PaperScope
LIVE · 2026-09-29 05:40 UTC

Representation Alignment as a Bottleneck in LLM-Based Retrosynthesis Planning

Hyunwoo Yoo, Cassie Huang, Haebin Shin, Li Zhang, Gail L. Rosen

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.35571 v1
Category
Submitted
2026-09-28

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.

arXiv abs page · PDF · same-day batch