Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios

TL;DR

SEMA is a novel multi-agent framework that enhances decision-making speed and accuracy in real-time strategy games by self-evolving, pruning observations, and integrating hierarchical knowledge, leading to over 50% latency reduction and improved win rates.

Contribution

This paper introduces SEMA, a self-evolving multi-agent system that combines adaptive bias calibration, dynamic observation pruning, and hierarchical knowledge integration for efficient RTS decision-making.

Findings

Achieves over 50% reduction in decision latency.

Demonstrates superior win rates across multiple StarCraft II maps.

Validates robustness and efficiency in complex RTS scenarios.

Abstract

Large language models (LLMs) have demonstrated exceptional potential in complex reasoning,pioneering a new paradigm for autonomous agent decision making in dynamic settings. However, in Real-Time Strategy (RTS) scenarios, LLMs suffer from a critical speed-quality trade-off. Specifically expansive state spaces and time limits render inference delays prohibitive, while stochastic planning errors undermine logical consistency. To address these challenges, we present SEMA (Self-Evolving Multi-Agent), a novel framework designed for high-performance, low-latency decision-making in RTS environments. This collaborative multi-agent framework facilitates self-evolution by adaptively calibrating model bias through in-episode assessment and cross-episode analysis. We further incorporate dynamic observation pruning based on structural entropy to model game states topologically. By distilling high dimensional data into core semantic information, this approach significantly reduces inference time. We also develop a hybrid knowledge-memory mechanism that integrates micro-trajectories, macro-experience, and hierarchical domain knowledge, thereby enhancing both strategic adaptability and decision consistency. Experiments across multiple StarCraft II maps demonstrate that SEMA achieves superior win rates while reducing average decision latency by over 50%, validating its efficiency and robustness in complex RTS scenarios.