AIHCLGApr 4, 2024

Designing for Human-Agent Alignment: Understanding what humans want from their agents

arXiv:2404.04289v143 citationsh-index: 4CHI Extended Abstracts
Originality Synthesis-oriented
AI Analysis

This addresses the challenge for designers and users in ensuring agents perform tasks as intended, though it is incremental by building on existing alignment research.

The paper tackles the problem of aligning human expectations with autonomous agents by identifying six key dimensions for alignment through a qualitative study on a negotiation task, expanding previous work on human-AI interaction.

Our ability to build autonomous agents that leverage Generative AI continues to increase by the day. As builders and users of such agents it is unclear what parameters we need to align on before the agents start performing tasks on our behalf. To discover these parameters, we ran a qualitative empirical research study about designing agents that can negotiate during a fictional yet relatable task of selling a camera online. We found that for an agent to perform the task successfully, humans/users and agents need to align over 6 dimensions: 1) Knowledge Schema Alignment 2) Autonomy and Agency Alignment 3) Operational Alignment and Training 4) Reputational Heuristics Alignment 5) Ethics Alignment and 6) Human Engagement Alignment. These empirical findings expand previous work related to process and specification alignment and the need for values and safety in Human-AI interactions. Subsequently we discuss three design directions for designers who are imagining a world filled with Human-Agent collaborations.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes