Feasibility and Implementation of LLM-based Auxiliary Combat Agents in Multi-unit Real-Time Strategy (RTS) Games

Location: Venue 5 - 358

This talk explores the feasibility and specific implementation of Large Language Models (LLMs) as auxiliary combat agents in multi-unit Real-Time Strategy (RTS) games. Unlike traditional rule-based or heuristic AI systems, LLM-based agents can understand and parse players' high-level commands and abstract language through natural language understanding, and dynamically convert them into executable game operations. We analyze key issues in the implementation process, including player semantic understanding, command learning comprehension, game structure learning, game state understanding, execution content output, and error correction, as well as challenges in real-time performance and accuracy trade-offs.