Interaction, Process, Infrastructure: A Unified Architecture for Human-Agent Collaboration
This addresses the problem of fragmented AI systems for researchers and AI system builders, offering a foundational architecture that is incremental in unifying existing design approaches.
The paper tackles the fragmentation of AI tools in professional knowledge work by proposing a unified layered framework that integrates interaction, process, and infrastructure, with a focus on making processes explicit and adaptable to enable sustained human-agent collaboration.
As AI tools proliferate across domains, from chatbots and copilots to emerging agents, they increasingly support professional knowledge work. Yet despite their growing capabilities, these systems remain fragmented: they assist with isolated tasks but lack the architectural scaffolding for sustained, adaptive collaboration. We propose a layered framework for human-agent systems that integrates three interdependent dimensions: interaction, process, and infrastructure. Crucially, our architecture elevates process to a primary focus by making it explicit, inspectable, and adaptable, enabling humans and agents to align with evolving goals and coordinate over time. This model clarifies limitations of current tools, unifies emerging system design approaches, and reveals new opportunities for researchers and AI system builders. By grounding intelligent behavior in structured collaboration, we reimagine human-agent collaboration not as task-specific augmentation, but as a form of coherent and aligned system for real-world work.