Simon Storf
Publications
Training Deliberative Monitors for Black-Box Scheming Detection
As autonomous agents become more capable of performing real-world tasks, distinguishing scheming behavior from benign task pursuit may become a central AI control problem. Existing monitors often rely on chain-of-thought access or internal activations, or use prompted frontier models, all of which can be unavailable, unreliable or expensive in deployment. In this work, we study action-only deliberative monitors: smaller open-weight models trained to detect scheming and sabotage from agentic trajectories without accessing the monitored agent's reasoning or model internals. Our method, inspired by deliberative alignment, uses a scheming specification to elicit structured rationales from a frontier teacher, filters them with a separate judge, and distills the highest-quality rationales into open-weight monitors with supervised fine-tuning and reinforcement learning. We train on five datasets, and evaluate across six out-of-distribution agentic misalignment benchmarks. We show that applying our method to Qwen3.5-27B yields higher performance than all low-cost frontier models as prompted monitors (Gemini 3.1 Flash-Lite, GPT-5.4 Nano, and Claude Haiku 4.5) and than Gemini 2.5 Pro, while also achieving lower marginal inference cost (token-metered USD per 1,000 evaluations). Stronger prompted frontier monitors (Gemini 3.1 Pro, GPT-5.4, Claude Sonnet 4.6, and Claude Opus 4.6) achieve higher performance but at roughly $16$--$34\times$ higher marginal inference cost. Several of our trained monitors are positioned on the empirical cost--performance Pareto frontier among the monitors we evaluate, providing practical low-cost, low-FPR alternatives to prompted frontier models.
Constitutional Black-Box Monitoring for Scheming in LLM Agents
Safe deployment of Large Language Model (LLM) agents in autonomous settings requires reliable oversight mechanisms. A central challenge is detecting scheming, where agents covertly pursue misaligned goals. One approach to mitigating such risks is LLM-based monitoring: using language models to examine agent behaviors for suspicious actions. We study constitutional black-box monitors: prompted classifiers that detect scheming using only externally observable inputs and outputs, optimized on synthetic data generated from natural-language behavior specifications. We introduce two pipelines for generating synthetic agent trajectories, STRIDE (iterative refinement) and Gloom (agent-environment simulation), from which we generate 1,000 samples each. We optimize frontier LLM monitors on these datasets via prompt sweeps, human refinement, and automated prompt optimization, and evaluate performance on 7,500 held-out trajectories from ControlArena, a suite of grounded environments where agents operate in more realistic contexts. Our results demonstrate that monitors selected purely on synthetic data can generalize to more realistic environments, capturing a meaningful scheming signal. However, we find that performance saturates quickly in our setting, with simple prompt sweeps matching the results of more extensive optimization. Pushing beyond this limit yields no further improvements and instead leads to overfitting.