Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tang, Xinye, Zhai, Haijun, Belwal, Chaitanya, Thayanithi, Vineeth, Baumann, Philip, Roy, Yogesh K
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2506.20815
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912471296507904
author Tang, Xinye
Zhai, Haijun
Belwal, Chaitanya
Thayanithi, Vineeth
Baumann, Philip
Roy, Yogesh K
author_facet Tang, Xinye
Zhai, Haijun
Belwal, Chaitanya
Thayanithi, Vineeth
Baumann, Philip
Roy, Yogesh K
contents LLM-powered applications are highly susceptible to the quality of user prompts, and crafting high-quality prompts can often be challenging especially for domain-specific applications. This paper presents a novel dynamic context-aware prompt recommendation system for domain-specific AI applications. Our solution combines contextual query analysis, retrieval-augmented knowledge grounding, hierarchical skill organization, and adaptive skill ranking to generate relevant and actionable prompt suggestions. The system leverages behavioral telemetry and a two-stage hierarchical reasoning process to dynamically select and rank relevant skills, and synthesizes prompts using both predefined and adaptive templates enhanced with few-shot learning. Experiments on real-world datasets demonstrate that our approach achieves high usefulness and relevance, as validated by both automated and expert evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20815
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dynamic Context-Aware Prompt Recommendation for Domain-Specific AI Applications
Tang, Xinye
Zhai, Haijun
Belwal, Chaitanya
Thayanithi, Vineeth
Baumann, Philip
Roy, Yogesh K
Artificial Intelligence
LLM-powered applications are highly susceptible to the quality of user prompts, and crafting high-quality prompts can often be challenging especially for domain-specific applications. This paper presents a novel dynamic context-aware prompt recommendation system for domain-specific AI applications. Our solution combines contextual query analysis, retrieval-augmented knowledge grounding, hierarchical skill organization, and adaptive skill ranking to generate relevant and actionable prompt suggestions. The system leverages behavioral telemetry and a two-stage hierarchical reasoning process to dynamically select and rank relevant skills, and synthesizes prompts using both predefined and adaptive templates enhanced with few-shot learning. Experiments on real-world datasets demonstrate that our approach achieves high usefulness and relevance, as validated by both automated and expert evaluations.
title Dynamic Context-Aware Prompt Recommendation for Domain-Specific AI Applications
topic Artificial Intelligence
url https://arxiv.org/abs/2506.20815