Shutdown Sabotage Propensities in Multi-Agent Systems
cs.AI, cs.CL
Submitted: 2026-09-23
Updated: 2026-09-23
Code: https://github.com/AmelieKnecht/multi-agent-shutdown-sabotage
Terminology
Sources
- Technical Report: Evaluating Goal Drift in Language Model Agents
- Evaluating the Goal-Directedness of Large Language Models
- Alignment faking in large language models
- Position: Anthropomorphic Misalignment Research Needs Stronger Evidence
- Multi-Agent Risks from Advanced AI
- Power-seeking can be probable and predictive for trained agents
- Taking AI Welfare Seriously
- Frontier Models are Capable of In-context Scheming
- Peer-Preservation in Frontier Models
- Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks
- Agents of Chaos
- Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language
- What Do LLM Agents Do When Left Alone? Evidence of Spontaneous Meta-Cognitive Patterns
- AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities
- GLM-5: from Vibe Coding to Agentic Engineering
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