Multi-Agent Simulations

The integration of Large Language Models (LLMs) with microscopic traffic simulation offers a promising path toward autonomous urban planning and intelligent transportation analysis. However, existing monolithic agent architectures often struggle with the complexity of end-to-end simulation workflows, leading to reasoning failures, parameter inconsistency, and a lack of systematic state management. This paper proposes a novel multi-agent collaborative framework designed to automate the entire lifecycle of traffic simulation in SUMO (Simulation of Urban Mobility). Our approach decouples the simulation pipeline into specialized roles, including Planner, Builder, Demand, Runner, and Analyst, coordinated by a high-level reasoning engine. We introduce a state-persistent Orchestrator leveraging the Model Context Protocol (MCP) to ensure seamless data handover and environmental consistency across distributed agent actions. This architecture enables a robust closed-loop refinement process, where simulation outcomes are iteratively analyzed and optimized to satisfy user-defined Key Performance Indicators (KPIs). Experimental results through role ablation studies demonstrate that the proposed multi-agent framework significantly enhances task success rates and parameter accuracy compared to single-agent baselines. Furthermore, case studies on real-world network extraction and traffic optimization highlight the system's capability to bridge the gap between high-level natural language intent and low-level simulation execution.

Large language models (LLMs) exhibit systematic political biases in voter simulations, but their underlying mechanisms and cross-lingual generalizations remain poorly understood. We introduce Dynamo-K, a census-grounded simulation framework evaluating Korean-language LLM political behavior across four models on six Korean elections (2017-2025). Using this framework, we identify three systematic failure modes: (1) progressive bias in moderate agents, where explicit mitigation reduces Mean Absolute Error (MAE) by 5.2 times; (2) model-dependent third-party salience collapse, distinguishing between salience failure and decision bias; and (3) regional polarization collapse, where models bidirectionally under-predict historical party strongholds. To address these failures, we demonstrate that scenario reframing recovers 62% of 2017 MAE by restoring third-party visibility. Furthermore, we introduce a learned reweighting adapter that successfully calibrates opposing-valence models without relying on candidate names at train or test time. Validating our diagnostic framework, Dynamo-K accurately predicts 3/3 presidential winners - including a 2.1%p MAE on the highly contested 0.73%p-margin 2022 race - and correctly identifies the dominant party in a held-out local election. The pipeline is open-source and provides a scalable, cost-effective method for diagnosing LLM political behavior.

We propose a framework for predicting the effects of mobility introduction measures using a human-flow digital twin. This digital twin incorporates a multi-agent simulator that can represent how visitors choose destinations depending on factors such as their current location and the attractiveness of spots. We extract data on how visitors selected destinations with respect to measured pre-intervention human-flow data, inter-spot distances, spot attractiveness, and travel volumes, and use these data to train each agent's decision model of this simulator. The trained decision model is a function that takes a visitor's current state and surrounding environmental information as input and outputs which spot the visitor will move toward next. By expressing mobility introduction measures as changes to inter-point distances or to spot attractiveness, the framework can reproduce human flows with mobility introduction in the multi-agent simulator and thereby quantify effects such as changes in visitor counts and circulation. We evaluated the proposed method using human-flow data measured with and without introducing mobility within Wakayama Castle Park in Japan. When reproducing flows with mobility introduction using a multi-layer perceptron decision model, the cosine similarity of the spatial population distribution exceeded 0.7, confirming that the approach can replicate the flow changes caused by the mobility introduction.

Social simulation provides a compelling testbed for studying social intelligence, where agents interact through multi-turn dialogues under evolving contexts and strategically adapting opponents. Such environments are inherently non-stationary, requiring agents to dynamically adjust their strategies over time. However, most Large Language Model (LLM) based social agents rely on static personas, while existing approaches for enhancing social intelligence, such as offline reinforcement learning or external planners, are ill-suited to these settings, typically assuming stationarity and incurring substantial training overhead. To bridge this gap, we propose \textbf{ALSO} (\textbf{A}dversarial on\textbf{L}ine \textbf{S}trategy \textbf{O}ptimization), the first framework for online strategy optimization in multi-agent social simulation. ALSO advances social adaptation through two key contributions. (1) ALSO formulates multi-turn interaction as an adversarial bandit problem, where combinations of static personas and dynamic strategy instructions are treated as arms, providing a principled solution to non-stationarity without relying on environmental stability assumptions. (2) To predict rewards and generalize sparse feedback in multi-turn dialogues, ALSO introduces a lightweight neural surrogate to predict rewards from interaction histories, enabling sample-efficient exploration and continuous online adaptation. Experiments on the Sotopia benchmark demonstrate that ALSO consistently outperforms static baselines and existing optimization methods in dynamic environments, validating the effectiveness of adversarial online strategy optimization for building robust social agents.

