# JEV-Star: Fast, Low-Cost StarCraft II Control with Language-Model Planning

arXiv: https://arxiv.org/abs/2609.27331 · HTML: https://mlsanity.com/paper/2609.27331/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2026.

## Built on by (most cited first, 5 of 5)

- [Typed Decision Models: An Early Evidence Audit and Evaluation Checklist](https://mlsanity.com/paper/2609.32160/) (2026)
- [Benchmarking System One decision models against trained classifiers and language models for automated decision gates](https://mlsanity.com/paper/2610.00346/) (2026)
- [OmniMed-Jev: Calibrating LVLM Confidence for Trustworthy Medical Multimodal Decisions via System One](https://mlsanity.com/paper/2610.00381/) (2026)
- [Token-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of Labor](https://mlsanity.com/paper/2610.08155/) (2026)
- [Can Jev be Your Q or Policy in Reinforcement Learning?](https://mlsanity.com/paper/2610.11692/) (2026)

## Abstract (arXiv)

We present JEV-Star, a StarCraft II controller that defeats the strongest non-cheating built-in AI, Lv7, by combining fast JEV action selection with persistent GPT-6 planning. The combined system wins four full games at Lv5--Lv7, including two Lv7 victories with different seeds, while retaining a median JEV response time of 0.422 seconds. Mean estimated model cost across these games is USD~3.71 per game: USD~0.15 for JEV and USD~3.56 for GPT-6. We compare this system with an initial JEV-only controller in full-game macro control and multi-unit micromanagement. The standalone controller reaches a 20-minute limit against Lv2 without expanding. Across 35 battle maps with three episodes per map and controller, the combined system raises mean enemy elimination from 16.50% to 37.69% and wins from 3 to 7 out of 105. Replay frames and decision logs document resource reservation, persistent economic goals, and stable army objectives in successful full games. The results demonstrate a practical division between inexpensive, subsecond decisions and longer-horizon planning. The comparison evaluates complete systems; concurrent interface improvements mean that planning's contribution is not isolated by a controlled ablation. Code is available at https://github.com/sc2musa/JevStar