Overview
| Name | RetroDFM-R · aliases: RetroDFM-R, RetroDFM-R-8B |
|---|---|
| Full name | The paper uses the model name only; no expanded name |
| Ambiguous names (not auto-linked) | ChemDFM |
| Family | Not a family entry. The sibling chemistry LLM line has no site entity record, so no family entry |
| Organization | Shanghai Jiao Tong University (X-LANCE Lab; School of Chemistry and Chemical Engineering), Suzhou Laboratory |
| Organization type | Academic lab |
| Country | China |
| Model class | Retrosynthesis (chemistry LLM + reinforcement-learning reasoning) |
| Domain | Small molecules (also: Text, LLMs & agents) |
| First release | · paper revision Basis: arXiv 2507.17448 v1 submitted Note: The site previously cited another paper's identifier (2510.16588); corrected source |
| Other milestones | |
| Latest update | † partly verified · new version Basis: Code repository commits (no release object) Code repository commits, alongside the paper's v2 (2026-08-24) and the creation of a new 8B weights repository (2026-08-20). No journal version was found and whether the newer weights change results is unverified. This is the latest sourced event Note: Previously 2026-08-24; corrected to 2026-08-25 per the repository commits source The most recent sourced event, not a claim that nothing changed since. |
| Status | Active · Paper revision, weights and code events within 12 months |
| Openness | Code: Open · GPL-3.0 Weights: Open · GPL-3.0 (per the group's model pages) Weights and code are GPL-3.0 per the group's public pages; the hosting namespace is the lab's open-source space, not a company |
| Benchmarks reported | 1 counted (self 1) |
| Wet-lab validation | None recorded |
| Unverified fields | † benchmarks_reported[0], release_milestones.weights_release, release_milestones.code_release, latest_update |
| As of | 2026-11-16 |
What it does
Starts from the group's chemistry LLM, continues pretraining on retrosynthesis text, cold-starts with distilled chain-of-thought and then applies reinforcement learning with verifiable signals such as reaction plausibility and product match, emitting precursors together with a reasoning trace. Unlike the pretraining route of Uni-Mol3 or the sequence-to-sequence route of Chemformer, the reasoning text is part of the output, which is its interpretability claim.
Benchmarks reported
Every row is one pairing from the survey's relation file; a score belongs to the benchmark page's ranking, where it is shown with metric, eval set, source type and date. 1 of 1 pairings are counted.
| Benchmark | Relation | Eval set / protocol | Source type | Note and evidence |
|---|---|---|---|---|
| 07 USPTO family (+PaRoutes) | Developer report, official protocol | — | Self-reported | USPTO-50K/FULL; with test-time augmentation noted · evidence |
Other evaluations (outside the 44)
- Double-blind preference study (Own task set) Self-reported: A double-blind comparison of the model's precursors against ground-truth reactants, with most responses rating the model output as better or equal; disagreements cluster on halogen substituent swaps, and the study was run by the authors
- Multi-step route planning case studies (Case study) Self-reported: Several multi-step synthesis route case studies with no common metric
Developers report: reinforcement learning with verifiable chemistry rewards beats existing sequence and edit-based methods on the official retrosynthesis splits while producing a readable reasoning trace.
Independent evidence: No independent evidence found. No third-party re-run or independent evaluation was found
Training data
Group in Figure 7: Public data only.
| Class | Value | Detail |
|---|---|---|
| a. Public databases | Yes | Continued pretraining on retrosynthesis chemistry data, including structure-name pairs from a public compound library and public retrosynthesis prediction data source |
| b. Private or licensed data | Not disclosed | |
| c. Own wet-lab data used for training | No | |
| d. Wet lab used only for validation | No | The paper reports no wet-lab validation source |
Wet-lab validation
None. The developers report no wet-lab validation.
Background
- Organization: An academic lab: a cross-media language intelligence lab in a Chinese university's computer science school, working with the same university's chemistry school and a regional laboratory; its open-source namespace is not a company. The lab also runs a joint lab with a speech-technology company.
- Funding: Acknowledgements list a national key programme, three national natural science foundation grants and two municipal science projects; training used eight datacentre-class GPUs.
- Products and partnerships: Sibling work includes a chemistry LLM with multimodal and reasoning variants (three public papers); on-site competitors are Chemformer and Uni-Mol3. No company partnerships disclosed.
- Related models: Chemformer, Uni-Mol3
Reading notes
- The site cited the wrong paper identifier; the correct source is arXiv 2507.17448 and the other identifier belongs to a different paper.
- The site's unknown-class figure is unverified and the abstract gives a different value, so always go back to the abstract's framing.
- With and without test-time augmentation are two settings with a visible gap; the figures once recorded as an abstract-versus-text conflict were a single reaction class, not the overall framing.
- USPTO data are frozen and leak templates, so high scores are not synthetic feasibility; there is no wet-lab or route-level independent validation.
Caveats
- All benchmark results are author-reported with no board entry.
- Weight dates rely on host-side repository creation; whether the two 8B weight releases differ in results is unverified.
- The reasoning trace aids readability, but its correctness rests on self-assessment only.
- The code repository has no release objects, so versioning can only be read from commits.
Sources
- Model paper, arXiv 2507.17448 (correct source) (preprint)
- Paper v1 full text (preprint)
- Code repository (repository)
- First 8B weights repository (package registry)
- Newer 8B weights repository (package registry)
Corrections
4 corrections
| Field | Was | Now | Basis | Found |
|---|---|---|---|---|
| sources | Cited arXiv 2510.16588 as this model's paper | The correct id is arXiv 2507.17448; the earlier id belongs to another paper | source | 2026-11-16 |
| benchmarks_reported | The "unknown class" retrosynthesis figure shown on the site | The figure is not confirmed; recorded per the abstract, and this page does not transcribe the score | source | 2026-11-16 |
| release_milestones.weights_release | 8B weights released 2026-01-12 | First 8B weights repository created 2025-11-20 (announced 2025-11-22); 2026-01-12 was only a README edit; another 8B repository was created 2026-08-20 | source | 2026-11-16 |
| latest_update | 2026-08-24 (paper v2) | 2026-08-25 (code repository commit, no release object) | source | 2026-11-16 |
Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.