AI agents are being increasingly deployed in dynamic, open-ended environments that require adapting to new information as it arrives. To efficiently measure this capability for realistic use-cases, we propose building grounded simulations that replay real-world events in the order they occurred. We build FutureSim, where agents forecast world events beyond their knowledge cutoff while interacting with a chronological replay of the world: real news articles arriving and questions resolving over the simulated period. We evaluate frontier agents in their native harness, testing their ability to predict world events over a three-month period from January to March 2026. FutureSim reveals a clear separation in their capabilities, with the best agent's accuracy being 25%, and many having worse Brier skill score than making no prediction at all. Through careful ablations, we show how FutureSim offers a realistic setting to study emerging research directions like long-horizon test-time adaptation, search, memory, and reasoning about uncertainty. Overall, we hope our benchmark design paves the way to measure AI progress on open-ended adaptation spanning long time-horizons in the real world.

Symmetrical Reality (SR) is emerging as a future trend for human-agent coexistence, placing higher demands on agents to acquire human-like intelligence. It calls for richer and more diverse human guidance. We introduce a three-stage demonstration paradigm integrating multimodal demonstration signals. Building on this paradigm, we developed TeachAnything, a cloud-based, crowdsourcing-oriented demonstration platform with physics simulation capable of collecting diverse demonstration data across varied scenes, tasks, and embodiments. By unifying virtual and physical interactions through both methodological design and physics simulation, the system serves as a practical foundation for developing embodied agents aligned with Symmetrical Reality.

The integration of large language models (LLMs) in economic simulations has significantly enhanced agent-based modeling, yet existing frameworks struggle to capture the interplay between short-term optimization and long-term strategic planning. Conventional approaches rely on static data-driven predictions, failing to incorporate adaptive behaviors influenced by economic sentiment, market volatility, and individual goals. To address these limitations, we introduce a novel EconAI framework, incorporating economic sentiment indexing (ESI), memory weighting, and dynamic decision-making mechanisms. By quantifying economic belief, adjusting historical data influence, and linking work-consumption behaviors, EconAI achieves a more human-like decision process, where agents adapt their actions based on both market signals and long-term objectives. It is the first LLM-powered simulation system that can simulate the macro/microeconomic environment and interactions in a unified framework. Empirical evaluations show that EconAI improves stability in economic responses, better replicates real-world employment-consumption cycles, and enhances overall decision robustness. This advancement marks a crucial step towards more realistic, adaptive economic agent simulations.

Large language model (LLM)-based multi-agent simulation offers a powerful testbed for studying social opinion dynamics. Yet current approaches often adopt two contrasting methods: either relying on fixed update rules with limited cognitive grounding or delegating belief change largely to unconstrained LLM interaction. We introduce ScioMind, a cognitively grounded simulation framework that bridges these paradigms by combining structured opinion dynamics with LLM-based agent reasoning. ScioMind integrates three key components: 1) a memory-anchored belief update rule that modulates susceptibility to influence via personality-conditioned anchoring strength; 2) a hierarchical memory architecture that supports persistent, experience-driven belief formation; and 3) dynamic agent profiles derived from a corpus-grounded retrieval pipeline, enabling heterogeneous personalities, rationales, and evolving internal states. We evaluate ScioMind on multiple case studies in a real-world policy debate scenario. Across metrics including polarisation, diversity, extremization, and trajectory stability, the proposed components consistently yield improvements in behavioural realism. In particular, dynamic profiles increase opinion diversity, memory and reflection reduce unstable oscillation, and anchoring induces persistent belief trajectories that better align with patterns reported in political psychology. These results suggest that our cognitively grounded design provides a novel solution to LLM-based social simulation that improves both stable and behavioural realism

Simulative and scenario-based testing are crucial methods in the safety assurance for automated driving systems. To ensure that simulation results are reliable, the real world must be modeled with sufficient fidelity, including not only the static environment but also the surrounding traffic of a vehicle under test. Thus, the availability of traffic agent models is of common interest to model naturalistic and parameterizable behavior, similar to human drivers. The interchangeability of agent models across different simulation environments represents a major challenge and necessitates harmonization and standardization. To address this challenge, we present a standardized and modular simulation integration architecture that enables the tool-independent integration of traffic agent models. The architecture builds upon the Open Simulation Interface (OSI) as a structured message format and the Functional Mock-up Interface (FMI) for dynamic model exchange. Rather than introducing yet another model or simulation tool, we provide a reusable reference implementation that translates these standards into a practical integration blueprint, including clear interfaces, data mappings, and execution semantics. The generic nature of the architecture is demonstrated by integrating an exemplary agent model into three widely used simulation environments: OpenPASS, CARLA, and CarMaker. As part of the evaluation, we show that the model yields consistent behavior in all simulation platforms, thereby validating the interoperability, modularity, and standard compliance of the proposed architecture. The reference implementation lowers integration barriers, serves as a foundation for future research, and is made publicly available at github.com/ika-rwth-aachen/agent-model-integration

Unconstructive debate and uncivil communication carry well-documented costs for productivity and cohesion, yet isolating their effect on operational efficiency has proven difficult. Human subject research in this domain is constrained by ethical oversight, limited reproducibility, and the inherent unpredictability of naturalistic settings. We address this gap by leveraging Large Language Model (LLM) based Multi-Agent Systems as a controlled sociological sandbox, enabling systematic manipulation of communicative behavior at scale. Using a Monte Carlo simulation framework, we generate thousands of structured 1-on-1 adversarial debates across varying toxicity conditions, measuring convergence time, defined as the number of rounds required to reach a conclusion, as a proxy for interactional efficiency. Building on a prior study, we replicate and extend its findings across two additional LLM agents of varying parameter size, allowing us to assess whether the effects of toxic behavior on debate dynamics generalize across model scale. The convergence latency of 25% reported in the previous study was confirmed. It was found that this latency is significantly bigger for models with fewer parameters. We further identify a significant first-mover advantage, whereby the agent initiating the discussion wins significantly above chance regardless of toxicity condition.

Agent-based modeling (ABM) has long been used in economics to study human behavior, and large language model (LLM) agents now enable new forms of social and economic simulation. While prior work has discovered strategic deception by LLM agents in financial trading and auction markets, e-commerce remains underexplored despite its distinctive information asymmetry: sellers privately observe product quality, whereas buyers rely on advertised claims and reputation signals. We introduce TruthMarketTwin, a controlled simulation framework for studying LLM-agent behavior in e-commerce markets. The framework is one of the first to model bilateral trade under asymmetric information sharing, where agents make strategic listing, purchasing, rating, and recourse-related decisions to optimize seller profit and buyer utility. We find that LLM agents released into traditional markets autonomously exploit weaknesses in reputation-based governance, while warrant enforcement reduces deception and reshapes strategic reasoning. Our results position LLM-agent simulation as a tool for studying institution-governed autonomous markets.

LLMs are increasingly capable of persuasion, which raises the question of how to protect users against manipulation. In a preregistered user study (N=120) across four decision-making scenarios, we find that an adversarial LLM with a hidden goal succeeds in steering users' decisions 65.4% of the time. We then introduce a "warden" model: a secondary LLM that monitors the human-AI interaction trace in real time and issues non-binding, private advisories to the user when it detects manipulation. Adding a warden more than halves the adversary's success rate to 30.4%, with a much smaller (8.6 percentage points) reduction for genuine interactions. To probe the mechanism behind these results, we release COAX-Bench, a simulation benchmark spanning 14 decision-making scenarios, including hiring, voting, and file access. Across 16,212 simulated multi-agent interactions, capable adversarial LLMs achieve their hidden goals in 34.7% of cases, which warden models reduce to 12.3%. Notably, even warden models substantially weaker than the adversary they oversee provide meaningful protection, suggesting a path for scalable oversight of more capable models.

Large-scale social simulators are essential for studying complex social patterns. Prior work explores hybrid methods to scale up simulations, combining large language models (LLM)-based agents with numerical agent-based models (ABM). However, this incurs high latency due to expensive memory retrieval and sequential ABM execution. To address this challenge, we propose GASim, a graph-accelerated hybrid multi-agent framework for large-scale social simulations. For core agents driven by LLM, GASim introduces Graph-Optimized Memory (GOM) to replace intensive LLM-based retrieval pipelines with lightweight propagation over a sparse memory graph. For the majority of ordinary agents, GASim employs Graph Message Passing (GMP), substituting sequential ABM execution with parallel updates by fine-grained feature aggregation and Graph Attention Network. We further introduce Entropy-Driven Grouping (EDG) that coordinates this hybrid partitioning, leveraging information entropy to dynamically identify emergent core agents situated in information-diverse neighborhoods. Extensive experiments show that GASim not only delivers a substantial 9.94-fold end-to-end speedup over the traditional hybrid framework but also consumes less than 20% of baseline tokens, significantly reducing costs while preserving strong alignment with real-world public opinion trends. Our code is available at https://github.com/Jasmine0201/GASim.

Static capabilities benchmarks suffer from saturation and contamination, making it difficult to track capabilities progress over time. We introduce Agent Island, a multiplayer simulation environment in which language-model agents compete in a game of interagent cooperation, conflict, and persuasion. The environment yields a dynamic benchmark designed to mitigate both saturation and contamination; new models can always outperform the current leading player in this winner-take-all game, and agents compete against other adaptive agents rather than face a fixed task set. We rank players with a Bayesian Plackett-Luce model, allowing us to quantify uncertainty in player skill. In 999 games involving 49 unique models, openai/gpt-5.5 dominates its peers with a posterior mean skill of 5.64, compared with 3.10 for the second-ranked model, openai/gpt-5.2, and 2.86 for the third-ranked model, openai/gpt-5.3-codex. We release the game logs as a dataset for analyses of model behavior. As an example, we investigate same-provider preference in final-round votes and find that models are 8.3 p.p. more likely to support a same-provider finalist than finalists from other providers. This preference is not uniform across providers: among separately estimated providers, the effect is strongest for OpenAI models and weakest for Anthropic models.

