RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Models

arXiv:2606.18950 · cs.AI · Submitted 2026-06-17 · Read on arXiv

cs.AI

Submitted: 2026-06-17

Updated: 2026-10-03

Code: https://github.com/beyond-all-reason/Beyond-All-Reason

Terminology

• Benchmark — 3× in this paper · explained in 2 episodes
• Vision-language models — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes

Sources

• GameGPT: Multi-agent Collaborative Framework for Game Development
• Strategic Reasoning with Language Models
• PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models
• AvalonBench: Evaluating LLMs Playing the Game of Avalon
• OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics
• TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft
• MemGPT: Towards LLMs as Operating Systems
• SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language models
• SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks
• Measuring General Intelligence with Generated Games
• SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?
• AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems