arXiv cs.AI· Tao Long, Lydia B. Chilton·· 10 天前AI 评分22
SPEAR：面向人机智能体交互对齐的五项原则
SPEAR: Five Principles for Interactive Human-Agent Alignment
AI 导读
一篇立场论文提出 SPEAR，将人机对齐从部署前的优化问题重新定义为持续的交互设计问题，包含 Specification、Process、Evaluation、Adaptation、Recalibration 五个支柱，分别对应意图表达与共识、智能体何时行动/询问/推迟/暂停、用户对智能体成败的判断、智能体在反复使用中对用户的适应，以及用户对智能体信任与预期的再校准。
正文 · 原文
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).
| Comments: | 3 pages. Best Talk Award at the ACM Conference on Human-AI Complementarity and Alignment (HCOMP 2026) |
| Subjects: | Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.07204 [cs.HC] |
| (or arXiv:2610.07204v1 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07204 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tao Long [view email]
[v1]
Mon, 5 Oct 2026 18:18:40 UTC (25 KB)
来源：arXiv cs.AI · arxiv.org