pith:3DN2IPLN
Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents
Ontology-coupled agents significantly outperform ungrounded agents on accuracy and role consistency across enterprise domains.
arxiv:2604.00555 v4 · 2026-04-01 · cs.AI · cs.CL · cs.SE
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{3DN2IPLNWM6TNOQPISXNHBVGUO}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
ontology-coupled agents significantly outperform ungrounded agents on Metric Accuracy (p < .001) and Role Consistency (p < .001) across all three models with large effect sizes (Kendall's W = .46-.64)
The ontologies are correctly specified and complete for the tested domains, and the controlled experiment adequately isolates the effect of ontological coupling from other factors such as prompt engineering or tool selection.
Ontology grounding improves accuracy and role consistency of enterprise LLM agents, with larger gains in domains poorly covered by training data.
Formal links
Cited by
Receipt and verification
| First computed | 2026-05-20T00:03:09.758045Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
d8dba43d6db33d36ba0f44aed386a6a391e881c909e9eb28c753201ae75e7c09
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/3DN2IPLNWM6TNOQPISXNHBVGUO \
| 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: d8dba43d6db33d36ba0f44aed386a6a391e881c909e9eb28c753201ae75e7c09
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "fd6a726809b40a990b97c0c30e547ade7b4d398bcb0ddf77b320922f06c72511",
"cross_cats_sorted": [
"cs.CL",
"cs.SE"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-04-01T06:59:15Z",
"title_canon_sha256": "8d5cc19e2e37e7fdb769c48e1399e69cdf671afb469619b9fa887c9ce336f09b"
},
"schema_version": "1.0",
"source": {
"id": "2604.00555",
"kind": "arxiv",
"version": 4
}
}