CueTip: An Interactive and Explainable Physics-aware Pool Assistant

2025-01-30

AI Summary

To address the lack of strategic understanding and decision support in billiards, this paper proposes an interactive intelligent coaching system tailored for multi-variant billiards. Methodologically, we introduce a novel tripartite architecture integrating (i) a natural-language interface, (ii) context-aware physical reasoning, and (iii) expert-rule-driven explanation generation. A neural adapter is designed to decouple decision-making, human–agent interaction, and explanatory modules, enabling dynamic switching among agent interaction styles. The system synergistically combines high-fidelity physics simulation, large language model (LLM) interfacing, a customized neural adapter, and embedded domain-specific expert rules. Contributions include: (i) real-time, physically grounded tactical recommendations that significantly improve win rates in critical scenarios; (ii) causal, natural-language explanations with higher reliability than black-box models; and (iii) context-sensitive real-time querying and pedagogical feedback.

Technology Category

• Multiagent Systems: Adversarial Agents
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Human-Aware Planning and Behavior Prediction

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: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We present an interactive and explainable automated coaching assistant called CueTip for a variant of pool/billiards. CueTip's novelty lies in its combination of three features: a natural-language interface, an ability to perform contextual, physics-aware reasoning, and that its explanations are rooted in a set of predetermined guidelines developed by domain experts. We instrument a physics simulator so that it generates event traces in natural language alongside traditional state traces. Event traces lend themselves to interpretation by language models, which serve as the interface to our assistant. We design and train a neural adaptor that decouples tactical choices made by CueTip from its interactivity and explainability allowing it to be reconfigured to mimic any pool playing agent. Our experiments show that CueTip enables contextual query-based assistance and explanations while maintaining the strength of the agent in terms of win rate (improving it in some situations). The explanations generated by CueTip are physically-aware and grounded in the expert rules and are therefore more reliable.

Problem

• Intelligent Assistant
• Billiard Game Strategy
• Physics-based Advice

Innovation

• Intelligent Billiards Assistant
• Expert Rule-based Strategy
• Mandarin Interaction