Pith Number

pith:GEVESBSU

pith:2026:GEVESBSU7V2UBS3Z6S77EXRXEL

not attested not anchored not stored refs resolved

Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG

Lawrence B. Hsieh, Pengfei Wei, Yiqun Sun

Distilling a corpus into a hierarchical skill directory lets an LLM agent navigate it to improve QA and RAG on structured enterprise data.

arxiv:2604.14572 v3 · 2026-04-16 · cs.IR · cs.AI · cs.CL · cs.MA

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{GEVESBSU7V2UBS3Z6S77EXRXEL}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

On an enterprise customer-support benchmark, Corpus2Skill improves both answer quality and grounding over single-shot dense, hybrid, hierarchical-retrieval, and agentic RAG baselines at a moderate cost tradeoff.

C2weakest assumption

The target corpus possesses a recoverable topical taxonomy that permits effective offline hierarchical clustering into a navigable skill directory.

C3one line summary

Corpus2Skill converts document corpora into navigable hierarchical skill directories for LLM agents, improving QA and RAG quality on single-domain enterprise data but not on open-domain or tabular corpora.

References

18 extracted · 18 resolved · 1 Pith anchors

[1] Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG 2020 · arXiv:2501.09136

[4] Name actual features, products, or processes

[7] What types of user QUESTIONS this group can answer Be specific -- name the main product areas, features, or workflows. Sub-group summaries: - Sub-group 1: {summary[:300]} - Sub-group 2: {summary[:300]

[8] The common TOPIC area these documents cover

[9] The types of QUESTIONS these documents answer

Formal links

2 machine-checked theorem links

Cited by

2 papers in Pith

A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications

Receipt and verification

First computed	2026-05-20T00:00:37.978523Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

312a490654fd7540cb79f4bff25e3722dea7cb5892a067edf74c910e7d30919b

Aliases

arxiv: 2604.14572 · arxiv_version: 2604.14572v3 · doi: 10.48550/arxiv.2604.14572 · pith_short_12: GEVESBSU7V2U · pith_short_16: GEVESBSU7V2UBS3Z · pith_short_8: GEVESBSU

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/GEVESBSU7V2UBS3Z6S77EXRXEL \
  | 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: 312a490654fd7540cb79f4bff25e3722dea7cb5892a067edf74c910e7d30919b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "597e48e1dc288ed268e8e895fbed293d51831d746c172b7dc3be5f432ef55386",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL",
      "cs.MA"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.IR",
    "submitted_at": "2026-04-16T03:05:37Z",
    "title_canon_sha256": "62fc5ed74a83ec6e8d78345a5d2f65042fb35e4dfc2fb19a8dba16bb27f78284"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.14572",
    "kind": "arxiv",
    "version": 3
  }
}