Conversational recommender systems (CRS) increasingly rely on user simulators for automated evaluation of sales agents. A key requirement for such simulators is the ability to model human decision-making. However, most existing simulation frameworks do not explicitly model the internal decision process, and LLM-based simulators often exhibit unrealistically strong information-processing capabilities, rarely exhibit the hesitation or decision deferral commonly observed in real consumer behavior, resulting in overly high acceptance probabilities. To address this limitation, we propose Hesitator, a theory-grounded user simulation framework that explicitly models human decision-making under choice overload. The framework introduces a modular Decision Module that separates utility-based item selection from overload-aware commitment decisions. Experiments across multiple user simulation frameworks, domains, sales modes, and LLM backbones show that integrating our module consistently mitigates unrealistic behaviors under increasing overload conditions. Furthermore, Hesitator reproduces established behavioral patterns from psychological economics, demonstrating its ability to model human decision behavior.

Multi-agent deliberation systems using large language models (LLMs) are increasingly proposed for policy simulation, yet they suffer from artificial consensus: evaluator agents converge on the same option regardless of their assigned value perspectives. We present the AI Council, a three-phase deliberation framework, and conduct 120 deliberations across two policy scenarios to test two interventions. First, architectural heterogeneity (assigning a different 7-9B parameter model to each value perspective) significantly reduces first-choice concentration compared to a homogeneous baseline (child welfare: 70.9% to 46.1%, p < 0.001, r = 0.58; housing: 46.0% to 22.9%, p < 0.001, r = 0.50). This contrasts with accuracy-oriented multi-agent debate, where heterogeneity does not reduce convergence, suggesting model diversity operates differently when no objectively correct answer exists. Second, coherence validation (using a frontier model to assess whether each evaluator's reasoning is grounded in its assigned values) reveals a fidelity-diversity tradeoff: on a scenario with a dominant option, it further reduces concentration (46.1% to 40.8%, p = 0.004), but on a scenario with genuinely competitive options, it increases concentration (22.9% to 26.6%, p = 0.96) by amplifying high-coherence evaluators who cluster on one option. This tradeoff may be a general property of multi-agent systems employing quality weighting. We report negative results from three failed Delphi designs, demonstrate that 8B models exhibit binary rather than graded responses to counter-arguments, and propose the trustworthy tension rate as a diagnostic measure of small-model deliberation capabilities.

As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment dynamics becomes a central bottleneck. Agents that manipulate objects, navigate software, coordinate with others, or design experiments require predictive environment models, yet the term world model carries different meanings across research communities. We introduce a "levels x laws" taxonomy organized along two axes. The first defines three capability levels: L1 Predictor, which learns one-step local transition operators; L2 Simulator, which composes them into multi-step, action-conditioned rollouts that respect domain laws; and L3 Evolver, which autonomously revises its own model when predictions fail against new evidence. The second identifies four governing-law regimes: physical, digital, social, and scientific. These regimes determine what constraints a world model must satisfy and where it is most likely to fail. Using this framework, we synthesize over 400 works and summarize more than 100 representative systems spanning model-based reinforcement learning, video generation, web and GUI agents, multi-agent social simulation, and AI-driven scientific discovery. We analyze methods, failure modes, and evaluation practices across level-regime pairs, propose decision-centric evaluation principles and a minimal reproducible evaluation package, and outline architectural guidance, open problems, and governance challenges. The resulting roadmap connects previously isolated communities and charts a path from passive next-step prediction toward world models that can simulate, and ultimately reshape, the environments in which agents operate. Code and resources are available at: https://github.com/matrix-agent/awesome-agentic-world-modeling.

Generative world models increasingly rely on 4D occupancy for realistic autonomous driving simulation. However, existing generation frameworks depend on rigid geometric conditions (e.g., explicit trajectories) or simplistic attribute-level text, failing to orchestrate complex, sequential multi-agent interactions. To address this semantic-spatiotemporal gap, we propose OccDirector, a pioneering framework that generates 4D occupancy dynamics conditioned solely on natural language. Operating as a ``scenario director'', OccDirector maps natural language scripts into physically plausible voxel dynamics without requiring geometric priors. Technically, it employs a VLM-driven Spatio-Temporal MMDiT equipped with a history-prefix anchoring strategy to ensure long-horizon interaction consistency. Furthermore, we introduce OccInteract-85k, a novel dataset uniquely annotated with multi-level language instructions: ranging from static layouts to intricate multi-agent behaviors, alongside a novel VLM-based evaluation benchmark. Extensive experiments demonstrate that OccDirector achieves state-of-the-art generation quality and unprecedented instruction-following capabilities, successfully shifting the paradigm from appearance synthesis to language-driven behavior orchestration.

