pith:737LKEDP
Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning
Applying kernel smoothing to a small number of reasoning traces yields accurate value and gradient estimates that improve policy optimization in LLM reasoning.
arxiv:2604.28005 v2 · 2026-04-30 · cs.LG · stat.ML
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{737LKEDPBXREIF3LTEMJ57EIL3}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Numerical and theoretical results demonstrate that our proposal achieves accurate value and gradient estimation, leading to improved policy optimization.
Kernel smoothing applied to a small number of reasoning traces per prompt can produce sufficiently unbiased and low-variance estimates of the true value function in the high-dimensional, discrete space of LLM outputs.
Kernel smoothing yields accurate value and gradient estimates for low-variance policy learning in LLM reasoning under tight per-prompt sampling budgets.
Cited by
Receipt and verification
| First computed | 2026-05-20T00:02:11.931112Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
fefeb5106f0de244176b99189efc885efd0614cd14e3cd1927a378449b865210
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/737LKEDPBXREIF3LTEMJ57EIL3 \
| 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: fefeb5106f0de244176b99189efc885efd0614cd14e3cd1927a378449b865210
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "82082ee2070f3522b2773346f824273a99fe47cb9e39c72d1452aed96a563a37",
"cross_cats_sorted": [
"stat.ML"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-04-30T15:27:34Z",
"title_canon_sha256": "1b358b977e70752e98dbcbabe5cb9351cccf7c8075f16468e345993f61002a30"
},
"schema_version": "1.0",
"source": {
"id": "2604.28005",
"kind": "arxiv",
"version": 2
}
}