---
title: SchemeArena
emoji: 🕶️
colorFrom: red
colorTo: blue
sdk: static
pinned: false
license: cc-by-4.0
short_description: Factorized stress testing of scheming in LLM agents
---

# SchemeArena

Project page for **SchemeArena: Factorized Stress Testing of Scheming in LLM Agents**.

- 400 agentic scheming scenarios over 28 safety-relevant tool domains
- 7 controlled setups varying instrumental goals, pressure, strategic hints, and oversight
- SCOUT, a criteria-based scheming monitor grounded in evidence from agents' reasoning and actions

Links: [Paper](https://arxiv.org/abs/2609.08126) · [Dataset](https://huggingface.co/datasets/launch/SchemeArena) · [Code](https://github.com/launchnlp/SchemeArena)