SIGN: Schema-Induced Games for Naming

2025-10-22

AI Summary

In real-world multi-LLM agent systems, unstructured communication leads to inconsistent naming conventions, causing collaboration failures and poor scalability. Method: We propose Schema-Induced Games for Naming (SIGN), a lightweight framework that employs minimal structured schemas as control mechanisms to guide agents in autonomously converging on consistent naming conventions through coordinated naming games. Contribution/Results: SIGN significantly accelerates consensus convergence—up to 5.8× faster than pure natural-language interaction—while markedly improving cross-agent semantic consistency. Its core innovation lies in treating minimal structure as a tunable “communication knob”: it preserves linguistic flexibility while enabling efficient, scalable multi-agent coordination. SIGN thus establishes a new paradigm for LLM collaboration that balances practical deployability with theoretical rigor.

Technology Category

• Multiagent Systems: Agent Communication
• Game Theory and Economic Paradigms: Coordination and Collaboration
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• 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
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

Real-world AI systems are tackling increasingly complex problems, often through interactions among large language model (LLM) agents. When these agents develop inconsistent conventions, coordination can break down. Applications such as collaborative coding and distributed planning therefore require reliable, consistent communication, and scalability is a central concern as systems grow. We introduce Schema-Induced Games for Naming (SIGN), a naming game that examines how lightweight structure can steer convention formation. We compare schema-induced communication to unconstrained natural language and find faster convergence with up to 5.8x higher agreement. These results suggest that minimal structure can act as a simple control knob for efficient multi-agent coordination, pointing toward broader applications beyond the naming game.

Problem

• Addressing inconsistent conventions in multi-agent systems
• Ensuring reliable communication for collaborative AI applications
• Improving coordination scalability through structured naming games

Innovation

• Schema-induced communication for multi-agent coordination
• Lightweight structure steers convention formation
• Faster convergence with higher agreement rates