# Large language models as uncertainty-calibrated optimizers for experimental discovery

arXiv: https://arxiv.org/abs/2504.06265 · HTML: https://mlsanity.com/paper/2504.06265/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 124 references that are in the map.
- First posted on arXiv 8 Apr 2025.

## Builds on (most cited first, 30 of 49)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration](https://mlsanity.com/paper/1809.11165/) (2018)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [Deep Kernel Learning](https://mlsanity.com/paper/1511.02222/) (2015)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [Laplace Redux -- Effortless Bayesian Deep Learning](https://mlsanity.com/paper/2106.14806/) (2021)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://mlsanity.com/paper/2302.12813/) (2023)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [Molecular Graph Convolutions: Moving Beyond Fingerprints](https://mlsanity.com/paper/1603.00856/) (2016)
- [Scalable Variational Gaussian Process Classification](https://mlsanity.com/paper/1411.2005/) (2014)
- [LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models](https://mlsanity.com/paper/2310.08659/) (2023)
- [Learning to Plan Chemical Syntheses](https://mlsanity.com/paper/1708.04202/) (2017)
- [Bayesian Low-rank Adaptation for Large Language Models](https://mlsanity.com/paper/2308.13111/) (2023)
- [Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders](https://mlsanity.com/paper/2203.12742/) (2022)
- [AnglE-optimized Text Embeddings](https://mlsanity.com/paper/2309.12871/) (2023)
- [A Review of Large Language Models and Autonomous Agents in Chemistry](https://mlsanity.com/paper/2407.01603/) (2024)
- [Unifying Molecular and Textual Representations via Multi-task Language Modelling](https://mlsanity.com/paper/2301.12586/) (2023)

## Built on by (most cited first, 13 of 13)

- [Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch](https://mlsanity.com/paper/2608.00316/) (2026)
- [Position: Intelligent Science Laboratory Requires the Integration of Cognitive and Embodied AI](https://mlsanity.com/paper/2506.19613/) (2025)
- [DASH: Decoupled Adaptive Surrogate - Acquisition Harness for Automated Bayesian Optimization](https://mlsanity.com/paper/2608.00641/) (2026)
- [Large Language Models Transform Organic Synthesis From Reaction Prediction to Automation](https://mlsanity.com/paper/2508.05427/) (2025)
- [Sample Efficient Generative Optimization for Molecular Design](https://mlsanity.com/paper/2607.12488/) (2026)
- [Bi-semantic Chemical Embedder for Joint Representation Learning of SMILES and Natural Language](https://mlsanity.com/paper/2608.03855/) (2026)
- [Epistemic Uncertainty for Test-Time Discovery](https://mlsanity.com/paper/2605.11328/) (2026)
- [Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search](https://mlsanity.com/paper/2608.15669/) (2026)
- [Frontier LLMs are effective batch optimizers: Assessing reasoning models in continuous and discrete settings](https://mlsanity.com/paper/2609.03177/) (2026)
- [Dynamic language model representations for multi-objective reaction optimisation](https://mlsanity.com/paper/2609.11790/) (2026)
- [The average-farmer illusion in language-model simulations of agricultural decisions](https://mlsanity.com/paper/2609.15038/) (2026)
- [Bayesian Optimization with Rich Auxiliary Information via LLMs](https://mlsanity.com/paper/2609.19437/) (2026)
- [Agentic-MatriBO: Capability-Compiled Agentic Bayesian Optimization for Materials and Chemical Design](https://mlsanity.com/paper/2610.17832/) (2026)

## Abstract (arXiv)

Scientific discovery increasingly depends on efficient experimental optimization to navigate vast design spaces under time and resource constraints. Traditional approaches often require extensive domain expertise and feature engineering. While large language models, with their vast scientific knowledge, circumvent the feature engineering limitations, they lack the calibrated uncertainty estimates required for high-stakes decision making. Hence, current optimization methods force a choice between domain knowledge and reliability, with no principled approach that affords both. In this work, we show that training language models through the uncertainty-aware objectives of traditional optimization methods enables their use as reliable optimizers guided by natural language. By teaching LLMs from experimental outcomes under uncertainty, we transform their overconfidence from a fundamental limitation into a precise calibration mechanism. Applied to Buchwald-Hartwig reactions, a cornerstone of pharmaceutical synthesis, our method nearly doubles the discovery rate of high-yielding reaction conditions, from 24% to 43% in 50 experimental iterations starting from 10 unsuccessful conditions. Across 19 diverse optimization problems spanning organic synthesis, materials science and catalysis, process chemistry, and molecular design, our approach ranks first on average, establishing a new paradigm for reliable, uncertainty-guided optimization with LLMs. Our approach can accelerate discovery by lowering the barrier to using powerful optimization methods, replacing the need for domain-specific feature engineering with more accessible natural language interfaces. These findings highlight that ensuring reliability through principled uncertainty quantification is critical for realizing the full potential of AI-guided experimentation.