Teaming in the AI Era: AI-Augmented Frameworks for Forming, Simulating, and Optimizing Human Teams

2025-06-05

AI Summary

In team formation and execution, misalignment among user preferences, dynamic objectives, and individual traits leads to low satisfaction, weak commitment, and suboptimal performance. Method: This paper proposes an AI-augmented dynamic team optimization framework comprising three components: (1) intelligent team formation via preference–objective alignment, (2) tAIfa—a real-time, personalized feedback intervention system, and (3) PuppeteerLLM—a multi-agent simulation and modeling platform. It introduces a novel closed-loop optimization paradigm integrating multi-armed bandits with large language models (LLMs), overcoming key limitations of conventional approaches—static configuration, single-objective optimization, and poor generalizability. Contribution/Results: Empirical and simulation evaluations demonstrate an average 23% improvement in team performance, a 3.8× acceleration in behavioral adaptation response time, and significant gains in member engagement and team cohesion.

Technology Category

• Humans and AI: Teamwork, Team formation
• Multiagent Systems: Teamwork
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Effective teamwork is essential across diverse domains. During the team formation stage, a key challenge is forming teams that effectively balance user preferences with task objectives to enhance overall team satisfaction. In the team performing stage, maintaining cohesion and engagement is critical for sustaining high team performance. However, existing computational tools and algorithms for team optimization often rely on static data inputs, narrow algorithmic objectives, or solutions tailored for specific contexts, failing to account for the dynamic interplay of team members personalities, evolving goals, and changing individual preferences. Therefore, teams may encounter member dissatisfaction, as purely algorithmic assignments can reduce members commitment to team goals or experience suboptimal engagement due to the absence of timely, personalized guidance to help members adjust their behaviors and interactions as team dynamics evolve. Ultimately, these challenges can lead to reduced overall team performance. My Ph.D. dissertation aims to develop AI-augmented team optimization frameworks and practical systems that enhance team satisfaction, engagement, and performance. First, I propose a team formation framework that leverages a multi-armed bandit algorithm to iteratively refine team composition based on user preferences, ensuring alignment between individual needs and collective team goals to enhance team satisfaction. Second, I introduce tAIfa (Team AI Feedback Assistant), an AI-powered system that utilizes large language models (LLMs) to deliver immediate, personalized feedback to both teams and individual members, enhancing cohesion and engagement. Finally, I present PuppeteerLLM, an LLM-based simulation framework that simulates multi-agent teams to model complex team dynamics within realistic environments, incorporating task-driven collaboration and long-term coordination.

Problem

• Balancing user preferences with task objectives for team satisfaction
• Maintaining team cohesion and engagement for high performance
• Addressing dynamic team dynamics with AI-augmented optimization tools

Innovation

• Multi-armed bandit algorithm for dynamic team formation
• LLM-powered feedback assistant for team engagement
• LLM-based simulation for modeling team dynamics