Prompt Adaptation as a Dynamic Complement in Generative AI Systems

• 成果类型: Article; Early Access
• 署名作者: Jahani, Eaman; Manning, Benjamin S.; Zhang, Joe; TuYe, Hong-Yi; Alsobay, Mohammed; Nicolaides, Christos; Suri, Siddharth; Holtz, David
• 署名单位: University System of Maryland; University of Maryland College Park; Massachusetts Institute of Technology (MIT); Massachusetts Institute of Technology (MIT); Stanford University; Microsoft; University of Cyprus; Microsoft; Columbia University
• 刊物名称: INFORMATION SYSTEMS RESEARCH
• ISSN/ISSBN: 1047-7047; 1526-5536
• DOI: 10.1287/isre.2025.2029
• 发表日期: 2026-04-30
• 关键词: generative AI; prompt engineering; prompt adaptation; human-AI interaction; complementary skills; information-technology; PERSPECTIVE; INNOVATION

摘要

As generative AI systems rapidly improve, a key question emerges: how do users adapt to these changes, and when does such adaptation matter for realizing performance gains? This paper studies prompt adaptation-how users adjust their inputs in response to evolving model behavior-using a common experimental design applied to two preregistered tasks with 3,750 total participants who submitted nearly 37,000 prompts. We show that the importance of prompt adaptation depends critically on task structure. In a task with fixed evaluation criteria and an unambiguous goal, user prompt adaptation accounts for roughly half of the performance gains from a model upgrade. In contrast, in an open-ended creative task where the space of acceptable outputs is effectively unbounded and quality is subjective, performance improvements are driven primarily by model capability; prompt adaptation plays a limited role. We further show that automated prompt rewriting cannot generally substitute for human adaptation: when aligned with task objectives, it can modestly improve performance, but when misaligned, it can actively undermine the gains from model improvements. Together, these findings position prompt adaptation as a dynamic complement whose importance depends on task structure and system design, and suggest that without it, a substantial share of the economic value created by advances in generative models may go unrealized.