pith:HJGG4FJU
CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answering
CacheRAG adds semantic caching to turn stateless LLM planners for knowledge graph questions into continual learners.
arxiv:2604.26176 v2 · 2026-04-28 · cs.DB · cs.CL
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{HJGG4FJUMZX4IQJTRCR5LJEEXS}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
CacheRAG significantly outperforms state-of-the-art baselines (e.g., +13.2% accuracy and +17.5% truthfulness on the CRAG dataset).
That the three proposed design principles (schema-agnostic ISR interface, MMR-based diversity retrieval, and bounded heuristic expansion) can be realized without introducing new failure modes or requiring extensive manual tuning of cache policies.
CacheRAG turns stateless LLM planners for KGQA into continual learners via schema-agnostic parsing, diversity-optimized hierarchical caching, and bounded subgraph expansion, yielding up to 13.2% accuracy gains on benchmarks.
Cited by
Receipt and verification
| First computed | 2026-06-02T03:04:41.614720Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
3a4c6e1534666fc4413388a3d5a484bc93ceb7d5005e3a57b56fcced13688210
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/HJGG4FJUMZX4IQJTRCR5LJEEXS \
| 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: 3a4c6e1534666fc4413388a3d5a484bc93ceb7d5005e3a57b56fcced13688210
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "7f51c31b076311b5f7d212ffdc33cba645f714ba68c406cac031304497eba5fb",
"cross_cats_sorted": [
"cs.CL"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.DB",
"submitted_at": "2026-04-28T23:46:47Z",
"title_canon_sha256": "7c173da619f0326e1d6aa8b3673b563e48c83d3268af691926e8ca026385a46e"
},
"schema_version": "1.0",
"source": {
"id": "2604.26176",
"kind": "arxiv",
"version": 2
}
}