"Teammates, Am I Clear?": Analysing Legible Behaviours in Teams

2025-07-29

AI Summary

This study addresses the problem of legibility—i.e., the ability of teammates to rapidly and accurately infer an agent’s intent—in multi-agent sequential decision-making. We present the first systematic extension of single-agent legibility to collaborative multi-agent settings. Our method introduces a sequence-decision-theoretic framework for legibility-aware multi-agent policy optimization, unifying treatment of both deterministic and stochastic environments, and incorporates legibility as an explicit objective in cooperative learning. The core contribution lies in explicitly modeling how well teammates can infer an agent’s intended actions, thereby enhancing team-level interpretability and predictability without compromising individual rationality. Empirical evaluation across multiple multi-agent benchmarks demonstrates that teams composed of legible agents significantly outperform teams of fully optimal-response agents: collaboration efficiency and task performance improve by 12.7%–34.5%.

Technology Category

• Multiagent Systems: Teamwork
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Intelligent Robots: Multi-Robot Systems

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

In this paper we investigate the notion of legibility in sequential decision-making in the context of teams and teamwork. There have been works that extend the notion of legibility to sequential decision making, for deterministic and for stochastic scenarios. However, these works focus on one agent interacting with one human, foregoing the benefits of having legible decision making in teams of agents or in team configurations with humans. In this work we propose an extension of legible decision-making to multi-agent settings that improves the performance of agents working in collaboration. We showcase the performance of legible decision making in team scenarios using our proposed extension in multi-agent benchmark scenarios. We show that a team with a legible agent is able to outperform a team composed solely of agents with standard optimal behaviour.

Problem

• Extending legible decision-making to multi-agent teams
• Improving collaboration performance in agent teams
• Demonstrating legible agents outperform standard optimal teams

Innovation

• Extends legible decision-making to multi-agent teams
• Improves collaboration performance in agent teams
• Outperforms standard optimal behavior in benchmarks