More Than Can Be Said: A Benchmark and Framework for Pre-Question Scientific Ideation

TL;DR

This paper introduces InciteResearch, a multi-agent framework that transforms tacit, vague research ideas into explicit, actionable insights, and presents TF-Bench, a benchmark for evaluating such tacit-to-explicit research assistance.

Contribution

It proposes a novel multi-agent framework for making implicit research understanding explicit and introduces the first benchmark for tacit-to-explicit scientific ideation.

Findings

InciteResearch outperforms prompt-based baselines in novelty and impact.

It shifts research proposals from recombination to architectural insight.

Achieves significant improvements on TF-Bench metrics.

Abstract

AI research agents have shown strong potential in automating literature search and manuscript refinement, yet most assume a clear and actionable initial input, operating only after a research question has been made explicit. In contrast, human research often begins with tacit friction, a sense of misalignment before a question can be formed. We introduce InciteResearch, a multi-agent framework designed to make a researcher's implicit understanding explicit, inspectable, and actionable. InciteResearch decomposes the logical chain of Socratic questioning and distributes it across the entire pipeline that: (1) Elicits a structured five-dimensional researcher profile state anchored by specific friction points from vague, even domain-unrelated inputs; (2) Violates hidden assumptions by maximizing the feasibility-novelty product with enforcing a 7-stage causal derivation trace; and (3) check whether the proposed method is a Necessary consequence of the reframed insight. We further introduce TF-Bench, the first benchmark for tacit-to-explicit research assistance that distinguishes domain-related from domain-unrelated inspirations across four scientific modes. On TF-Bench, InciteResearch achieves leapfrogging gains over a prompt-based baseline (novelty/impact from 3.671/3.806 to 4.250/4.397), shifting generated proposals from recombination to architectural insight. Our work demonstrates that AI can serve as an extension of thinking itself, rather than merely automating downstream execution.