Saved in:
Bibliographic Details
Main Authors: Zhang, Zheng, Nguyen, Cuong C., Rosewarne, David, Wells, Kevin, Carneiro, Gustavo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.00904
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917383599292416
author Zhang, Zheng
Nguyen, Cuong C.
Rosewarne, David
Wells, Kevin
Carneiro, Gustavo
author_facet Zhang, Zheng
Nguyen, Cuong C.
Rosewarne, David
Wells, Kevin
Carneiro, Gustavo
contents Learning to defer (L2D) enables human-AI cooperation by deciding when an AI system should act autonomously or defer to a human expert. Existing L2D methods, however, assume static human performance, contradicting well-established findings on fatigue-induced degradation. We propose Fatigue-Aware Learning to Defer via Constrained Optimisation (FALCON), which explicitly models workload-varying human performance using psychologically grounded fatigue curves. FALCON formulates L2D as a Constrained Markov Decision Process (CMDP) whose state includes both task features and cumulative human workload, and optimises accuracy under human-AI cooperation budgets via PPO-Lagrangian training. We further introduce FA-L2D, a benchmark that systematically varies fatigue dynamics from near-static to rapidly degrading regimes. Experiments across multiple datasets show that FALCON consistently outperforms state-of-the-art L2D methods across coverage levels, generalises zero-shot to unseen experts with different fatigue patterns, and demonstrates the advantage of adaptive human-AI collaboration over AI-only or human-only decision-making when coverage lies strictly between 0 and 1.
format Preprint
id arxiv_https___arxiv_org_abs_2604_00904
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Fatigue-Aware Learning to Defer via Constrained Optimisation
Zhang, Zheng
Nguyen, Cuong C.
Rosewarne, David
Wells, Kevin
Carneiro, Gustavo
Machine Learning
Learning to defer (L2D) enables human-AI cooperation by deciding when an AI system should act autonomously or defer to a human expert. Existing L2D methods, however, assume static human performance, contradicting well-established findings on fatigue-induced degradation. We propose Fatigue-Aware Learning to Defer via Constrained Optimisation (FALCON), which explicitly models workload-varying human performance using psychologically grounded fatigue curves. FALCON formulates L2D as a Constrained Markov Decision Process (CMDP) whose state includes both task features and cumulative human workload, and optimises accuracy under human-AI cooperation budgets via PPO-Lagrangian training. We further introduce FA-L2D, a benchmark that systematically varies fatigue dynamics from near-static to rapidly degrading regimes. Experiments across multiple datasets show that FALCON consistently outperforms state-of-the-art L2D methods across coverage levels, generalises zero-shot to unseen experts with different fatigue patterns, and demonstrates the advantage of adaptive human-AI collaboration over AI-only or human-only decision-making when coverage lies strictly between 0 and 1.
title Fatigue-Aware Learning to Defer via Constrained Optimisation
topic Machine Learning
url https://arxiv.org/abs/2604.00904