AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation
cs.AI, cs.CR
Submitted: 2026-03-08
Updated: 2026-10-09
Code: https://github.com/CosmosYi/AutoControl-Arena
Project page: https://cosmosyi.github.io/AutoControl-Arena
Terminology
Sources
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- Inverse Scaling in Test-Time Compute
- Alignment faking in large language models
- Risks from Learned Optimization in Advanced Machine Learning Systems
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- Reliable Weak-to-Strong Monitoring of LLM Agents
- OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
- SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents
- Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
- AgentBench: Evaluating LLMs as Agents
- Agentic Misalignment: How LLMs Could Be Insider Threats
- Frontier Models are Capable of In-context Scheming
- The Alignment Problem from a Deep Learning Perspective
- Evaluating Frontier Models for Dangerous Capabilities
- Safety Alignment Should Be Made More Than Just a Few Tokens Deep
- Identifying the Risks of LM Agents with an LM-Emulated Sandbox
- Model evaluation for extreme risks
- SafeArena: Evaluating the Safety of Autonomous Web Agents
- AI Sandbagging: Language Models can Strategically Underperform on Evaluations
- Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection