Omakase: proactive assistance with actionable suggestions for evolving scientific research projects

2026-04-10

AI Summary

Current AI research assistants struggle to comprehend the long-term contextual evolution of scientific projects and thus fail to proactively identify users’ latent needs or deliver actionable recommendations. This work proposes the first proactive AI assistance framework tailored for extended research endeavors, which automatically infers timely queries by monitoring project documents, invokes deep research systems accordingly, and distills lengthy reports into concise, stage-relevant, and executable suggestions. Integrating context-aware modeling, automated query generation, and contextual summarization, the approach yields an iterative research assistant prototype. User evaluations demonstrate that the generated queries are both timely and effective, and that the distilled recommendations substantially outperform the original reports in terms of actionability.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

As AI agents become increasingly capable of complex knowledge tasks, the lack of context limits their capability to proactively reason about a user's latent needs throughout a long evolving project. In scientific research, many researchers still manually query a deep research system and compress their rich project contexts into short, targeted queries. Further, a deep research system produces exhaustive reports, making it difficult to identify concrete actions. To explore the opportunities of research assistants that are proactive throughout a research project, we conducted several studies (N=42) with a technology probe and an iterative prototype. The latest iteration of our system, Omakase, is a research assistant that monitors a user's project documents to infer timely queries to a deep research system. Omakase then distills long reports into suggestions contextualized to their evolving projects. Our evaluations showed that participants found the generated queries to be useful and timely, and rated Omakase's suggestions as significantly more actionable than the original reports.

Problem

• proactive assistance
• scientific research
• actionable suggestions
• project context
• AI research assistant

Innovation

• proactive AI assistant
• context-aware querying
• actionable suggestions
• scientific research support
• project evolution tracking