Beyond Partner Diversity: An Influence-Based Team Steering Framework for Zero-Shot Human-Machine Teaming

TL;DR

This paper introduces Influence-Based Team Steering (IBTS), a novel framework that enhances zero-shot human-machine teaming by shaping influence to discover and steer toward effective coordination patterns, improving performance in multi-agent settings.

Contribution

The paper proposes IBTS, a new influence-shaping approach that improves zero-shot coordination in human-machine teams, especially in multi-agent and real human interaction scenarios.

Findings

IBTS outperforms baselines in team performance across various settings.

Influence shaping helps discover diverse, high-performing coordination modes.

IBTS effectively transfers learned coordination beyond dyadic interactions.

Abstract

While AI agents are rapidly advancing from isolated tools to interactive collaborators, data-driven human-machine teaming (HMT) methods remain costly in their reliance on human interaction data across domains, teammates, and team sizes. Zero-shot coordination (ZSC) addresses this bottleneck by simulating diverse partner populations to approximate how unseen partners might behave. However, partner coverage alone is insufficient as team settings scale and communication becomes degraded. To remedy this deficiency, we propose Influence-Based Team Steering (IBTS), a framework that uses influence shaping to incentivize agents to discover diverse, high-performing team interaction patterns and further steers ongoing trajectories toward stronger learned coordination modes. We assess IBTS on Overcooked-AI in both two-agent and three-agent settings, allowing us to test whether learned coordination structure transfers beyond dyadic interaction. Our evaluation includes simulated partners, synthetic partner-style variation, and, to our knowledge, the first 30-subject Overcooked-AI HMT study involving two real human teammates and one machine teammate. Across these evaluations, IBTS improves team performance against competing baselines, highlighting the need for scaled ZSC to combine sparse-reward coordination mechanisms with partner-variation coverage rather than relying on diversity alone.