# GP-MoLFormer-Sim: Test Time Molecular Optimization through Contextual Similarity Guidance

arXiv: https://arxiv.org/abs/2506.05628 · HTML: https://mlsanity.com/paper/2506.05628/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Builds on (most cited first, 22 of 22)

- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation](https://mlsanity.com/paper/2106.04399/) (2021)
- [GFlowNet Foundations](https://mlsanity.com/paper/2111.09266/) (2021)
- [Molecular De Novo Design through Deep Reinforcement Learning](https://mlsanity.com/paper/1704.07555/) (2017)
- [Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development](https://mlsanity.com/paper/2102.09548/) (2021)
- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [Optimization of Molecules via Deep Reinforcement Learning](https://mlsanity.com/paper/1810.08678/) (2018)
- [Sample Efficiency Matters: A Benchmark for Practical Molecular Optimization](https://mlsanity.com/paper/2206.12411/) (2022)
- [Exploring Chemical Space with Score-based Out-of-distribution Generation](https://mlsanity.com/paper/2206.07632/) (2022)
- [Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model](https://mlsanity.com/paper/2310.09520/) (2023)
- [Efficient Evolutionary Search Over Chemical Space with Large Language Models](https://mlsanity.com/paper/2406.16976/) (2024)
- [DrugAssist: A Large Language Model for Molecule Optimization](https://mlsanity.com/paper/2401.10334/) (2023)
- [Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning](https://mlsanity.com/paper/2004.12485/) (2020)
- [BOSS: Bayesian Optimization over String Spaces](https://mlsanity.com/paper/2010.00979/) (2020)
- [Guiding Deep Molecular Optimization with Genetic Exploration](https://mlsanity.com/paper/2007.04897/) (2020)
- [Optimizing Molecules using Efficient Queries from Property Evaluations](https://mlsanity.com/paper/2011.01921/) (2020)
- [Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design](https://mlsanity.com/paper/2110.06389/) (2021)
- [Genetic-guided GFlowNets for Sample Efficient Molecular Optimization](https://mlsanity.com/paper/2402.05961/) (2024)
- [Application of generative autoencoder in de novo molecular design](https://mlsanity.com/paper/1711.07839/) (2017)
- [Drug Discovery with Dynamic Goal-aware Fragments](https://mlsanity.com/paper/2310.00841/) (2023)
- [Large Language Models can be Strong Self-Detoxifiers](https://mlsanity.com/paper/2410.03818/) (2024)

## Built on by (most cited first, 2 of 2)

- [MolLIBRA: Genetic Molecular Optimization with Multi-Fingerprint Surrogates and Text-Molecule Aligned Critic](https://mlsanity.com/paper/2602.07002/) (2026)
- [Frontier LLMs are effective batch optimizers: Assessing reasoning models in continuous and discrete settings](https://mlsanity.com/paper/2609.03177/) (2026)

## Abstract (arXiv)

The ability to design molecules while preserving similarity to a target molecule and/or property is crucial for various applications in drug discovery, chemical design, and biology. We introduce in this paper an efficient training-free method for navigating and sampling from the molecular space with a generative Chemical Language Model (CLM), while using the molecular similarity to the target as a guide. Our method leverages the contextual representations learned from the CLM itself to estimate the molecular similarity, which is then used to adjust the autoregressive sampling strategy of the CLM. At each step of the decoding process, the method tracks the distance of the current generations from the target and updates the logits to encourage the preservation of similarity in generations. We implement the method using a recently proposed ~47M parameter SMILES-based CLM, GP-MoLFormer, and therefore refer to the method as GP-MoLFormer-Sim, which enables a test-time update of the deep generative policy to reflect the contextual similarity to a set of guide molecules. The method is further integrated into a genetic algorithm (GA) and tested on a set of standard molecular optimization benchmarks involving property optimization, molecular rediscovery, and structure-based drug design. Results show that, GP-MoLFormer-Sim, combined with GA (GP-MoLFormer-Sim+GA) outperforms existing training-free baseline methods, when the oracle remains black-box. The findings in this work are a step forward in understanding and guiding the generative mechanisms of CLMs.