# An Agentic Retrobiosynthesis Framework with Learned Frontier Selection

arXiv: https://arxiv.org/abs/2608.30702 · HTML: https://mlsanity.com/paper/2608.30702/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 31 Aug 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, 13 of 13)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions](https://mlsanity.com/paper/2308.11483/) (2023)
- [Learning to Plan Chemical Syntheses](https://mlsanity.com/paper/1708.04202/) (2017)
- [Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search](https://mlsanity.com/paper/2006.15820/) (2020)
- [Chemical reasoning in LLMs unlocks strategy-aware synthesis planning and reaction mechanism elucidation](https://mlsanity.com/paper/2503.08537/) (2025)
- [AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search](https://mlsanity.com/paper/2509.20988/) (2025)
- [Synthelite: Chemist-aligned and feasibility-aware synthesis planning with LLMs](https://mlsanity.com/paper/2512.16424/) (2025)
- [LARC: Towards Human-level Constrained Retrosynthesis Planning through an Agentic Framework](https://mlsanity.com/paper/2508.11860/) (2025)
- [RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning](https://mlsanity.com/paper/2607.14512/) (2026)

## Abstract (arXiv)

Large language models are increasingly used as agents for multistep retrosynthesis, raising the question of how much their search policy contributes independently of the underlying reaction model. We investigate this question in a biological setting through rule-based retrobiosynthesis: a deterministic biochemical engine generates the same validated transitions for every method, searching for routes that terminate in metabolites available to an Escherichia coli chassis, while the policy only selects which frontier molecule to expand next. Prompted and LoRA-tuned Qwen2.5-7B policies use a strict choice-only interface. The fine-tuned policy reaches 65±1% solve rate at 10 expansions on LASER versus 59% for MCTS, and at 200 expansions reaches 78±1% versus 75% on LASER, 88±3% versus 80% on the RetroPath RL Golden benchmark, and 63±2% versus 45% on the BioNavi-NP benchmark. Fine-tuning also consistently outperforms direct prompting. These results show that route-supervised frontier selection can improve budgeted search without altering biochemical generation, although performance remains dependent on frontier construction and reaction ranking.