Agent MechSuits: Mechanistic Subspace Safety Steering for Multi-Turn CLI Agents

arXiv:2606.22673 · cs.AI, cs.SE · Submitted 2026-06-21 · Read on arXiv

cs.AI, cs.SE

Submitted: 2026-06-21

Updated: 2026-10-05

Terminology

• Interpretability — 2× in this paper · explained in 15 episodes
• Mechanistic interpretability — 2× in this paper · explained in 2 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes

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