---
title: "KolTa: A Physics-Informed Active Learning Framework for Formulation Discovery with Limited Data"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.06394v1"
permalink: "https://feed.astralor.com/items/itm_247e71418b21e9e9900d2ed4"
published: "2026-11-04T11:59:02.000Z"
score: 60
channel: "finance"
tags: ["RAG","KolTa","Physics-Informed Active Learning","Framework","Formulation Discovery","Limited Data Finding","Finding"]
---

# KolTa: A Physics-Informed Active Learning Framework for Formulation Discovery with Limited Data

## At a glance

Finding high-performing formulations is difficult when few have been measured and experimental budgets are limited. We propose KolTa, an active learning framework that selects batches to discover the top 5% of formulati…

## Key points

- Finding high-performing formulations is difficult when few have been measured and experimental budgets are limited.
- We propose KolTa, an active learning framework that selects batches to discover the top 5% of formulations at a target temperature under a fixed query budget.
- KolTa combines a three-stage predictor of component contributions, role-conditioned interactions, and anchored temperature response with task-specific soft physics constraints.

## Full text

Finding high-performing formulations is difficult when few have been measured and experimental budgets are limited. We propose KolTa, an active learning framework that selects batches to discover the top 5% of formulations at a target temperature under a fixed query budget. KolTa combines a three-stage predictor of component contributions, role-conditioned interactions, and anchored temperature response with task-specific soft physics constraints. Its Physics-Residual-Calibrated Upper Confidence Bound (PRC-UCB) acquisition rule combines predicted utility, ensemble disagreement, and a target-temperature physics residual, with nonnegative exploration weights fitted to out-of-fold signed errors. We evaluate the framework on three measured tasks and one simulated task covering binary-mixture viscosity, drug solubility, ionic-liquid viscosity, and electrolyte conductivity. KolTa ranks first or second in mean area under the learning curve (AULC) on every task and outperforms seven of the eight comparator strategies in paired tests, winning 75 of 78 paired comparisons across tasks and seeds against those seven strategies. Across the three measured tasks, its largest gap to the best mean AULC is 0.032, compared with at least 0.056 for every comparator. On Drug, reaching 80% average recovery of the remaining targets across drugs requires an estimated median of 348 additional formulation queries, about 18% fewer than the fastest comparator. Researchers can adapt the framework to diverse formulation problems through component roles and physical constraints.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_247e71418b21e9e9900d2ed4