HAAS: A Policy-Aware Framework for Adaptive Task Allocation Between Humans and Artificial Intelligence Systems

📅 2026-05-04
📈 Citations: 0
✨ Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the challenge of dynamically, efficiently, and governably allocating tasks between humans and machines beyond static binary divisions. It proposes the HAAS framework, which integrates a rule-driven expert system with a contextual multi-armed bandit learner, leveraging a five-dimensional cognitive model and a five-level autonomy spectrum to enable adaptive task allocation in software engineering and manufacturing domains. Innovatively treating governance as a tunable design parameter, the study finds that strong governance simultaneously enhances performance and mitigates fatigue in manufacturing, whereas moderate governance becomes increasingly advantageous with accumulated experience. The research also uncovers a workload buffering effect and establishes a cross-domain, reproducible benchmark platform, offering organizations an auditable and comparable environment for simulating human–machine collaboration strategies.
📝 Abstract
Deciding how to distribute work between humans and AI systems is a central challenge in organisational design. Most approaches treat this as a binary choice, yet the operational reality is richer: humans and AI routinely share tasks or take complementary roles depending on context, fatigue, and the stakes involved. Governing that distribution -- balancing efficiency, oversight, and human capability -- remains an open problem. This paper presents Human-AI Adaptive Symbiosis (HAAS), an implemented framework for adaptive task allocation in software engineering and manufacturing. HAAS combines two coupled components: a rule-based expert system that enforces governance constraints before any learning occurs, and a contextual-bandit learner that selects among feasible collaboration modes from outcome feedback. Task-agent fit is represented through five auditable cognitive dimensions and a five-mode autonomy spectrum -- from human-only to fully autonomous -- embedded in a reproducible benchmark spanning both domains. Three empirical findings emerge. First, governance is not a binary switch but a tunable design variable: tighter constraints predictably convert autonomous AI assignments into supervised collaborations, with domain-specific costs and benefits. Second, in manufacturing, stronger governance can improve operational performance and reduce fatigue simultaneously -- a workload-buffering effect that contradicts the usual framing of governance as pure overhead. Third, no single governance setting dominates across all contexts; moderate governance becomes increasingly competitive as the learner accumulates experience within the governed action space. Together, these findings position HAAS as a pre-deployment workbench for comparing and inspecting human--AI allocation policies before organisational commitment.
Problem

Research questions and friction points this paper is trying to address.

task allocation
human-AI collaboration
governance
adaptive systems
autonomy
Innovation

Methods, ideas, or system contributions that make the work stand out.

adaptive task allocation
human-AI collaboration
governance constraints
contextual bandits
autonomy spectrum
V
Vicente Pelechanoa
Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Politècnica de València, Camino de Vera s/n, Valencia, Spain
A
Antoni Mestre
Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Politècnica de València, Camino de Vera s/n, Valencia, Spain
M
Manoli Albert
Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Politècnica de València, Camino de Vera s/n, Valencia, Spain
M
Miriam Gil
Departament d’Informàtica, Universitat de València, Valencia, Spain