mlsanityData to 7 Oct 2026

AI Metropolis: Scaling Large Language Model-based Multi-Agent Simulation with Out-of-order Execution

arXiv 2411.03519 ↗First posted 5 Nov 2024cs.DC cs.AI cs.LGcited by 14

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

With more advanced natural language understanding and reasoning capabilities, large language model (LLM)-powered agents are increasingly developed in simulated environments to perform complex tasks, interact with other agents, and exhibit emergent behaviors relevant to social science and gaming. However, current multi-agent simulations frequently suffer from inefficiencies due to the limited parallelism caused by false dependencies, resulting in performance bottlenecks. In this paper, we introduce AI Metropolis, a simulation engine that improves the efficiency of LLM agent simulations by incorporating out-of-order execution scheduling. By dynamically tracking real dependencies between agents, AI Metropolis minimizes false dependencies, enhancing parallelism and enabling efficient hardware utilization. Our evaluations demonstrate that AI Metropolis achieves speedups from 1.3x to 4.15x over standard parallel simulation with global synchronization, approaching optimal performance as the number of agents increases.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 18 of its 34 references that are in the map. First posted on arXiv 5 Nov 2024.

Builds on

18 of 34 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023An LLM Compiler for Parallel Function Calling7 Dec

Other references · 17

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  4. 2016Pointer Sentinel Mixture Modelscited by 2,992
  5. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  6. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  7. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  8. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  9. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,151
  10. 2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedbackcited by 738
  11. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
  12. 2023SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefillscited by 187
5 more
  1. 2023S-LoRA: Serving Thousands of Concurrent LoRA Adapterscited by 146
  2. 2023Punica: Multi-Tenant LoRA Servingcited by 80
  3. 2023Training Socially Aligned Language Models on Simulated Social Interactionscited by 77
  4. 2023Fairness in Serving Large Language Modelscited by 77
  5. 2023Pearl: A Production-ready Reinforcement Learning Agentcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 7.

14 papers.

Sort:

By area:

  1. 2025The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspectivecited by 38
  2. 2025Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agentscited by 23
  3. 2025Sherlock: Reliable and Efficient Agentic Workflow Executioncited by 10
  4. 2025TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrievalcited by 9
  5. 2025Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMscited by 9
  6. 2025Batch Query Processing and Optimization for Agentic Workflowscited by 6
  7. 2025Open Agent Specification (Agent Spec): A Unified Representation for AI Agentscited by 5
  8. 2026WhatIf: Interactive Exploration of LLM-Powered Social Simulations for Policy Reasoningcited by 3
  9. 2026Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulationcited by 3
  10. 2026ScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory Managementcited by 2
  11. 2026AgenticCache: Cache-Driven Asynchronous Planning for Embodied AI Agentscited by 2
  12. 2026Agents in the Large: Perception-Centered Architecture for Persistent Agentscited by 1
2 more
  1. 2026ATLAS: A Multi-LLM Training Framework for EvoDPO with Adaptive Reference Evolutioncited by 0
  2. 2026SmoothAgent: Efficient Long-Horizon LLM-Based Agent Serving with Lookahead Context Engineeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges
  2. 2024OpenCity: A Scalable Platform to Simulate Urban Activities with Massive LLM Agents
  3. 2025Optimizing Sequential Multi-Step Tasks with Parallel LLM Agents
  4. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives
  5. 2026A Two-Tier Perspective on Inference-Time Parallelism in Multi-Agent LLM Systems
  6. 2025Simulation Agent: A Framework for Integrating Simulation and Large Language Models for Enhanced Decision-Making
  7. 2025FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaboration
  8. 2024Very Large-Scale Multi-Agent Simulation in AgentScope