AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

We present CivBench, an open-source benchmark for evaluating language model agents in long-horizon, tool-mediated environments through the Model Context Protocol (MCP). A single episode spans 300+ turns and produces thousands of tool calls over a large action space, requiring sustained planning, state monitoring, and execution under partial observability. The environment exposes 76 MCP tools and a narration layer that converts visual game state into structured text. We use CivBench to characterise agent behaviour across four model families in 23 admissible runs. The sample is a pilot, not a mo

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-21T05:32:15.665Z. This is not the publication date.