Planning Ahead with RSA: Efficient Signalling in Dynamic Environments by Projecting User Awareness across Future Timesteps

2025-10-27

AI Summary

To address the misalignment of human–AI beliefs arising from delayed AI information delivery and limited human attention in dynamic environments, this paper proposes a cognitive-modeling–based proactive communication planning method. The core innovation lies in the first extension of the Rational Speech Act (RSA) model to multi-timestep dynamic scenarios, integrating Bayesian reference resolution with user attention constraints to construct an “awareness projection” model that predicts future multi-step cognitive states and thereby optimizes information scheduling sequences. A prior-guided message interpretation mechanism enables cross-temporal adaptive signal modulation. Experiments demonstrate that, compared to baselines, the method significantly improves information transmission efficiency (+23.6%) and task coordination accuracy (+18.4%). It establishes a novel, interpretable, and predictive, cognition-driven paradigm for real-time human–AI alignment.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Agent Communication

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Adaptive agent design offers a way to improve human-AI collaboration on time-sensitive tasks in rapidly changing environments. In such cases, to ensure the human maintains an accurate understanding of critical task elements, an assistive agent must not only identify the highest priority information but also estimate how and when this information can be communicated most effectively, given that human attention represents a zero-sum cognitive resource where focus on one message diminishes awareness of other or upcoming information. We introduce a theoretical framework for adaptive signalling which meets these challenges by using principles of rational communication, formalised as Bayesian reference resolution using the Rational Speech Act (RSA) modelling framework, to plan a sequence of messages which optimise timely alignment between user belief and a dynamic environment. The agent adapts message specificity and timing to the particulars of a user and scenario based on projections of how prior-guided interpretation of messages will influence attention to the interface and subsequent belief update, across several timesteps out to a fixed horizon. In a comparison to baseline methods, we show that this effectiveness depends crucially on combining multi-step planning with a realistic model of user awareness. As the first application of RSA for communication in a dynamic environment, and for human-AI interaction in general, we establish theoretical foundations for pragmatic communication in human-agent teams, highlighting how insights from cognitive science can be capitalised to inform the design of assistive agents.

Problem

• Optimizing message timing and specificity for dynamic human-AI collaboration
• Planning multi-step communication to align user beliefs with environments
• Using cognitive models to manage attention in time-sensitive tasks

Innovation

• Uses Rational Speech Act framework for message planning
• Adapts message specificity and timing to user
• Projects user awareness across multiple future timesteps