We study emergent social dynamics in LLM agents playing The Resistance: Avalon, a hidden-role deception game. Unlike prior work on single-game performance, our agents play repeated games while retaining memory of previous interactions, including who played which roles and how they behaved, enabling us to study how social dynamics evolve. Across 188 games, two key phenomena emerge. First, reputation dynamics emerge organically when agents retain cross-game memory: agents reference past behavior in statements like "I am wary of repeating last game's mistake of over-trusting early success." These reputations are role-conditional: the same agent is described as "straightforward" when playing good but "subtle" when playing evil, and high-reputation players receive 46% more team inclusions. Second, higher reasoning effort supports more strategic deception: evil players more often pass early missions to build trust before sabotaging later ones, 75% in high-effort games vs 36% in low-effort games. Together, these findings show that repeated interaction with memory gives rise to measurable reputation and deception dynamics among LLM agents.

Team-level failure in nuclear control rooms arises not from isolated operator error, but from emergent interaction dynamics, delayed diagnosis, suppressed dissent, and authority-driven error propagation, that conventional human reliability analysis methods are structurally unable to model. This study introduces TEAM-SimHRA, a multi-agent large language model simulation framework that reconceptualizes human reliability as an interaction-driven emergent property of control room teams rather than a static individual attribute. Unlike existing approaches that assign fixed error probabilities to predefined tasks, TEAM-SimHRA reproduces collective cognition, role-conditioned authority dynamics, and real-time communication suppression across temporally evolving accident progressions. Validated against the Three Mile Island (1979) and Chernobyl (1986) accidents, the two most extensively documented nuclear team failures , the framework achieves face-validity pass rates of 43.5% and 52.6% respectively, reproducing near-historical decision delay (134.8 vs. 138 min), perfect communication suppression stability, and full authority pressure cascade at historically accurate propagation depth. These results demonstrate that multi-agent simulation can extract quantitative team-level reliability indicators that are inaccessible to traditional methods, opening a viable path toward simulation-based dynamic probabilistic risk assessment for safety-critical sociotechnical systems.

Modeling coordination among generative agents in complex multi-round decision-making presents a core challenge for AI and operations management. Although behavioral experiments have revealed cognitive biases behind supply chain inefficiencies, traditional methods face scalability and control limitations. We introduce a scalable experimental paradigm using Large Language Models (LLMs) to simulate multi-stage supply chain dynamics. Grounded in a Hierarchical Reasoning Framework, this study specifically analyzes the impact of cognitive heterogeneity on agent interactions. Unlike prior homogeneous settings, we employ DeepSeek and GPT agents to systematically vary reasoning sophistication across supply chain tiers. Through rigorously replicated and statistically validated simulations, we investigate how this cognitive diversity influences collective outcomes. Results indicate that agents exhibit myopic and self-interested behaviors that exacerbate systemic inefficiencies. However, we demonstrate that information sharing effectively mitigates these adverse effects. Our findings extend traditional behavioral methods and offer new insights into the dynamics of AI-enabled organizations. This work underscores both the potential and limitations of LLM-based agents as proxies for human decision-making in complex operational environments.

The increasing integration of artificial intelligence (AI) in everyday life brings with it new challenges and questions for regarding how humans interact with autonomous agents. Multi-agent experiments, where humans and AI act together, can offer important opportunities to study social decision making, but there is a lack of accessible tooling available to researchers to run such experiments. We introduce two tools designed to reduce these barriers. The first, CoGrid, is a multi-agent grid-based simulation library with dual NumPy and JAX backends. The second, Multi-User Gymnasium (MUG), translates such simulation environments directly into interactive web-based experiments. MUG supports interactions with arbitrary numbers of humans and AI, utilizing either server-authoritative or peer-to-peer networking with rollback netcode to account for latency. Together, these tools can enable researchers to deploy studies of human-AI interaction, facilitating inquiry into core questions of psychology, cognition, and decision making and their relationship to human-AI interaction. Both tools are open source and available to the broader research community. Documentation and source code is available at {cogrid, multi-user-gymnasium}.readthedocs.io. This paper details the functionality of these tools and presents several case studies to illustrate their utility in human-AI multi-agent experimentation.

