AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent Simulations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915946023616512 |
|---|---|
| author | Ma, Jenny Sahni, Riya Sreedhar, Karthik Chilton, Lydia B. |
| author_facet | Ma, Jenny Sahni, Riya Sreedhar, Karthik Chilton, Lydia B. |
| contents | 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 notable and emergent dynamics. We present AgentDynEx, an AI system that helps set up simulations from user-specified mechanics and dynamics. AgentDynEx uses LLMs to guide users through a Configuration Matrix to identify core mechanics and define milestones to track dynamics. It also introduces a method called \textit{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 have more complex mechanics and maintain its notable dynamics compared to simulations without nudging. We discuss the importance of nudging as a technique for balancing mechanics and dynamics of multi-agent simulations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09662 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent Simulations Ma, Jenny Sahni, Riya Sreedhar, Karthik Chilton, Lydia B. Multiagent Systems Artificial Intelligence Human-Computer Interaction 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 notable and emergent dynamics. We present AgentDynEx, an AI system that helps set up simulations from user-specified mechanics and dynamics. AgentDynEx uses LLMs to guide users through a Configuration Matrix to identify core mechanics and define milestones to track dynamics. It also introduces a method called \textit{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 have more complex mechanics and maintain its notable dynamics compared to simulations without nudging. We discuss the importance of nudging as a technique for balancing mechanics and dynamics of multi-agent simulations. |
| title | AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent Simulations |
| topic | Multiagent Systems Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2504.09662 |