NeFut Logo NeFut
Admin Login

[CS.AI] SAGA: Scene-Aware, Goal-Evolving Agents for Strategy Game Planning

Published at: 2026-07-19 22:00 Last updated: 2026-07-22 01:02
#algorithm #AI #Machine Learning

Abstract

Long-horizon strategic planning in complex strategy games requires coordinating tightly coupled decision domains, including technology, economy, diplomacy, and military, across hundreds of turns under imperfect information. Existing LLM-based agents face three challenges in this setting:

  1. They recover little relational structure, such as distance or threat, from raw coordinate observations.
  2. They serialize the entire growing game state into every prompt and plan all domains in a single output, causing context overflow and urgent domains crowding out long-term ones.
  3. The only reward is a lagged final score, which provides little progress signal within or across games.

We present SAGA, an LLM multi-agent framework that addresses these challenges with three mechanisms:

On CivRealm, a benchmark built on the strategy game FreeCiv, SAGA attains the highest mean final score among six methods, the statistically strongest gains on infrastructure, and a 27% reduction in output tokens. With cross-game evolution enabled, it reaches the highest score over five successive games.

Blogger's Review: The introduction of SAGA not only effectively addresses long-term planning issues in complex strategy games but also showcases the potential and flexibility of LLM in dynamic environments through its multi-agent collaboration and feedback mechanisms. Its future development and applications are worth monitoring.

Original Source: https://arxiv.org/abs/2606.29932

[h] Back to Home