# MolLingo: Molecule-Native Representations for LLM-Powered Scientific Agents

arXiv: https://arxiv.org/abs/2605.27853 · HTML: https://mlsanity.com/paper/2605.27853/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 16 of its 45 references that are in the map.
- First posted on arXiv 27 May 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 16 of 16)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development](https://mlsanity.com/paper/2102.09548/) (2021)
- [What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks](https://mlsanity.com/paper/2305.18365/) (2023)
- [DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual Screening](https://mlsanity.com/paper/2310.06367/) (2023)
- [PharmAgents: Building a Virtual Pharma with Large Language Model Agents](https://mlsanity.com/paper/2503.22164/) (2025)
- [GraphBPE: Molecular Graphs Meet Byte-Pair Encoding](https://mlsanity.com/paper/2407.19039/) (2024)
- [Accelerating Drug Discovery Through Agentic AI: A Multi-Agent Approach to Laboratory Automation in the DMTA Cycle](https://mlsanity.com/paper/2507.09023/) (2025)
- [Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning](https://mlsanity.com/paper/2603.05900/) (2026)
- [Target Specific De Novo Design of Drug Candidate Molecules with Graph Transformer-based Generative Adversarial Networks](https://mlsanity.com/paper/2302.07868/) (2023)
- [MADD: Multi-Agent Drug Discovery Orchestra](https://mlsanity.com/paper/2511.08217/) (2025)
- [FragmentNet: Adaptive Graph Fragmentation for Graph-to-Sequence Molecular Representation Learning](https://mlsanity.com/paper/2502.01184/) (2025)
- [Toward Closed-loop Molecular Discovery via Language Model, Property Alignment and Strategic Search](https://mlsanity.com/paper/2512.09566/) (2025)
- [M^4olGen: Multi-Agent, Multi-Stage Molecular Generation under Precise Multi-Property Constraints](https://mlsanity.com/paper/2601.10131/) (2026)

## Built on by (most cited first, 4 of 4)

- [Evaluating Agentic Bioinformatics through Function, Evidence, and Validation](https://mlsanity.com/paper/2607.27556/) (2026)
- [Molecular LLM Agents: From Architectural Design to Scientific Autonomy](https://mlsanity.com/paper/2608.23104/) (2026)
- [Fraglingo: Molecular Design via Attachment-Aware Autoregressive Fragment Generation](https://mlsanity.com/paper/2609.13519/) (2026)
- [SpecOpt: Contact-Diff Reasoning for Agentic Molecule Optimization Toward Binding Specificity](https://mlsanity.com/paper/2609.21165/) (2026)

## Abstract (arXiv)

We present MolLingo, a multi-agent system that emulates the reasoning process of a chemist to automate molecular design. Existing LLM-based approaches either operate as standalone generative models without access to external tools or lack the multi-agent coordination and shared memory needed for iterative, evidence-driven reasoning across the molecular design pipeline. MolLingo addresses this by coordinating a Literature Agent, a Chemist Agent, and an Orchestrator through a shared memory module, with each agent equipped with domain-specific tools. To enable effective molecular reasoning, we introduce BRICS-based Fragment Enumeration (BFE), a synthesis-aware molecular fragmentation method that decomposes molecules into chemically meaningful building blocks represented as block-based SMILES paired with common chemical names. This representation bridges molecular structure and LLM semantic space, enabling block-level reasoning and editing that is difficult with raw SMILES alone. As a case study in early-stage therapeutic design, MolLingo further grounds the Chemist Agent's reasoning in binding site geometry and residue-level protein context derived from molecular docking to optimize molecules for stronger target binding. Across four benchmarks, MolLingo consistently outperforms frontier LLMs and specialized baselines, including a fourfold docking score improvement over GPT-5.4 despite using the same underlying model, consistent drug property optimization gains across multiple LLM backbones, and state-of-the-art results on TOMG-Bench, surpassing both frontier LLMs and the RL-based optimization method RePO. Our results suggest that LLMs are already capable molecular design assistants when guided through chemically meaningful representations and biologically grounded structural context. Code is available at: https://anonymous.4open.science/status/MolLingo-7450.