MMORF: A Multi-agent Framework for Designing Multi-objective Retrosynthesis Planning Systems
On the map: LLM agents and tool use → Medical and scientific domain agents
Abstract (arXiv)
Multi-objective retrosynthesis planning is a critical chemistry task requiring dynamic balancing of quality, safety, and cost objectives. Language model-based multi-agent systems (MAS) offer a promising approach for this task: leveraging interactions of specialized agents to incorporate multiple objectives into retrosynthesis planning. We present MMORF, a framework for constructing MAS for multi-objective retrosynthesis planning. MMORF features modular agentic components, which can be flexibly combined and configured into different systems, enabling principled evaluation and comparison of different system designs. Using MMORF, we construct two representative MAS: MASIL and RFAS. On a newly curated benchmark consisting of 218 multi-objective retrosynthesis planning tasks, MASIL achieves strong safety and cost metrics on soft-constraint tasks, frequently Pareto-dominating baseline routes, while RFAS achieves a 48.6% success rate on hard-constraint tasks, outperforming state-of-the-art baselines. Together, these results show the effectiveness of MMORF as a foundational framework for exploring MAS for multi-objective retrosynthesis planning. Code and data are available at https://github.com/ninglab/MMORF.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 11 of its 64 references that are in the map. First posted on arXiv 6 Apr 2026.
Builds on
11 of 64 references.
Closest ancestors · 1
Same direction, newest first
- 2025LARC: Towards Human-level Constrained Retrosynthesis Planning through an Agentic Framework16 Aug
Other references · 10
- 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
- 2017Learning to Plan Chemical Synthesescited by 179
- 2020Retro*: Learning Retrosynthetic Planning with Neural Guided A* Searchcited by 76
- 2024Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Searchcited by 24
- 2025LIDDIA: Language-based Intelligent Drug Discovery Agentcited by 24
- 2021Self-Improved Retrosynthetic Planningcited by 23
- 2024RetroGFN: Diverse and Feasible Retrosynthesis using GFlowNetscited by 12
- 2025Synthelite: Chemist-aligned and feasibility-aware synthesis planning with LLMscited by 10
- 2020A Pareto Dominance Principle for Data-Driven Optimizationcited by 7
- 2024Tango*: Constrained synthesis planning using chemically informed value functionscited by 7
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2026RetroPlanner: Multi-Route Expansion and Multi-Objective Reasoning for LLM-Based Retrosynthesis Planning
- 2026RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning
- 2026Representation Alignment as a Bottleneck in LLM-Based Retrosynthesis Planning
- 2025AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search
- 2026Reinforced Reasoning for End-to-End Retrosynthetic Planning
- 2025RetroDFM-R: Reasoning-Driven Retrosynthesis Prediction with Large Language Models via Reinforcement Learning
- 2026An Agentic Retrobiosynthesis Framework with Learned Frontier Selection
- 2025Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesis