SPEAR: Five Principles for Interactive Human-Agent Alignment

Abstract:Recent AI alignment work often frames alignment as a pre-deployment optimization problem: collect human feedback, learn preferences or principles, finetune the model, and deploy an aligned system. This framing has produced major progress, but it under-specifies what happens once AI systems act as agents on users' behalf in situated, long-term, and social contexts. This position paper reframes human-agent alignment as an ongoing interaction design problem. We propose SPEAR, five pillars of interactive alignment: Specification (how people express intent and establish shared understanding), Process (how agents decide when to act, ask, defer, or pause), Evaluation (how people judge whether agents succeeded), Adaptation (how agents adapt to users over repeated use), and Recalibration (how people adapt their trust, expectations, and behavior in response to agents).

3 pages. Best Talk Award at the ACM Conference on Human-AI Complementarity and Alignment (HCOMP 2026)

Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)

arXiv:2610.07204 [cs.HC]

(or arXiv:2610.07204v1 [cs.HC] for this version)

https://doi.org/10.48550/arXiv.2610.07204 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.