Representation Alignment as a Bottleneck in LLM-Based Retrosynthesis Planning

2026-09-28

AI Summary

This study addresses the challenge that large language models (LLMs) struggle to generate Planning Domain Definition Language (PDDL) specifications end-to-end for chemical retrosynthetic planning due to the absence of intermediate abstractions. To overcome this limitation, this work proposes a structured design paradigm based on intermediate representations, decomposing the task into three sequential sub-steps: molecule mapping, reaction mapping, and PDDL generation. Our investigation reveals that representation alignment, rather than model capacity, constitutes the primary bottleneck constraining performance. The proposed approach significantly improves the success rate of retrosynthetic planning, empirically validating the critical role of intermediate representations in complex symbolic reasoning. Ultimately, this research establishes a novel paradigm for integrating LLMs with symbolic planning frameworks.

Abstract

While LLMs show promise in general reasoning, symbolic planning in chemistry remains a bottleneck. Direct''SMILES-to-PDDL''attempts fail because they force models to juggle chemical analysis and planning-language structuring simultaneously. We hypothesize that this failure stems from a lack of intermediate abstractions rather than insufficient model capacity. By decomposing retrosynthesis into molecule mapping, reaction mapping, and PDDL generation, we achieve high success rates where end-to-end approaches fail. This provides evidence that a primary bottleneck lies in representation alignment rather than raw model capacity. Our structural analysis demonstrates that intermediate representations are essential in retrosynthesis planning, highlighting the importance of representation-centric design in future systems.

Problem

• Retrosynthesis Planning
• Representation Alignment
• Large Language Models
• Symbolic Planning
• Intermediate Abstractions

Innovation

• Representation Alignment
• Retrosynthesis Planning
• Task Decomposition
• Intermediate Abstractions
• PDDL Generation