized agent pathways. Rigorous validation across question answering, mathematical deduction, and code generation benchmarks confirms that AMAS systematically exceeds state-of-the-art single-agent and multi-agent approaches across diverse LLM architectures. Our investigation establishes that context-sensitive structural adaptability constitutes a foundational requirement for high-performance LLM MAS deployments.