# RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning

arXiv: https://arxiv.org/abs/2607.14512 · HTML: https://mlsanity.com/paper/2607.14512/

## Key facts

- Cited by 3 papers 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 23 of its 47 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 23 of 23)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [Can Language Models Solve Graph Problems in Natural Language?](https://mlsanity.com/paper/2305.10037/) (2023)
- [Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction](https://mlsanity.com/paper/1811.02633/) (2018)
- [Learning to Plan Chemical Syntheses](https://mlsanity.com/paper/1708.04202/) (2017)
- [Retrosynthetic reaction prediction using neural sequence-to-sequence models](https://mlsanity.com/paper/1706.01643/) (2017)
- [Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search](https://mlsanity.com/paper/2006.15820/) (2020)
- [Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction prediction](https://mlsanity.com/paper/2110.09681/) (2021)
- [Root-aligned SMILES: A Tight Representation for Chemical Reaction Prediction](https://mlsanity.com/paper/2203.11444/) (2022)
- [Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Search](https://mlsanity.com/paper/2407.06334/) (2024)
- [Self-Improved Retrosynthetic Planning](https://mlsanity.com/paper/2106.04880/) (2021)
- [Retrosynthetic Planning with Dual Value Networks](https://mlsanity.com/paper/2301.13755/) (2023)
- [Retro-fallback: retrosynthetic planning in an uncertain world](https://mlsanity.com/paper/2310.09270/) (2023)
- [LLM-Augmented Chemical Synthesis and Design Decision Programs](https://mlsanity.com/paper/2505.07027/) (2025)
- [AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search](https://mlsanity.com/paper/2509.20988/) (2025)

## Built on by (most cited first, 3 of 3)

- [An Agentic Retrobiosynthesis Framework with Learned Frontier Selection](https://mlsanity.com/paper/2608.30702/) (2026)
- [Latent JEPA: Abstract Future Prediction for Latent Reasoning in Chemistry](https://mlsanity.com/paper/2610.01947/) (2026)
- [RetroPlanner: Multi-Route Expansion and Multi-Objective Reasoning for LLM-Based Retrosynthesis Planning](https://mlsanity.com/paper/2610.16391/) (2026)

## Abstract (arXiv)

Multi-step retrosynthesis planning seeks to decompose a target molecule into commercially available building blocks through a sequence of feasible reactions. The vast combinatorial search space makes this task challenging even for expert chemists. Traditional methods combine tree search with offline-trained value networks that score candidates in isolation, without reasoning about complete multi-step routes. Recent work leverages Large Language Models (LLMs) for this task, but relies on simple interfaces that limit exploration of the full search space. We introduce RetroAgent, an LLM agent that bridges symbolic search and neural reasoning through a harness with structured memory. Through memory and chemistry tools, the agent observes the full search state, including explored routes, available alternatives, and properties of intermediates, enabling informed decisions grounded in both global progress and domain knowledge. Experiments on in-distribution and out-of-distribution benchmarks demonstrate that RetroAgent delivers strong performance and generalization.