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.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Yoo, H., Huang, C., Shin, H., Zhang, L., & Rosen, G. L. (2026). Representation Alignment as a Bottleneck in LLM-Based Retrosynthesis Planning. https://omanscience.com/en/articles/representation-alignment-as-a-bottleneck-in-llm-based-retrosynthesis-planning
MLA 9
Yoo, Hyunwoo, et al. "Representation Alignment as a Bottleneck in LLM-Based Retrosynthesis Planning." https://omanscience.com/en/articles/representation-alignment-as-a-bottleneck-in-llm-based-retrosynthesis-planning.
Chicago (author–date)
Yoo, Hyunwoo, Cassie Huang, Haebin Shin, Li Zhang, and Gail L. Rosen. 2026. "Representation Alignment as a Bottleneck in LLM-Based Retrosynthesis Planning." https://omanscience.com/en/articles/representation-alignment-as-a-bottleneck-in-llm-based-retrosynthesis-planning.
Harvard
Yoo, H., Huang, C., Shin, H., Zhang, L. and Rosen, G. L. (2026) 'Representation Alignment as a Bottleneck in LLM-Based Retrosynthesis Planning', Available at: https://omanscience.com/en/articles/representation-alignment-as-a-bottleneck-in-llm-based-retrosynthesis-planning.
Vancouver
Yoo H, Huang C, Shin H, Zhang L, Rosen GL. Representation Alignment as a Bottleneck in LLM-Based Retrosynthesis Planning. https://omanscience.com/en/articles/representation-alignment-as-a-bottleneck-in-llm-based-retrosynthesis-planning
IEEE
H. Yoo, C. Huang, H. Shin, L. Zhang, and G. L. Rosen, "Representation Alignment as a Bottleneck in LLM-Based Retrosynthesis Planning," https://omanscience.com/en/articles/representation-alignment-as-a-bottleneck-in-llm-based-retrosynthesis-planning.