# Deciphering Scientific Reasoning Steps from Outcome Data for Molecule Optimization

arXiv: https://arxiv.org/abs/2603.20262 · HTML: https://mlsanity.com/paper/2603.20262/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 25 of its 98 references that are in the map.
- First posted on arXiv 13 Mar 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 25 of 25)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [MolGAN: An implicit generative model for small molecular graphs](https://mlsanity.com/paper/1805.11973/) (2018)
- [Training a Scientific Reasoning Model for Chemistry](https://mlsanity.com/paper/2506.17238/) (2025)
- [GenMol: A Drug Discovery Generalist with Discrete Diffusion](https://mlsanity.com/paper/2501.06158/) (2025)
- [Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations](https://mlsanity.com/paper/2505.21318/) (2025)
- [BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model](https://mlsanity.com/paper/2505.23579/) (2025)
- [Nature Language Model: Deciphering the Language of Nature for Scientific Discovery](https://mlsanity.com/paper/2502.07527/) (2025)
- [ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback](https://mlsanity.com/paper/2305.18090/) (2023)
- [PharmAgents: Building a Virtual Pharma with Large Language Model Agents](https://mlsanity.com/paper/2503.22164/) (2025)
- [ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge](https://mlsanity.com/paper/2507.21990/) (2025)
- [Generative Artificial Intelligence for Navigating Synthesizable Chemical Space](https://mlsanity.com/paper/2410.03494/) (2024)
- [Chem-R: Learning to Reason as a Chemist](https://mlsanity.com/paper/2510.16880/) (2025)
- [MT-Mol:Multi Agent System with Tool-based Reasoning for Molecular Optimization](https://mlsanity.com/paper/2505.20820/) (2025)
- [Collaborative Expert LLMs Guided Multi-Objective Molecular Optimization](https://mlsanity.com/paper/2503.03503/) (2025)
- [SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines](https://mlsanity.com/paper/2509.21320/) (2025)
- [POLO: Preference-Guided Multi-Turn Reinforcement Learning for Lead Optimization](https://mlsanity.com/paper/2509.21737/) (2025)
- [Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications](https://mlsanity.com/paper/2508.00669/) (2025)
- [mCLM: A Modular Chemical Language Model that Generates Functional and Makeable Molecules](https://mlsanity.com/paper/2505.12565/) (2025)
- [Large Language Models for Controllable Multi-property Multi-objective Molecule Optimization](https://mlsanity.com/paper/2505.23987/) (2025)
- [ChemAU: Harness the Reasoning of LLMs in Chemical Research with Adaptive Uncertainty Estimation](https://mlsanity.com/paper/2506.01116/) (2025)
- [Conditional Chemical Language Models are Versatile Tools in Drug Discovery](https://mlsanity.com/paper/2507.10273/) (2025)
- [Coder as Editor: Code-driven Interpretable Molecular Optimization](https://mlsanity.com/paper/2510.14455/) (2025)

## Abstract (arXiv)

Emerging reasoning models hold promise for automating scientific discovery. However, their training is hindered by a critical supervision gap: experimental outcomes are abundant, whereas intermediate reasoning steps are rarely documented at scale. To bridge this gap, we propose DESRO, a framework for deciphering scientific reasoning from outcomes. By analyzing shared patterns and key differences within grouped data, a large language model (LLM) can recover the underlying logic. We instantiate this framework in molecule optimization, a pivotal stage in drug discovery that traditionally relies on the iterative reasoning of medicinal chemists. Across 2.3 million molecular property records, our framework infers optimization rationales by grouping molecules with shared fragments, then using an LLM to analyze how structural variations correlate with property differences. Based on the derived data, we train a model that conducts molecule optimization through an interpretable reasoning process. DESRO achieves the highest success rates on 15 out of 18 tasks, spanning both single- and multi-property optimization of bioactivity and ADMET properties. The reasoning process enables robust generalization to out-of-distribution scenarios, including novel property combinations, unseen biological targets, and unseen properties defined solely by natural language descriptions. In retrospective case studies under strict temporal splits, the model autonomously reconstructs expert-level lead optimization trajectories. Additionally, our framework extends beyond molecule optimization to reaction ligand selection. Our results establish deciphering reasoning steps from outcome data as a viable paradigm for enabling scientific reasoning, providing a scalable approach to accelerate scientific discovery.