pith:KX22QOPD
CogRAG: Tackling Heterogeneous Cognitive Demands in RAG via Stratified Retrieval and Reasoning
CogRAG+ separates retrieval from reasoning in LLMs using dual paths and structured templates to fix knowledge gaps on professional exams.
arxiv:2604.25928 v2 · 2026-04-01 · cs.CL
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{KX22QOPDYIJANPOUB4MCBFSQNH}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Experiments on two representative models, Qwen3-8B and Llama3.1-8B, show that CogRAG+ consistently outperforms general-purpose models and standard RAG methods on the Registered Dietitian qualification exam. In single-question mode, it raises overall accuracy to 85.8% for Qwen3-8B and 60.3% for Llama3.1-8B, with clear gains over vanilla baselines.
The assumption that a judge-driven dual-path retrieval strategy can reliably identify and supply missing foundational knowledge without domain-specific tuning or additional training data.
CogRAG+ raises LLM accuracy on a dietitian exam to 85.8% by using dual-path retrieval and structured reasoning templates.
Formal links
Receipt and verification
| First computed | 2026-06-03T01:05:14.150446Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
55f5a839e3c21206bdd40f1820965069ec405284b4cc23cb912c5d44b46d3af3
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/KX22QOPDYIJANPOUB4MCBFSQNH \
| 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: 55f5a839e3c21206bdd40f1820965069ec405284b4cc23cb912c5d44b46d3af3
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "5a3ef9266d69cd2cef9046f9e9820edb0e3578e4f61a6d2c56fbc8e01a1b5c8c",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CL",
"submitted_at": "2026-04-01T13:31:12Z",
"title_canon_sha256": "9cce5771b904db0a97992173e7393cfc956537ed62f258162045cbb829a4f483"
},
"schema_version": "1.0",
"source": {
"id": "2604.25928",
"kind": "arxiv",
"version": 2
}
}