LLM-empowered agent simulations are increasingly used to study social emergence, yet the micro-to-macro causal mechanisms behind macro outcomes often remain unclear. This is challenging because emergence arises from intertwined agent interactions and meso-level feedback and nonlinearity, making generative mechanisms hard to disentangle. To this end, we introduce \textbf{\textsc{CAMO}}, an automated \textbf{Ca}usal discovery framework from \textbf{M}icr\textbf{o} behaviors to \textbf{M}acr\textbf{o} Emergence in LLM agent simulations. \textsc{CAMO} converts mechanistic hypotheses into computable factors grounded in simulation records and learns a compact causal representation centered on an emergent target $Y$. \textsc{CAMO} outputs a computable Markov boundary and a minimal upstream explanatory subgraph, yielding interpretable causal chains and actionable intervention levers. It also uses simulator-internal counterfactual probing to orient ambiguous edges and revise hypotheses when evidence contradicts the current view. Experiments across four emergent settings demonstrate the promise of \textsc{CAMO}.

Language models are increasingly used to simulate people: survey respondents, negotiators, stakeholders in policy exercises. In that role a model should reproduce how people plausibly behave, hesitating, conceding late, and settling for imperfect deals, rather than playing the best move. We call this the sampler role, in contrast to the solver role of finding the best move, and we test how the reasoning modes providers ship to strengthen models as solvers affect it. Our testbed is multi-party negotiation: five agents bargain over a regulation for fifteen turns, and unresolved issues are decided by an authority. Agents without a structured memory of the negotiation almost never reach agreement, whether reasoning is on or off: 314 of 315 such runs end with the authority deciding. What reasoning changes is how the failure looks. With reasoning enabled, one model family negotiates visibly, with varied moves, concessions in most runs, and a different path every time, yet still ends without agreement in fifteen runs of fifteen. Diversity checks would pass a model whose endings never change. Two further results show the task permits agreement: when agents write their own short running notes on the negotiation, agreement becomes the norm, while the same notes supplied ready-made change nothing; and hand-coded agents following textbook concession strategies agree in most runs under identical rules. Simulation pipelines should therefore vet models as samplers, on the distributions of outcomes they produce. Fidelity as a sampler must be tested on its own: solver strength is no guide to it, and switching on reasoning leaves it where it was.

Training reinforcement-learning agents for cyber defense requires an environment that reflects the operational setting: noisy, partial observations, several defenders coordinating across a network, and an adaptive adversary realized through self-play. We present NetForge RL, a multi-agent environment for this setting on procedurally generated enterprise and operational-technology (OT) networks. A red agent compromises hosts with partial observability; three zone-split blue agents defend from synthetic SIEM telemetry, Windows/Sysmon event logs encoded into dense embeddings rather than a ground-truth state vector. The environment follows the PettingZoo parallel API with fixed-shape observations and MITRE ATT&CK-mapped actions, ships five scenarios with named difficulty presets and a held-out evaluation split, and replays deterministically under a seed. A JAX backend vectorizes a reduced transition core, reaching 2.5 x 10^5 environment-steps/s at batch 4096 on CPU, as a fast surrogate for training-loop iteration. Alongside the environment we provide reference baselines (scripted, a JAX IPPO trainer, and a self-play tournament), six diagnostic probes that each measure one defensive skill, and an evaluation runner reporting 95% confidence intervals. We describe the reproducibility engineering behind the environment and include a responsible-use statement.

Social actors do not observe a common social world: each individual forms judgments from a partial and potentially distorted view of the surrounding network. We study whether graph-local evidence and credibility-weighted communication can generate persistent distortions in perceived academic standing, even when agents repeatedly receive objective performance signals. We introduce a data-constrained multi-agent framework in which LLM agents operate through individualized subjective graphs that determine peer visibility, evidence access, and interaction opportunities. Agents exchange uncertainty-annotated assessments, evaluate message credibility, and maintain explicit Gaussian belief states updated through Bayesian fusion. We evaluate the framework on 12 middle-school classrooms comprising 482 students, using questionnaire-derived social information and six consecutive examinations. On the Social-Observed subset (n=419), collective ranking error increases from 0.066 \pm 0.008 to 0.124 \pm 0.009 across six epochs despite repeated exam-based anchoring. Ablations associate individualized visibility and LLM-based trust gating with more stable long-horizon behavior, while constrained retrieval primarily safeguards against global-information leakage. Compared with evaluated DeGroot configurations, the proposed framework achieves lower final ranking error; those DeGroot configurations exhibit near-zero terminal opinion diversity. These findings establish subjective-graph LLM agents as a mechanism-oriented framework for data-constrained simulated social perception. Code is available at https://anonymous.4open.science/r/Rashomonomon-0126.

Most existing robot simulators prioritize rigid-body dynamics and photorealistic rendering, but largely neglect the thermally and optically complex phenomena that characterize real-world fire environments. For robots envisioned as future firefighters, this limitation hinders both reliable capability evaluation and the generation of representative training data prior to deployment in hazardous scenarios. To address these challenges, we introduce Fire as a Service (FaaS), a novel, asynchronous co-simulation framework that augments existing robot simulators with high-fidelity and computationally efficient fire simulations. Our pipeline enables robots to experience accurate, multi-species thermodynamic heat transfer and visually consistent volumetric smoke without disrupting high-frequency rigid-body control loops. We demonstrate that our framework can be integrated with diverse robot simulators to generate physically accurate fire behavior, benchmark thermal hazards encountered by robotic platforms, and collect realistic multimodal perceptual data. Crucially, its real-time performance supports human-in-the-loop teleoperation, enabling the successful training of reactive, multimodal policies via Behavioral Cloning. By adding fire dynamics to robot simulations, FaaS provides a scalable pathway toward safer, more reliable deployment of robots in fire scenarios.

This paper presents a hybrid insider threat detection framework for enterprise environments, integrating multi-agent simulation, layered SIEM correlation, trust-adaptive thresholds, behavioral and communication forensics, and Theory-of-Mind reasoning. Email is treated not as a control channel but as a coordination and social-engineering evidence stream correlated with authentication, file-access, and privilege events. Four variants are evaluated: Layered SIEM-Core (LSC), Cognitive-Enriched SIEM (CE-SIEM), Evidence-Gated SIEM (EG-SIEM), and EG-SIEM-Enron with Enron-calibrated email forensics. Across ten matched runs with eight malicious insiders, actor-level F1 improves from 0.567 for LSC to 0.774 for CE-SIEM, 0.898 for EG-SIEM, and 0.944 for EG-SIEM-Enron; paired Wilcoxon tests confirm the first three differences after Holm-Bonferroni correction. Evidence gating reduces confirmed false positives from 33.7 per run under LSC and 49.3 under CE-SIEM to 0.2 and 0.0 respectively, a precision gain traded against longer confirmation time. Domain-shift evaluation shows that an Enron-trained email classifier does not transfer to a different operational email domain, although target-domain fine-tuning reaches F1 = 0.974 under grouped template-family evaluation. On CERT r4.2, the evidence-gated logic improves actor-level detection while reducing false positives, outperforming tabular anomaly detectors and a sentence-embedding baseline. Scalability tests to 1000 agents indicate stable detection quality.

Autonomous agents navigating human society must master both production activities and social interactions, yet existing benchmarks rarely evaluate these skills simultaneously. To bridge this gap, we introduce StarDojo, a novel benchmark based on Stardew Valley, designed to assess AI agents in open-ended production-living simulations. In StarDojo, agents are tasked to perform essential livelihood activities such as farming and crafting, while simultaneously engaging in social interactions to establish relationships within a vibrant community. StarDojo features 1,000 meticulously curated tasks across five key domains: farming, crafting, exploration, combat, and social interactions. Additionally, we provide a compact subset of 100 representative tasks for efficient model evaluation. The benchmark offers a unified, user-friendly interface that eliminates the need for keyboard and mouse control, supports all major operating systems, and enables the parallel execution of multiple environment instances, making it particularly well-suited for evaluating the most capable foundation agents, powered by multimodal large language models (MLLMs). Extensive evaluations of state-of-the-art MLLMs agents demonstrate substantial limitations, with the best-performing model, GPT-4.1, achieving only a 12.7% success rate, primarily due to challenges in visual understanding, multimodal reasoning and low-level manipulation. As a user-friendly environment and benchmark, StarDojo aims to facilitate further research towards robust, open-ended agents in complex production-living environments.

Multi-agent large language model simulations have the potential to model complex human behaviors and interactions. If the mechanics are set up properly, unanticipated and valuable social dynamics can surface. However, it is challenging to consistently enforce simulation mechanics while still allowing for rich and emergent dynamics. We present AgentDynEx, an AI system that helps set up, track, and repair simulations. Specifically, AgentDynEx introduces milestones that act as checkpoints and failure conditions that act as guardrails to ensure dynamics are relevant and mechanics are respected as the simulation progresses. It also introduces a method called nudging, where the system dynamically reflects on simulation progress and gently intervenes if it begins to deviate from intended outcomes. A technical evaluation found that nudging enables simulations to progress further without reducing the presence notable dynamics compared to simulations without nudging. A case study with AgentDynEx documented instances where real users were able to simulate lived experiences. We discuss the importance of nudging as a technique for guiding agents towards desirable behaviors while preserving their freedom of choice.

