mlsanityData to 14 Oct 2026

AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent Simulations

arXiv 2504.09662 ↗First posted 13 Apr 2025cs.MA cs.AI cs.HCcited by 1

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 17 of its 89 references that are in the map. First posted on arXiv 13 Apr 2025.

Builds on

17 of 89 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Simulating Cooperative Prosocial Behavior with Multi-Agent LLMs: Evidence and Mechanisms for AI Agents to Inform Policy Decisions18 Feb
  2. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society12 Feb
  3. 2024Can Large Language Model Agents Simulate Human Trust Behavior?7 Feb
  4. 2023Generative Agent-Based Modeling: Unveiling Social System Dynamics through Coupling Mechanistic Models with Generative Artificial Intelligence20 Sep
  5. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 12

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  3. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  4. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 515
  5. 2022Social Simulacra: Creating Populated Prototypes for Social Computing Systemscited by 301
  6. 2023Theory of Mind for Multi-Agent Collaboration via Large Language Modelscited by 135
  7. 2022PromptChainer: Chaining Large Language Model Prompts through Visual Programmingcited by 134
  8. 2025Interactive Debugging and Steering of Multi-Agent AI Systemscited by 68
  9. 2023Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creationcited by 64
  10. 2023Spellburst: A Node-based Interface for Exploratory Creative Coding with Natural Language Promptscited by 30
  11. 2023Balancing Autonomy and Alignment: A Multi-Dimensional Taxonomy for Autonomous LLM-powered Multi-Agent Architecturescited by 25
  12. 2024DynEx: Dynamic Code Synthesis with Structured Design Exploration for Accelerated Exploratory Programmingcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026SCSimulator: An Exploratory Visual Analytics Framework for Partner Selection in Supply Chains through LLM-driven Multi-Agent Simulationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026AI Agents Alone Are Not (Yet) Sufficient for Social Simulation
  2. 2025Simulating Teams with LLM Agents: Interactive 2D Environments for Studying Human-AI Dynamics
  3. 2025Emergent Crowds Dynamics from Language-Driven Multi-Agent Interactions
  4. 2026HumanStudy-Bench: Towards AI Agent Design for Participant Simulation
  5. 2025Static Sandboxes Are Inadequate: Modeling Societal Complexity Requires Open-Ended Co-Evolution in LLM-Based Multi-Agent Simulations
  6. 2025Simulation Agent: A Framework for Integrating Simulation and Large Language Models for Enhanced Decision-Making
  7. 2026DIG to Heal: Scaling General-purpose Agent Collaboration via Explainable Dynamic Decision Paths
  8. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives