Proximal State Nudging: A Shared Autonomy Algorithm to Combat Skill Atrophy from AI Assistance
By
[Submitted on 19 May 2026]
Summary
This paper introduces Proximal State Nudging (PSN), a shared autonomy algorithm designed to reduce skill atrophy — the gradual decline of human capability caused by over-reliance on AI assistance. PSN jointly optimizes for both skill development and task performance by nudging users toward states estimated to be most learnable. The algorithm outperformed existing shared autonomy baselines in simulated LunarLander environments, and in human subject studies (n=60) using the CARLA driving simulator, PSN produced up to 7x larger gains in unassisted skill compared to standard blended shared autonomy, while incurring 50% fewer collisions than unassisted self-practice.
Source
Twitter / XProximal State Nudging: A Shared Autonomy Algorithm to Combat Skill Atrophy from AI Assistancearxiv.orgKey quotes
· 3 pulledSkill atrophy, the gradual decline of human capability under AI assistance, poses a safety risk in shared-control of semi-autonomous systems, where operators may be unable to distinguish their own inputs from autonomous corrections.
We propose Proximal State Nudging (PSN), a shared autonomy algorithm that jointly optimizes for skill development and task performance by nudging users toward states estimated to be most learnable.
PSN produces up to 7x larger gains in unassisted skill than standard blended shared autonomy, while incurring 50% fewer collisions than unassisted self-practice.
You might also wanna read
DILLO: A Language-Based World Model for Proactive Agent Steering Without Visual Simulation
This paper introduces DILLO (DIstiLLed Language-ActiOn World Model), a proactive agent steering framework that replaces slow visual simulati
arxiv.org·16d ago
Using Curriculum Learning and PufferLib to Train Superhuman AI Agents for 2048 and Tetris
The article describes using PufferLib, a reinforcement learning framework, to train gaming agents that achieve superhuman performance in 204
LifeSkill: A Reinforcement Learning Framework for Online Lifelong Learning in LLM Agents
This paper introduces LifeSkill, a two-stage reinforcement learning framework for online lifelong learning in Large Language Model (LLM) age
arxiv.org·14d ago
New Benchmark Reveals High Rates of Outcome-Driven Constraint Violations in Autonomous AI Agents
Researchers introduce a new benchmark for evaluating autonomous AI agents' safety, specifically focusing on outcome-driven constraint violat
arxiv.org·4mo ago
Multi-Agent Reinforcement Learning Reduces Drone Racing Collisions by 50% While Achieving Champion-Level Performance
This article presents research demonstrating that multi-agent reinforcement learning (MARL) enables superhuman performance in shared, dynami
Stabilizing LLM Behavior: The Assistant Axis Approach to Preventing Harmful Persona Drift
The article discusses how large language models (LLMs) develop character personas during training and introduces the concept of an "Assistan
anthropic.com·19d agoStabilizing LLM Behavior: The Assistant Axis Approach to Preventing Harmful Persona Drift
The article discusses how large language models (LLMs) develop character personas during training and introduces the concept of an "Assistan
anthropic.com·19d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.