Scenario-based testing with driving simulators is extensively used to identify failing conditions of automated driving assistance systems (ADAS). However, existing studies have shown that repeated test execution in the same as well as in distinct simulators can yield different outcomes, which can be attributed to sources of flakiness or different implementations of the physics. In this paper, we present MultiSim, a novel approach to multi-simulation ADAS testing based on a search-based testing approach that leverages an ensemble of simulators to identify failure-inducing, simulator-agnostic test scenarios. During the search, each scenario is evaluated jointly on multiple simulators. Scenarios that produce consistent results across simulators are prioritized for further exploration, while those that fail on only a subset of simulators are given less priority, as they may reflect simulator-specific issues rather than generalizable failures. Our empirical study, which involves testing three lane-keeping ADAS on different pairs of three widely used simulators, demonstrates that MultiSim outperforms single-simulator testing by achieving, on average, a higher rate of simulator-agnostic failures by 66%. Compared to a state-of-the-art multi-simulator approach that combines the outcome of independent test generation campaigns obtained in different simulators, MultiSim identifies, on average, up to 3.4X more simulator-agnostic failing tests and higher failure rates. To avoid the costly execution of test inputs on which simulators disagree, we propose to predict simulator disagreements and bypass test executions. Our results show that utilizing a surrogate model during the search retains the average number of valid failures and also improves efficiency. Our findings indicate that combining an ensemble of simulators is a promising approach for the automated cross-replication in ADAS testing.

While modern Autonomous Vehicle (AV) systems can develop reliable driving policies under regular traffic conditions, they frequently struggle with safety-critical traffic scenarios. This difficulty primarily arises from the rarity of such scenarios in driving datasets and the complexities associated with predictive modeling of multiple vehicles. Effectively simulating safety-critical traffic situations is therefore a crucial challenge. In this paper, we introduce TrafficGamer, which facilitates game-theoretic traffic simulation by viewing common road driving as a multi-agent game. When we evaluate the empirical performance across various real-world datasets, TrafficGamer ensures both the fidelity, exploitability, and diversity of the simulated scenarios, guaranteeing that they not only statically align with real-world traffic distribution but also efficiently capture equilibria for representing safety-critical scenarios involving multiple agents compared with other methods. Additionally, the results demonstrate that TrafficGamer provides highly flexible simulations across various contexts. Specifically, we demonstrate that the generated scenarios can dynamically adapt to equilibria of varying tightness by configuring risk-sensitive constraints during optimization. We have provided a demo webpage at: https://anonymous.4open.science/api/repo/trafficgamer-demo-1EE0/file/index.html.

Can AI Agents simulate real-world trading environments to investigate the impact of external factors on stock trading activities (e.g., macroeconomics, policy changes, company fundamentals, and global events)? These factors, which frequently influence trading behaviors, are critical elements in the quest for maximizing investors' profits. Our work attempts to solve this problem through large language model based agents. We have developed a multi-agent AI system called StockAgent, driven by LLMs, designed to simulate investors' trading behaviors in response to the real stock market. The StockAgent allows users to evaluate the impact of different external factors on investor trading and to analyze trading behavior and profitability effects. Additionally, StockAgent avoids the test set leakage issue present in existing trading simulation systems based on AI Agents. Specifically, it prevents the model from leveraging prior knowledge it may have acquired related to the test data. We evaluate different LLMs under the framework of StockAgent in a stock trading environment that closely resembles real-world conditions. The experimental results demonstrate the impact of key external factors on stock market trading, including trading behavior and stock price fluctuation rules. This research explores the study of agents' free trading gaps in the context of no prior knowledge related to market data. The patterns identified through StockAgent simulations provide valuable insights for LLM-based investment advice and stock recommendation. The code is available at https://github.com/MingyuJ666/Stockagent.

Multi-agent traffic simulation seeks diverse, coordinated, and physically realistic futures from maps and observed history. Long-horizon closed-loop generation must reconcile multiple decision time scales while its context evolves with generated states. Existing methods often unfold long futures from an initial scene and resolve intent, interaction, and motion monolithically, weakening cross-scale consistency and adaptation. Multimodal rollout poses a further consistency problem: independently reselecting modes across agents or commits can stitch together incompatible futures instead of preserving a coherent joint branch. We present Hi-FLoop, a branch-consistent multi-timescale state-feedback framework. Eight scene-level Worlds represent joint hypotheses; all agents share one selected World identity throughout all 16 commits of an 8-second rollout, while Goal, Preview, and Control states adapt within that branch. An 8-second Goal anchors intent, a 2-second Preview coordinates interactions, and 1-second Control produces physical motion. Every 0.5-second commit feeds back only its executed prefix as new facts, while unexecuted hypotheses never enter factual memory. Joint Preview Interaction induces a sparse directed future graph and uses conflict probabilities and signed arrival-time differences to refine interaction-aware motion. For generated-state recovery, a prefix-frozen A-to-B cascade transfers typed physical state and the branch index--but no latent state--from a frozen prefix model to an independently parameterized recovery model. On the full H-D public-validation split of 955 scenarios, the S2.1 cascade obtains an 8-second scene-joint ADE-at-joint-minFDE@8/joint-minFDE@8 of 2.048/6.384 m when one World must explain all evaluated agents. Agent-centric oracle-minADE@8 is 0.526 m at 6 seconds and 0.875 m at 8 seconds.