AI Paper Atlas

Research map / Large language models / Agents, code and math

SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?

Udari Madhushani Sehwag, Elaine Lau, Haniyeh Ehsani Oskouie, Shayan Shabihi, Erich Liang, Andrea Sarai Echeverria Toledo, Guillermo A. Mangialardi, Sergio Fonrouge, Ed-Yeremai Hernandez-Cardona, Paula Vergara, Utkarsh Tyagi, Chen Bo Calvin Zhang and 5 more

ICML 2026 · Large language models › Agents, code and math · approach: LLMs for scientific discovery · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
provide expert-curated background knowledge in context (ablation)all 15 LLMs · SciPredictaccuracy: about +3% on average (1.2 to 5.8% by model)Improved
let the model generate its own background knowledge before answering (ablation)LLMs · SciPredictaccuracyHurt
add self-generated background to expert background (SABK) (ablation)LLMs with expert BK · SciPredictaccuracyNo clear effect
keep facts the model already knows in the background context (full vs filtered BK) (ablation)LLMs · SciPredictaccuracyImproved
convert MCQ questions to free-form by removing options (ablation)LLMs · SciPredict MCQ subsetaccuracyHurt
background knowledge effect on model confidence (ablation)LLMs · SciPredictself-reported confidenceNo clear effect
use model self-reported confidence/feasibility to select tasksLLMs · SciPredictaccuracy vs self-reported level: about 20% regardless of ratingNo clear effect
use human-expert-rated feasibility to select tasksHuman experts · SciPredictaccuracy: about 5% -> about 80%Improved
change decoding temperature 0.0 to 1.0 and top-p (ablation)LLM predictions · SciPredictaccuracyNo clear effect
switch LLM judge from Gemini-3-Pro to GPT-5.2 (ablation)free-form evaluation · SciPredict free-formaccuracyNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy