pith:WKYJLQMB
Prompt Optimization Is a Coin Flip: Diagnosing When It Helps in Compound AI Systems
Prompt optimization in compound AI systems performs no better than random chance on most tasks.
arxiv:2604.14585 v2 · 2026-04-16 · cs.AI · cs.CL
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{WKYJLQMBAUVRUFRACMHMKGQWP4}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Prompt optimization in compound AI systems is statistically indistinguishable from a coin flip: across 72 optimization runs on Claude Haiku (6 methods × 4 tasks × 3 repeats), 49% score below zero-shot; ... optimization helps only when the task has exploitable output structure -- a format the model can produce but does not default to.
That the tested tasks, models (Claude Haiku, Amazon Nova Lite), and optimization methods are representative enough for the conclusions about interaction effects (p > 0.52) and exploitable output structure to generalize to other compound AI systems.
Prompt optimization in compound AI systems is statistically indistinguishable from random chance except when tasks have exploitable output structure; a two-stage diagnostic predicts success.
Receipt and verification
| First computed | 2026-05-28T01:04:40.145303Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
b2b095c181052b1a1620130ec51a167f28d185e94de65f8064e60be64198f54e
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/WKYJLQMBAUVRUFRACMHMKGQWP4 \
| 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: b2b095c181052b1a1620130ec51a167f28d185e94de65f8064e60be64198f54e
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "ff912bb80d5464568b224fd1c42b15b927036bbb6e95114c81bb049248c97f08",
"cross_cats_sorted": [
"cs.CL"
],
"license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-04-16T03:23:46Z",
"title_canon_sha256": "662f573db131e5cd7e7c7cd80bc165db3f7d6623bfbf3d3f4723bd87495016e4"
},
"schema_version": "1.0",
"source": {
"id": "2604.14585",
"kind": "arxiv",
"version": 2
}
}