MobileCity: An Efficient Framework for Large-Scale Urban Behavior Simulation (2026.eacl-industry)
Copied to clipboard
| Challenge: | Existing methods for simulating realistic urban behaviors rely on static profiles and synchronous inference pipelines that hinder scalability. |
| Approach: | They propose a lightweight generative agent framework for city-scale simulation powered by cognitively-grounded generative agents. |
| Outcome: | Experiments with 4,000 agents show that MobileCity generates more human-like urban dynamics than baselines while maintaining high computational efficiency. |
Similar Papers
CitySim: Modeling Urban Behaviors and City Dynamics with Large-Scale LLM-Driven Agent Simulation (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing models rely on rigid, hand-crafted rules to model nuanced behavior in urban environments. |
| Approach: | They propose an urban simulator that generates realistic daily schedules using a recursive value-driven approach that balances mandatory activities, personal habits, and situational factors. |
| Outcome: | The proposed urban simulator exhibits closer alignment with real humans than previous work. |
Can MLLMs Find Their Way in a City? Exploring Emergent Navigation from Web-Scale Knowledge (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing evaluation benchmarks for multimodal large language models (MLLMs) are language-centric or heavily reliant on simulated environments, rarely probing the nuanced, knowledge-intensive reasoning essential for practical, real-world scenarios. |
| Approach: | They propose a task of Sparsely Grounded Visual Navigation to evaluate MLLM-driven agents in city navigation in four diverse global cities. |
| Outcome: | The proposed benchmark encompassing four diverse global cities evaluates agents' decision-making abilities in city navigation. |
A Parallelized Framework for Simulating Large-Scale LLM Agents with Realistic Environments and Interactions (2025.acl-industry)
Copied to clipboard
| Challenge: | Existing work on large language models lacks a realistic environment and parallelized framework to support complex interactions between agents and environments. |
| Approach: | They propose a framework that integrates realistic societal environments and parallelized interactions to support simulations of large-scale agents. |
| Outcome: | The proposed framework can support simulations of 30,000 agents faster than the wall-clock time with 24 NVIDIA A800 GPUs and the performance increases linearly with the increase of LLM computational resources. |
Humanoid Agents: Platform for Simulating Human-like Generative Agents (2023.emnlp-demo)
Copied to clipboard
| Challenge: | Humanoid Agents aims to guide Generative Agents to behave more like humans using System 1 processing . we introduce three elements of System 1 that can influence their behavior . |
| Approach: | They propose a system that guides Generative Agents to behave more like humans . they introduce three elements of System 1 processing that can influence their behavior . humanoid agents can use these dynamic elements to adapt their daily activities and conversations . |
| Outcome: | The proposed system guides Generative Agents to behave more like humans . it incorporates three elements of System 1 processing that can influence their behavior . humanoid agents can adapt their daily activities and conversations with other agents . |
CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations (2026.findings-acl)
Copied to clipboard
| Challenge: | LLM-empowered agent simulations generate rich, adaptive, and often nonlinear interaction patterns. |
| Approach: | They propose an automated Causal discovery framework for LLM agent simulations that converts mechanistic hypotheses into computable factors and learns a compact causal representation centered on an emergent target. |
| Outcome: | Experiments across four emergent settings demonstrate the promise of CAMO. |
GTA: Generating Long-horizon Tasks for Web Agents at Scale (2026.acl-long)
Copied to clipboard
Tenghao Huang, Kung-Hsiang Huang, Prafulla Kumar Choubey, Yilun Zhou, Muhao Chen, Jonathan May, Chien-Sheng Wu
| Challenge: | Existing benchmarks provide only coarse start–goal annotations without intermediate trajectories . Existing frameworks provide no supervision over the agent's latent decision process . |
| Approach: | They propose a framework that integrates crawling, retrieval-based seeding, in-context generation and automated quality control to produce realistic tasks paired with executable trajectories. |
| Outcome: | The proposed framework decouples crawling from generation for greater efficiency and ensures dense supervision through deterministic replays and systematic validation. |
Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training (2026.acl-long)
Copied to clipboard
Jihao Gu, Qihang Ai, Yingyao Wang, Pi Bu, Jingxuan Xing, Yue Cao, Zekun Zhu, Wei Jiang, Ziming Wang, Yingxiu Zhao, Ming-Liang Zhang, Jun Song, Yuning Jiang, Bo Zheng
| Challenge: | Existing approaches to training agents for visual-language models trap them in local optima, hindering exploration and error correction with the environment. |
| Approach: | They propose a hierarchical training recipe that bridges atomic action execution and strategic task completion. |
| Outcome: | The proposed training recipe bridges atomic action execution and strategic task completion. |
SimUSER: Simulating User Behavior with Large Language Models for Recommender System Evaluation (2025.acl-industry)
Copied to clipboard
| Challenge: | Recommender systems are a key component of our day-to-day lives, but evaluation remains a challenge due to the gap between offline metrics and online behaviors. |
| Approach: | They propose a framework that enables users to build believable human proxies from historical data. |
| Outcome: | The proposed framework exhibits closer alignment with real humans than previous work, both at micro and macro levels. |
Unveiling the Truth and Facilitating Change: Towards Agent-based Large-scale Social Movement Simulation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for simulating social movements encounter challenges in capturing behavior of participants. |
| Approach: | They propose a hybrid framework for social media user simulation wherein users are categorized into two types: core and ordinary users. |
| Outcome: | The proposed framework is able to simulate the behavior of social media users across real-world datasets and demonstrate its effectiveness and flexibility. |
UrbanLLM: Autonomous Urban Activity Planning and Management with Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | UrbanLLM is a fine-tuned large language model designed to tackle diverse urban problems. |
| Approach: | They propose a fine-tuned large language model to tackle diverse urban problems . UrbanLLM decomposes urban-related queries into manageable sub-tasks . |
| Outcome: | The proposed model outperforms existing models in urban planning and management tasks. |