Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search

Hugging Face Daily Papers Papers
large-discovery-model generative-model bayesian-non-parametric uncertainty-aware-search molecules proteins scientific-discovery

Summary

The paper introduces Large Discovery Model (LDM), a recurrent architecture that couples generative models with Bayesian non-parametric surrogates to guide uncertainty-aware search in scientific domains like molecules and proteins, achieving significant performance gains over existing methods.

Scientific discovery often involves optimising expensive-to-evaluate objectives over vast, structured, and open-ended hypothesis spaces, such as molecules, protein sequences, and computer programs. Generative models such as large language models (LLMs) provide expressive priors over such spaces, but their likelihoods and self-assessments are unreliable proxies for the objectives and calibrated epistemic uncertainty, especially for novel candidates outside the observed data distribution. We introduce the Large Discovery Model (LDM), an empirically grounded recurrent architecture that couples a generative model with a Bayesian non-parametric reward surrogate model. The generative model proposes and refines candidate designs, while the surrogate predicts their performance and quantifies uncertainty, yielding an uncertainty-aware value that guides candidate generation, refinement, and selection. The discovery memory and the surrogate model are continually updated as each new experimental observation arrives. We evaluate LDM on three scenarios spanning different design modalities and objectives, including neural-network training, antibody design, and molecular optimisation. Compared to LLM-only reflection or traditional statistical search across these domains, LDM achieves a 2.4times greater reduction in validation BPB, an 18.2% relative decrease in binding energy, and more than 60% relative gains in molecular multi-objective performance. These results suggests that LDM could serve as a general-purpose discovery engine for effective search over open-ended hypothesis spaces.
Original Article
View Cached Full Text

Cached at: 08/18/26, 11:52 AM

Paper page - Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search

Source: https://huggingface.co/papers/2608.15669 Authors:

,

,

,

,

,

,

,

,

,

,

Abstract

A recurrent Large Discovery Model couples generative proposal with a Bayesian non-parametric reward surrogate to guide uncertainty-aware search across molecules, proteins, and programs.

Scientific discovery often involves optimising expensive-to-evaluate objectives over vast, structured, and open-ended hypothesis spaces, such as molecules, protein sequences, and computer programs.Generative models such as large language models (LLMs) provide expressive priors over such spaces, but their likelihoods and self-assessments are unreliable proxies for the objectives and calibrated epistemic uncertainty, especially for novel candidates outside the observed data distribution. We introduce theLarge Discovery Model(LDM), an empirically groundedrecurrent architecturethat couples agenerative modelwith aBayesian non-parametric reward surrogatemodel. Thegenerative modelproposes and refines candidate designs, while the surrogate predicts their performance and quantifies uncertainty, yielding anuncertainty-aware valuethat guides candidate generation, refinement, and selection. Thediscovery memoryand the surrogate model are continually updated as each new experimental observation arrives. We evaluate LDM on three scenarios spanning different design modalities and objectives, including neural-network training,antibody design, andmolecular optimisation. Compared to LLM-only reflection or traditional statistical search across these domains, LDM achieves a 2.4times greater reduction in validation BPB, an 18.2% relative decrease in binding energy, and more than 60% relative gains in molecular multi-objective performance. These results suggests that LDM could serve as a general-purpose discovery engine for effective search over open-ended hypothesis spaces.

View arXiv pageView PDFProject pageGitHub5Add to collection

Get this paper in your agent:

hf papers read 2608\.15669

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.15669 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.15669 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.15669 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Automatic Ordinary Differential Equations Discovery For Biological Systems Using Large Language Model Powered Agentic System

arXiv cs.AI

This paper introduces MEDA, an LLM- and symbolic regression-powered agentic framework for automatically discovering ordinary differential equation (ODE) models of biological dynamical systems. It retrieves background knowledge, proposes candidate ODEs, and evaluates them across canonical model retrieval, extrapolation, and open-ended discovery tasks, demonstrating strong structural recovery and biologically plausible models.