Topic
simulation
Simulating Language Evolution Under Regulated Social Media Using LLMs and Genetic Algorithms
A new research paper presents a multi-agent framework using Large Language Models and genetic algorithms to simulate how language strategies evolve under regulated social media platforms. The framework, tested on a password game and an illegal pet trade scenario, shows significant improvement in uninterrupted dialogue turns and information transmission accuracy over increasing rounds. A user study with 40 participants validated the realism.
UniMM Framework Achieves State-of-the-Art in Multi-Agent Simulation for Autonomous Driving
Researchers introduce UniMM, a unified mixture model framework for multi-agent simulation that covers regression-based and discrete models. The framework achieves state-of-the-art performance on the WOSAC benchmark by addressing behavioral multimodality and closed-loop distributional shifts.
New Frontier Simulator Cuts LLM Inference Latency Error to Under 3% for Disaggregated Serving
Researchers introduce Frontier, a discrete-event simulator for modern LLM inference serving that models disaggregated execution, runtime optimizations, and stateful workloads. On a 16-H800 GPU testbed, Frontier achieves average throughput error below 4% and reduces end-to-end latency error from 44.9% to 6.4% under co-location, and from 51.7% to 2.6% under disaggregation. The simulator scales to over 1K GPUs on commodity CPUs and enables new use cases like SLA-dependent Pareto frontier exploration.
ControlMap: Controllable HD Map Generation Using Latent Diffusion for Traffic Simulation
Current autonomous driving simulation is limited by costly HD map creation. ControlMap presents a pipeline using latent diffusion and ControlNet to generate HD maps that follow specific road topologies and city styles. The model introduces novel metrics for adherence and similarity.
RealityBridge: New AI Framework Edits 3D Driving Simulations to Close the Sim-to-Real Gap
RealityBridge is a structure-preserving framework that edits 3D Gaussian Splatting driving simulations and bridges the gap to real-world video quality. It uses multimodal controls and autoregressive training to reduce artifacts, harmonize illumination, and ensure temporal consistency, outperforming existing methods on driving datasets.
Posterior Twins: Distributional Behavioral Simulation for Enterprise Decisions
A new arXiv paper introduces Posterior Twins, a memory-grounded digital-twin approach for enterprise behavioral simulation. Evaluated on a 226-example benchmark, the TL-Twin Alpha model achieves the lowest reported Wasserstein-1 distance (1.16), while TL-Twin Delta and TL-Twin Gamma offer balanced operating points. The paper emphasizes governable memory, behavioral model routing, scenario orchestration, distributional aggregation, and auditability as necessary components for reusable decision evidence.
New LLM-Based Simulator Evaluates Deliberative Polling Information Systems Against Strategic Attacks
Researchers introduce the LLM-based Agentic Bipolar Argumentation Simulator (ABAS) to evaluate information systems for deliberative polling. ABAS simulates autonomous agents voting and submitting justifications, measuring coverage of the reason space. Experiments show that a tag-flood attack collapses coverage, while a reversed-PageRank weighting resists it markedly better than uniform weights.
Shachi: A Modular Open-Source Framework for LLM-Based Agent-Based Modeling of Emergent Collective Behavior
Researchers introduced Shachi, a modular framework for agent-based modeling where LLM-driven agents have independently controllable cognitive components. Tested on a 10-task benchmark, Shachi replicates real-world market dynamics in a U.S. tariff shock scenario, offering an open-source tool for studying emergent collective behavior.
Edu-Theater: A Data-Efficient LLM Agent Framework for Scalable Learner Behavior Simulation
Edu-Theater is a new LLM-powered agent framework for simulating learner behavior. It uses a cohort-aware roll-call paradigm to reduce data and computation needs. Experiments on two real-world datasets show higher accuracy with fewer LLM calls, enabling scalable synthetic data generation for adaptive testing.
Technology FBI builds entire town with 200 hackable servers to train agents against global cyber threats
The FBI's Kinetic Cyber Range, a 22,000-square-foot mock town in Huntsville, Alabama, contains 11 facilities including houses, a data center, and a hotel, all with 200 hackable servers. More than 1,400 students have trained there since February 2025, learning to combat emerging cyber threats through hands-on exercises with drone software, vehicle forensics, and IoT.
Technology Decart's Oasis 3: Photorealistic Driving Simulations
Decart has launched Oasis 3, a world model that simulates photorealistic driving environments in real time. Targeting autonomous vehicle companies, the model is available via API and aims to build a developer ecosystem. Despite its efficiency and photorealism, the model faces challenges in maintaining thematic consistency and physics simulation.