pith:RZXN3SBP
A3D: Agentic AI flow for autonomous Accelerator Design
An agentic AI flow automates the entire hardware accelerator design process for complex applications with no human intervention.
arxiv:2605.15237 v1 · 2026-05-14 · cs.AR · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{RZXN3SBPEUWBCCLIV6HQA5R36O}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Our implementation of A3D, using commercial components like Claude Sonnet 4.5 and the Catapult HLS tool, demonstrates its effectiveness by generating accelerator designs with no human intervention from complex scientific applications like LAMMPS (molecular dynamics simulation) and QMCPACK (quantum chemistry).
That current LLMs, when partitioned into specialist and verifier agents and augmented with agentic RAG, can reliably perform workload analysis, identify bottlenecks, refactor code for HLS compatibility, and generate correct micro-architectures for complex irregular scientific codes without introducing errors that require human correction.
A3D is an agentic AI system that automates end-to-end hardware accelerator design for complex applications like LAMMPS and QMCPACK with no human intervention.
References
Formal links
Receipt and verification
| First computed | 2026-05-20T00:00:47.813951Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
8e6eddc82f252c110968af8f00763bf39c81c117748e25e6309a42ca17a645c0
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/RZXN3SBPEUWBCCLIV6HQA5R36O \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 8e6eddc82f252c110968af8f00763bf39c81c117748e25e6309a42ca17a645c0
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "c7a828d442e7a1ed174b6c43bb29d601bddf53e130c9131f03b375ccc2c8b1c1",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.AR",
"submitted_at": "2026-05-14T01:28:16Z",
"title_canon_sha256": "26315e89bb16829fbc8148940bdb7132b537031c4e70d80ab04f9d09f379299c"
},
"schema_version": "1.0",
"source": {
"id": "2605.15237",
"kind": "arxiv",
"version": 1
}
}