Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes
Abstract
Using the theoretical lens of the modified-action MDP, we show that common alignment techniques that are typically developed under single-user settings do not account for the dynamics of long-horizon multi-party interactions. We use a roleplay simulation methodology to quantify how AI partner interventions affect the trajectory of collaborative task dialogues. We show that interventions that are robust to action modification significantly outperform standard alignment in collaborative task support.
Fields of Study & Subjects
Semantic Web and Ontologies
Knowledge Management and Sharing
Business Process Modeling and Analysis
Publication details
- Journal / source
- Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems
- Publisher
- International Foundation for Autonomous Agents and Multiagent Systems
- Publication date
- 24 May 2026
- Language
- EN