This canonical paper page includes Commercialization Proof and Related Resources.
ARXIV:2603.26512 · GENERATIVE CAD · SUBMITTED 30 MAR · 21:52 UTC · FRESHNESS STALE
ARXIV:2603.26512GENERATIVE CADSUBMITTED 30 MAR · 21:52 UTCFRESHNESS STALEJesse Barkley · Rumi Loghmani · Amir Barati Farimani · arXiv
CADSmith is a multi-agent system that generates precise CAD models from natural language using programmatic geometric validation and iterative refinement.
Opportunity summary
Pain CADSmith is a multi-agent system that generates precise CAD models from natural language using programmatic geometric validation and iterative refinement.
Evidence 33 refs | 3 sources | 50% coverage
Blocker Evidence unverified
CADSmith is a multi-agent system that generates precise CAD models from natural language using programmatic geometric validation and iterative refinement. We present CADSmith, a multi-agent pipeline that generates CadQuery code from natural language.
Existing methods for text-to-CAD generation either operate in a single pass with no geometric verification or rely on lossy visual feedback that cannot resolve dimensional errors. We present CADSmith, a multi-agent pipeline that generates…
ScienceToStartup currently rates this 7.0/10 on the public viability pass. Against a zero-shot baseline, CADSmith achieves a 100% execution rate (up from 95%), improves the median F1 score from 0.9707 to 0.9846, the median…
Generative CAD moved forward this cycle; last verified April 2026. Public score 7.0/10. Production flags indicate code availability.
Continue into Read for claims, analysis, references, and neighboring papers.
mobile layout uses overflow-hidden min-w-0 break-wordsOpportunity summary
Score7.0Public score shown from the verified overall while the stale axis breakdown refreshesAnalysis summary
CADSmith is a multi-agent system that generates precise CAD models from natural language using programmatic geometric validation and iterative refinement.
Loading BUILD…
Paper Pack
10.48550/arXiv.2603.26512CADSmith is a multi-agent system that generates precise CAD models from natural language using programmatic geometric validation and iterative refinement.
Abstract
Existing methods for text-to-CAD generation either operate in a single pass with no geometric verification or rely on lossy visual feedback that cannot resolve dimensional errors. We present CADSmith, a multi-agent pipeline that generates CadQuery code from natural language. It then undergoes an iterative refinement process through two nested correction loops: an inner loop that resolves execution errors and an outer loop grounded in programmatic geometric validation. The outer loop combines exact measurements from the OpenCASCADE kernel (bounding box dimensions, volume, solid validity) with holistic visual assessment from an independent vision-language model Judge. This provides both the numerical precision and the high-level shape awareness needed to converge on the correct geometry. The system uses retrieval-augmented generation over API documentation rather than fine-tuning, maintaining a current database as the underlying CAD library evolves. We evaluate on a custom benchmark of 100 prompts in three difficulty tiers (T1 through T3) with three ablation configurations. Against a zero-shot baseline, CADSmith achieves a 100% execution rate (up from 95%), improves the median F1 score from 0.9707 to 0.9846, the median IoU from 0.8085 to 0.9629, and reduces the mean Chamfer Distance from 28.37 to 0.74, demonstrating that closed-loop refinement with programmatic geometric feedback substantially improves the quality and reliability of LLM-generated CAD models.
Source availability
PDF linkedThe paper record includes a public PDF URL.
Extraction status
Parse run linkedA document parse run is attached to this paper.
Proof status
unverified33 refs; 3 sources; 50% coverage.
What was readable
Derived fallback: Estimated from adjacent evidence; not verified from source.
Viability
Time to MVP
Commercial
Export
Preparing verified analysis
Dimensions overall score 7.0
PROBLEM
CADSmith is a multi-agent system that generates precise CAD models from natural language using programmatic geometric validation and iterative refinement. We present CADSmith, a multi-agent pipeline that generates CadQuery code from natural language.
METHOD
Existing methods for text-to-CAD generation either operate in a single pass with no geometric verification or rely on lossy visual feedback that cannot resolve dimensional errors. We present CADSmith, a multi-agent pipeline that generates CadQuery code from natural language.
RESULT
ScienceToStartup currently rates this 7.0/10 on the public viability pass. Against a zero-shot baseline, CADSmith achieves a 100% execution rate (up from 95%), improves the median F1 score from 0.9707 to 0.9846, the median IoU from 0.8085 to 0.9629, and reduces the mean Chamfer...
WHY NOW
Generative CAD moved forward this cycle; last verified April 2026. Public score 7.0/10. Production flags indicate code availability.
We present CADSmith, a multi-agent pipeline that generates CadQuery code from natural language.
This is a core statement of the system's function, directly from the abstract.
partial
It then undergoes an iterative refinement process through two nested correction loops: an inner loop that resolves execution errors and an outer loop grounded in programmatic geometric validation.
The abstract and analysis explicitly describe the two nested correction loops.
partial
The outer loop combines exact measurements from the OpenCASCADE kernel (bounding box dimensions, volume, solid validity) with holistic visual assessment from an independent vision-language model Judge.
The abstract clearly outlines the components of the outer loop.
partial
Against a zero-shot baseline, CADSmith achieves a 100% execution rate (up from 95%)
This is a specific, quantifiable result presented in the abstract.
partial
improves the median F1 score from 0.9707 to 0.9846
This is a specific, quantifiable result presented in the abstract.
partial
and reduces the mean Chamfer Distance from 28.37 to 0.74
This is a specific, quantifiable result presented in the abstract.
partial
The system uses retrieval-augmented generation over API documentation rather than fine-tuning, maintaining a current database as the underlying CAD library evolves.
The abstract states this approach and its benefit for maintaining currency.
partial
The system might face challenges with highly specialized or extremely complex designs that fall outside the current benchmark.
This is explicitly mentioned as a caveat in the analysis section.
partial
We present CADSmith, a multi-agent pipeline that generates CadQuery code from natural language.
This is a core statement of the paper's contribution, clearly outlined in the abstract and introduction.
partial
It then undergoes an iterative refinement process through two nested correction loops: an inner loop that resolves execution errors and an outer loop grounded in programmatic geometric validation.
The abstract and introduction explicitly describe the two nested correction loops as a key part of the methodology.
partial
The outer loop combines exact measurements from the OpenCASCADE kernel (bounding box dimensions, volume, solid validity) with holistic visual assessment from an independent vision-language model Judge.
The abstract and introduction detail the components of the outer loop, highlighting the combination of kernel metrics and a vision-language model.
partial
Against a zero-shot baseline, CADSmith achieves a 100% execution rate (up from 95%)
This is a specific quantitative result presented in the abstract and results section.
partial
Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.
Concepts
Methods
Materials
Markets
Competitors
CADSmith is a multi-agent system that generates precise CAD models from natural language using programmatic geometric validation and iterative refinement.
Segment
Generative CAD
Adoption evidence
No public code link in the paper record yet
Commercial read
7.0/10 public viability
Direct
Adjacent
Substitute
Unknown
No indexed public discussion is attached to 2603.26512 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.
Hacker News
Not indexed yet
Not indexed yet
Bluesky
Not indexed yet
Preview the source document here, or use the hero PDF action for a new tab.
Reference metadata is not materialized in the public index yet. The source PDF remains the authority; cache refresh is optional.
CITED BY
No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.
Foundation
Extension
Commercially relevant
Owned Distribution
Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.
3/3 checks · 100%
Build Passport
Build passport pending - Proof Lab budget No verified cost estimate / $7.00 cap
status
missing
reason
passport_row_missing
proof status
unverified
cost/budget
No verified cost estimate
confidence low
next verification path
Build brief missing until Build Passport data exists.
Source missing: Build Passport payload.
Experiment plan missing until prototype path is available.
No prototype path attached.
Validation checklist missing until required assets, cost, and regulatory flags are verified.
No checklist artifact is attached to the Build Passport payload.
Derived signals show verified:false until source-backed receipts exist.
Evidence coverage
OpportunityKernel evidence_receipt
33 refs / 3 sources / 50% coverage
stale
Verify missing sources before using this as buyer proof. verified:false
Build readiness
BuildPassport EvidenceState
passport absent
stale
Run Proof Lab or inspect typed missing state. verified:false
Artifact maturity
GitHub and Hugging Face maturity payloads
No public artifact surface observed
stale
Open source artifacts or mark the gap as missing. verified:false
Technical feasibility
partial
Current read
Runnable path is not fully verified.
Evidence
No Build Passport payload attached.
Gaps
Next test
Run minimal reproduction from the Build Passport prototype path.
Market urgency
partial
Current read
Research evidence exists; buyer urgency still needs source proof.
Evidence
33 references, 3 sources, 50% evidence coverage.
Gaps
Next test
Collect buyer interview, deployment evidence, or cited demand signal.
Buyer clarity
missing
Current read
No budget owner is verified for this paper.
Evidence
Build tab has no CRM, procurement, or operator source.
Gaps
Next test
Map target operator, economic buyer, and procurement trigger.
Defensibility
missing
Current read
Defensibility signals are missing.
Evidence
No defensibility receipt attached.
Gaps
Next test
Refresh defensibility bars with source receipts.
Integration burden
missing
Current read
No public implementation surface observed.
Evidence
No GitHub or Hugging Face payload attached.
Gaps
Next test
Write integration checklist from prototype path and target workflow.
Capital intensity
missing
Current read
No observed cost estimate is verified.
Evidence
Cost passport has no observed_usd value.
Gaps
Next test
Run cost passport or mark the cost field not applicable.
Regulatory load
missing
Current read
No regulatory classification is attached.
Evidence
Build Passport ledger does not include regulatory flags.
Gaps
Next test
Classify regulatory flags before commercialization planning.
No named scientific founder assigned.
Paper authors are not treated as operators without consent.
People
No named person assigned.
Gaps
Next verification path
Prototype owner missing.
Build Passport does not name an implementer.
People
No named person assigned.
Gaps
Next verification path
Operator workflow not sourced.
No buyer or workflow interview attached.
People
No named person assigned.
Gaps
Next verification path
No GTM owner verified.
No CRM or outreach source attached.
People
No named person assigned.
Gaps
Next verification path
Regulatory need unclassified.
No clinical or regulatory source attached.
People
No named person assigned.
Gaps
Next verification path
ARTIFACTS
No public artifacts yet.
DEFENSIBILITY
Defensibility and confidence evidence pending.
WATCHTOWER
No verified watchtower monitor rows yet.
FORESIGHT
No prediction yet — minted on next Foresight batch.
OPPORTUNITYKERNEL CHANGES SINCE LAST VIEW
No verified OpportunityKernel changes since the last view.
COMPETITIVE LANDSCAPE UPDATES
No verified competitive landscape changes yet.
RELATED PAPER UPDATES
No verified related paper changes yet.
SIGNAL CANVAS HISTORY AND DELTAS
No Signal Canvas history deltas yet.
TIMELINE
Save this paper to start tracking momentum - commits, demos, and score changes appear here.
No tracked events yet.
Score trend will appear after multiple data points.
BUZZ
Buzz trend pending.