Towards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMs
cs.AI
Submitted: 2026-04-19
Updated: 2026-10-07
Terminology
Sources
- Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
- 'Indifference' methods for managing agent rewards
- Gemma 4 Technical Report
- Alignment faking in large language models
- The Off-Switch Game
- Corrigibility with Utility Preservation
- Power-seeking can be probable and predictive for trained agents
- Frontier Models are Capable of In-context Scheming
- gpt-oss-120b & gpt-oss-20b Model Card
- Frontier AI systems have surpassed the self-replicating red line
- Proximal Policy Optimization Algorithms
- Towards Shutdownable Agents via Stochastic Choice
- A Game-Theoretic Analysis of the Off-Switch Game
- OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
- Qwen3 Technical Report
- WebArena: A Realistic Web Environment for Building Autonomous 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
- 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