Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors
cs.AI, cs.CY
Submitted: 2026-05-07
Updated: 2026-11-10
Code: https://github.com/agent-infra/sandbox
Project page: https://instrumentalchoices.com
Terminology
Sources
- Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?
- Liars' Bench: Evaluating Lie Detectors for Language Models
- A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-case Prototypes
- Large Language Models Often Know When They Are Being Evaluated
- Large Language Models can Strategically Deceive their Users when Put Under Pressure
- Difficulties with Evaluating a Deception Detector for AIs
- Will artificial agents pursue power by default?
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents