# CARE: Context-Aware Ranking Evolution with Executable Scoring Programs for Budgeted Reaction Optimization

arXiv: https://arxiv.org/abs/2606.14581 · HTML: https://mlsanity.com/paper/2606.14581/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 51 references that are in the map.
- First posted on arXiv 12 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Unexpected Improvements to Expected Improvement for Bayesian Optimization](https://mlsanity.com/paper/2310.20708/) (2023)
- [Large Language Models to Enhance Bayesian Optimization](https://mlsanity.com/paper/2402.03921/) (2024)
- [HSEvo: Elevating Automatic Heuristic Design with Diversity-Driven Harmony Search and Genetic Algorithm Using LLMs](https://mlsanity.com/paper/2412.14995/) (2024)
- [A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?](https://mlsanity.com/paper/2402.05015/) (2024)
- [Gryffin: An algorithm for Bayesian optimization of categorical variables informed by expert knowledge](https://mlsanity.com/paper/2003.12127/) (2020)
- [Bayesian Optimization of Catalysis With In-Context Learning](https://mlsanity.com/paper/2304.05341/) (2023)
- [Language-Based Bayesian Optimization Research Assistant (BORA)](https://mlsanity.com/paper/2501.16224/) (2025)
- [BoFire: Bayesian Optimization Framework Intended for Real Experiments](https://mlsanity.com/paper/2408.05040/) (2024)
- [Distilling and exploiting quantitative insights from Large Language Models for enhanced Bayesian optimization of chemical reactions](https://mlsanity.com/paper/2504.08874/) (2025)

## Built on by (most cited first, 1 of 1)

- [From Checker to Forecaster: Code-Owned Evaluation of Model-Generated Strategic Routes Under Delayed Ground Truth](https://mlsanity.com/paper/2607.10972/) (2026)

## Abstract (arXiv)

High-throughput experimentation can evaluate many reaction conditions, yet combinatorial condition spaces still exceed the available experiment budget. This makes experiment selection a sequential decision problem: each new condition must be chosen from limited observations before its outcome is known. LLMs can express task-specific selection logic. A direct recommendation, however, is neither a persistent executable object that can be validated and revised nor an independently auditable decision rule. We introduce CARE, a reference-conditioned controller that separates program synthesis from experiment selection. An LLM writes an executable scoring program that ranks the remaining conditions, while a non-LLM reference policy supplies a numerical candidate and support summary. CARE forms an optional alternative from the program, applies a reference-conditioned intervention gate to compare it with the reference, and records the decision before the selected outcome is revealed. Each new outcome updates controller state and can trigger retention, revision, or regeneration of the active program. This outcome-guided program evolution changes the scoring logic without updating the LLM parameters. In matched offline replay with 30 seeds on eight reaction-optimization tasks, CARE attains the lowest normalized regret, the highest normalized best-so-far AUC, and the highest Top-1% Success@15 among the evaluated methods. These results support using a scoring program written by an LLM as one component of a reference-conditioned optimizer rather than as a standalone experiment selector.