# Training-Free Active Learning Framework in Materials Science with Large Language Models

arXiv: https://arxiv.org/abs/2511.19730 · HTML: https://mlsanity.com/paper/2511.19730/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 59 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Builds on (most cited first, 26 of 26)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [Large Language Models to Enhance Bayesian Optimization](https://mlsanity.com/paper/2402.03921/) (2024)
- [Emergent autonomous scientific research capabilities of large language models](https://mlsanity.com/paper/2304.05332/) (2023)
- [Cold-start Active Learning through Self-supervised Language Modeling](https://mlsanity.com/paper/2010.09535/) (2020)
- [Context Length Alone Hurts LLM Performance Despite Perfect Retrieval](https://mlsanity.com/paper/2510.05381/) (2025)
- [NoLiMa: Long-Context Evaluation Beyond Literal Matching](https://mlsanity.com/paper/2502.05167/) (2025)
- [A Review of Large Language Models and Autonomous Agents in Chemistry](https://mlsanity.com/paper/2407.01603/) (2024)
- [Practical Obstacles to Deploying Active Learning](https://mlsanity.com/paper/1807.04801/) (2018)
- [Benchmarking the Performance of Bayesian Optimization across Multiple Experimental Materials Science Domains](https://mlsanity.com/paper/2106.01309/) (2021)
- [OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery](https://mlsanity.com/paper/2503.17604/) (2025)
- [The Order Effect: Investigating Prompt Sensitivity to Input Order in LLMs](https://mlsanity.com/paper/2502.04134/) (2025)
- [From Selection to Generation: A Survey of LLM-based Active Learning](https://mlsanity.com/paper/2502.11767/) (2025)
- [ActiveLLM: Large Language Model-based Active Learning for Textual Few-Shot Scenarios](https://mlsanity.com/paper/2405.10808/) (2024)
- [Language-Based Bayesian Optimization Research Assistant (BORA)](https://mlsanity.com/paper/2501.16224/) (2025)
- [Benchmarking Active Learning Strategies for Materials Optimization and Discovery](https://mlsanity.com/paper/2204.05838/) (2022)
- [Integrating Chemistry Knowledge in Large Language Models via Prompt Engineering](https://mlsanity.com/paper/2404.14467/) (2024)
- [Evaluating the Performance and Robustness of LLMs in Materials Science Q&A and Property Predictions](https://mlsanity.com/paper/2409.14572/) (2024)
- [DARWIN 1.5: Large Language Models as Materials Science Adapted Learners](https://mlsanity.com/paper/2412.11970/) (2024)
- [Are Longer Prompts Always Better? Prompt Selection in Large Language Models for Recommendation Systems](https://mlsanity.com/paper/2412.14454/) (2024)
- [Active Learning via Classifier Impact and Greedy Selection for Interactive Image Retrieval](https://mlsanity.com/paper/2412.02310/) (2024)
- [Benchmarking Self-Driving Labs](https://mlsanity.com/paper/2508.06642/) (2025)
- [Can Large Language Models Improve SE Active Learning via Warm-Starts?](https://mlsanity.com/paper/2501.00125/) (2024)
- [Developing and Validating a High-Throughput Robotic System for the Accelerated Development of Porous Membranes](https://mlsanity.com/paper/2508.10973/) (2025)

## Built on by (most cited first, 3 of 3)

- [Perspective: Towards sustainable exploration of chemical spaces with machine learning](https://mlsanity.com/paper/2604.00069/) (2026)
- [Building informative materials datasets beyond targeted objectives](https://mlsanity.com/paper/2605.05104/) (2026)
- [LLMs as Acquisition Policies for Finite-Pool Materials Optimization: A Controlled Study](https://mlsanity.com/paper/2608.19790/) (2026)

## Abstract (arXiv)

Active learning (AL) accelerates scientific discovery by prioritizing the most informative experiments, but traditional machine learning (ML) models used in AL suffer from cold-start limitations and domain-specific feature engineering, restricting their generalizability. Large language models (LLMs) offer a new paradigm by leveraging their pretrained knowledge and universal token-based representations to propose experiments directly from text-based descriptions. Here, we introduce an LLM-based active learning framework (LLM-AL) that operates in an iterative few-shot setting and benchmark it against conventional ML models across four diverse materials science datasets. We explored two prompting strategies: one using concise numerical inputs suited for datasets with more compositional and structured features, and another using expanded descriptive text suited for datasets with more experimental and procedural features to provide additional context. Across all datasets, LLM-AL could reduce the number of experiments needed to reach top-performing candidates by over 70% and consistently outperformed traditional ML models. We found that LLM-AL performs broader and more exploratory searches while still reaching the optima with fewer iterations. We further examined the stability boundaries of LLM-AL given the inherent non-determinism of LLMs and found its performance to be broadly consistent across runs, within the variability range typically observed for traditional ML approaches. These results demonstrate that LLM-AL can serve as a generalizable alternative to conventional AL pipelines for more efficient and interpretable experiment selection and potential LLM-driven autonomous discovery.