Scaling Empowered Agents
cs.AI, cs.LG
Submitted: 2026-10-09
Updated: 2026-10-09
Comments: 30 pages, 13 figures
Project page: https://empowerment-geometry.github.io/scaling-empowerment
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- What Is Worth Representing? Representational Empowerment for Continual Model Construction
- BuilderBench: The Building Blocks of Intelligent Agents
- The Geometry of Empowerment
- Unsupervised Real-Time Control through Variational Empowerment
- Intrinsically-Motivated Humans and Agents in Open-World Exploration
- Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning
- Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL
- Proximal Policy Optimization Algorithms
- Estimating the Empowerment of Language Model Agents
- Representation Learning with Contrastive Predictive Coding
- When Assisting One Disempowers Another
- Empowerment Gain and Causal Model Construction: Children and adults are sensitive to controllability and variability in their causal interventions
- Efficient Empowerment Estimation for Unsupervised Stabilization
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