Seventeen researchers in a lab study produced proposals rated as more grounded in existing literature when using LitPivot compared to a standard text editor paired with an AI chat tool.
The system, developed by researchers at AllenAI and the University of Pennsylvania, helps writers manage the shift in research direction that occurs when reading prior work. It connects the task of developing an idea with the decision of which literature to measure it against.
Using papers retrieved through Asta Paper Finder, LitPivot organises sources around the specific section of a proposal being edited. It offers critiques supported by excerpts from selected studies and suggests revisions that the user can accept, edit, or reject.
The tool is designed for early-stage research ideation but could apply to longer writing tasks, such as drafting the introduction section of a paper.
LitPivot will be presented at UIST 2026 in Detroit. Read the paper here.
Why pivoting is hard
Research ideas evolve through engagement with the literature. Analysis of meeting notes from four completed computer science projects identified 21 literature-initiated pivots. These fell into two types: differentiating an idea from existing work to establish novelty, and aligning an idea with existing work to build on it. This project itself went through two pivots before settling on its contributions.
In a formative study, five researchers struggled to develop proposals while critically evaluating them. When a paper challenged an idea’s novelty, they wanted concrete suggestions for revision supported by prior work. LitPivot’s assessments pair literature-supported critiques with specific suggestions for revising the selected part of an idea.
How LitPivot works
A researcher starts by writing a short proposal in an editor and enabling facet highlighting. This segments the articulated idea into different facets, such as a problem, contribution, and evaluation. To check a proposed facet, the user clicks that segment in the draft.
An adjacent panel groups related papers based on the selected facet. If the evaluation facet is selected, the system groups papers by the evaluation methods they use. The researcher selects papers, requests an assessment, and reviews a suggested revision alongside excerpts supporting the critique. The literature is then reranked based on relevance to the revised facet.
LitPivot separates a research idea into its problem, proposed contribution, and evaluation plan. Each facet has its own set and relevance ranking of related literature. The system groups retrieved papers around the facet being edited, letting the user choose which ones the system should use to assess the draft.
Alongside scientific-writing environments such as Prism and agentic assistants such as Claude Code, LitPivot explores a new workflow for developing an early research idea. It involves choosing literature to assess the idea against, using that evidence to revise it, and reconsidering which papers matter as the idea changes. The system makes those steps explicit for each part of the proposal while the user controls both the draft and the evidence used to assess it.
For a problem statement, LitPivot looks for evidence that the problem exists and reasons why it matters. To assess a proposed contribution, it compares what the selected papers have already addressed with the limitations and future work they describe, looking for remaining gaps. For an evaluation plan, it checks whether the proposed tests address the research question and how similar work has been evaluated. The system then suggests a rewrite with supporting quotes attached.
Changing one facet of an idea can leave another out of date. LitPivot flags passages that may need revision, such as an evaluation plan that no longer adequately evaluates a revised contribution. Users can accept, edit, or reject suggestions and request new papers or refresh the literature ranking as their proposal develops.
Paraphrased example from one study participant.
Our findings
In the lab study, 17 researchers each developed one assigned idea with LitPivot and another with a baseline tool. Both conditions used the same collection of papers. Two domain experts, unaware of which system had been used, rated the resulting proposals on a single criterion: how well they used relevant literature to support and justify the idea. Proposals developed with LitPivot received higher ratings.
Participants in the same study also reported a stronger understanding of the surrounding literature and greater self-reported improvements in their ideas’ novelty and usefulness with LitPivot than with the baseline. Domain experts also reviewed the participants’ ideas and rated the ideas revised using LitPivot to be significantly better grounded in relevant literature.
One participant started with a proposal to generate consistent, factual synthetic medical notes. LitPivot identified consistency across multiple hospital visits as a potential gap in the selected literature. The participant reviewed abstracts and removed papers about single-visit notes. After another assessment, they narrowed the proposal to detecting contradictions across notes from multiple visits. The example shows how revising an idea and choosing the literature used to assess it can inform each other.
In a follow-up study, five researchers used LitPivot on their own ongoing projects during 30-minute sessions. Participants used LitPivot across multiple project phases, not just at the beginning. Two used it to vet new ideas against the literature, while three used it to refine the framing of more mature ideas. One researcher highlighted how seeing parallel concepts from different domains helped them reframe their contribution.
These studies suggest that LitPivot can support both early exploration and the refinement of an existing research direction.
Supporting scientific discovery
At Ai2, the team is developing AI to help researchers formulate testable ideas and examine the evidence behind them. Asta supports that effort through theory generation from published findings (Theorizer), synthesis, and hypothesis generation and testing on data (AutoDiscovery), while HARPA generates promising hypotheses informed by emerging research trends. Scideator lets researchers recombine elements of prior work into new ideas and assess their novelty, and IdeaSynth supports iterative refinement with feedback grounded in the literature.
A recent study, Old Ideas, Novel Problems, examines the limits of automated novelty evaluation, showing how small prompt changes can alter an AI judge’s verdict on the same ideas. LitPivot extends this line of work by making the choice of relevant literature part of the revision process. Researchers can change which papers they use to assess a proposal as their idea develops, then use critiques and supporting excerpts to decide how to revise it. The system connects those decisions across the proposal’s problem, contribution, and evaluation plan.
The goal is to help scientists build on existing knowledge and turn early ideas into new contributions to their fields.
What it means
Writers no longer have to switch between a document editor and a search engine to find context. The tool keeps the literature relevant to the specific sentence or paragraph being edited, ensuring that the evidence supports the claim immediately. This reduces the friction of verifying ideas against the wider body of work while the draft is still being shaped.
