mlsanityData to 14 Oct 2026

From Single-Step Edit Response to Multi-Step Molecular Optimization

arXiv 2605.10035 ↗First posted 11 May 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Conditional molecular optimization aims to edit a molecule to realize a specified property shift. In practice, structurally similar molecule data is scarce, while decisions are inherently action-level: at each step, the system must select one local structural edit from a candidate set that is strictly filtered by chemical feasibility rules. This level mismatch between supervision and decision makes oracle-in-the-loop search unstable in molecular optimization. Regressing on property differences between molecule pairs improves data efficiency but relies on oracle-in-the-loop search, entangling transformation effects with global context and providing limited guidance for selecting the next feasible edit, often resorting to oracle-in-the-loop search. For this reason, we propose a response-oriented discrete edit optimization approach comprising two tightly coupled components: a single-step molecular edit response predictor (SMER) and a multi-step planner that composes local predictions into optimization trajectories via guided tree search (SMER-Opt). The approach learns a directional evaluation model over edit actions to support constraint-aware planning. It mines weakly related molecule pairs and decomposes their structural differences into minimal edit units, turning endpoint property annotations into process-level supervision and yielding reusable, transferable action primitives. A directional edit evaluator then scores feasible candidate edits by their likelihood of moving the molecule toward the desired property change, substantially reducing dependence on external evaluator queries at decision time. Code is available at https://anonymous.4open.science/r/SMER.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 56 references that are in the map. First posted on arXiv 11 May 2026.

Builds on

31 of 56 references.

References · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
  4. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 520
  5. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 392
  6. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 364
  7. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 305
  8. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 264
  9. 2018Optimization of Molecules via Deep Reinforcement Learningcited by 200
  10. 2023Geometric Latent Diffusion Models for 3D Molecule Generationcited by 186
  11. 2022Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pocketscited by 183
  12. 2020Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Editscited by 88
19 more
  1. 2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
  2. 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generationcited by 65
  3. 2023TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentialscited by 54
  4. 2021Differentiable Scaffolding Tree for Molecular Optimizationcited by 53
  5. 2024RGFN: Synthesizable Molecular Generation Using GFlowNetscited by 41
  6. 2024Genetic-guided GFlowNets for Sample Efficient Molecular Optimizationcited by 39
  7. 2024DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimizationcited by 27
  8. 2025DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discoverycited by 19
  9. 2023Generation of 3D Molecules in Pockets via Language Modelcited by 13
  10. 2024Text-guided multi-property molecular optimization with a diffusion language modelcited by 11
  11. 2025Collaborative Expert LLMs Guided Multi-Objective Molecular Optimizationcited by 11
  12. 2025Antibody Design and Optimization with Multi-scale Equivariant Graph Diffusion Models for Accurate Complex Antigen Bindingcited by 9
  13. 2023Molecule Design by Latent Prompt Transformercited by 8
  14. 2025Can Molecular Evolution Mechanism Enhance Molecular Representation?cited by 7
  15. 2025Graph Diffusion that can Insert and Deletecited by 6
  16. 2025Graph-structured Small Molecule Drug Discovery Through Deep Learning: Progress, Challenges, and Opportunitiescited by 5
  17. 2026MolEvolve: LLM-Guided Evolutionary Search for Interpretable Molecular Optimizationcited by 4
  18. 2024Regressor-free Molecule Generation to Support Drug Response Predictioncited by 3
  19. 2025Towards Efficient Molecular Property Optimization with Graph Energy Based Modelscited by 2

Built on by

Not cited yet.