paper-with-me

Papers

Very Large-Scale Multi-Agent Simulation in AgentScope

2024-07-25 · Xuchen Pan, Dawei Gao, Yuexiang Xie, Yushuo Chen, Zhewei Wei, Yaliang Li, Bolin Ding, Ji-Rong Wen, Jingren Zhou

Recent advances in large language models (LLMs) have opened new avenues for applying multi-agent systems in very large-scale simulations. However, there remain several challenges when conducting multi-agent simulations with existing platforms, such as limited scalability and low efficiency, unsatisfied agent diversity, and effort-intensive management processes. To address these challenges, we develop several new features and components for AgentScope, a user-friendly multi-agent platform, enhancing its convenience and flexibility for supporting very large-scale multi-agent simulations. Specifically, we propose an actor-based distributed mechanism as the underlying technological infrastructure towards great scalability and high efficiency, and provide flexible environment support for simulating various real-world scenarios, which enables parallel execution of multiple agents, automatic workflow conversion for distributed deployment, and both inter-agent and agent-environment interactions. Moreover, we integrate an easy-to-use configurable tool and an automatic background generation pipeline in AgentScope, simplifying the process of creating agents with diverse yet detailed background settings. Last but not least, we provide a web-based interface for conveniently monitoring and managing a large number of agents that might deploy across multiple devices. We conduct a comprehensive simulation to demonstrate the effectiveness of these proposed enhancements in AgentScope, and provide detailed observations and insightful discussions to highlight the great potential of applying multi-agent systems in large-scale simulations. The source code is released on GitHub at https://github.com/modelscope/agentscope/tree/main/examples/paper_large_scale_simulation to inspire further research and development in large-scale multi-agent simulations.

📄 PDF Abstract BibTeX arXiv:2407.17789

Code (1)

modelscope/agentscope 공식 구현

Similar Papers 제목 키워드 기반

LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulation

2024-12-12 · Yijun Liu, Wu Liu, Xiaoyan Gu, Yong Rui 외

The believable simulation of multi-user behavior is crucial for understanding complex social systems. Recently, large language models (LLMs)-based AI agents have made significant progress, enabling them to achieve human-…

User Simulation

CityBehavEx: A Scalable and Empirically Validated LLM-Assisted Urban Simulation Platform

2026-07-13 · Gustavo H. Santos, Aline Viana, Thiago H Silva arxiv

Recent LLM-based multi-agent urban simulators can generate semantically rich city routines, but they remain costly to scale and are often weakly validated against empirical mobility patterns. We present CityBehavEx, an i…

Multi-Agent Collaboration for Automated Design Exploration on High Performance Computing Systems

2026-03-12 · Harshitha Menon, Charles F. Jekel, Kevin Korner, Brian Gunnarson 외 arxiv

Today's scientific challenges, from climate modeling to Inertial Confinement Fusion design to novel material design, require exploring huge design spaces. In order to enable high-impact scientific discovery, we need to s…

Parallel Bayesian Optimization of Agent-based Transportation Simulation

2022-07-11 · Kiran Chhatre, Sidney Feygin, Colin Sheppard, Rashid Waraich

MATSim (Multi-Agent Transport Simulation Toolkit) is an open source large-scale agent-based transportation planning project applied to various areas like road transport, public transport, freight transport, regional evac…

Bayesian Optimization

ScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory Management

2026-01-29 · Zaifeng Pan, Yipeng Shen, Zhengding Hu, Zhuang Wang 외 arxiv

LLM-based multi-agent simulations are increasingly adopted across application domains, but remain difficult to scale due to GPU memory pressure. Each agent maintains private GPU-resident states, including models, prefix …