pith:7IK6ILWQ
From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio versions via TTS and noise, showing model-dependent performance with small text-to-voice gaps of 1.8-4.8 points on Confetti and When2Call.
arxiv:2605.15104 v1 · 2026-05-14 · cs.CL
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{7IK6ILWQAPXKMPENTXFUTGBANA}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Our dataset-agnostic framework uses text-to-speech, speaker variation, and environmental noise to create paired text-audio instances while preserving the original dataset annotations.
That adding TTS, speaker variation, and environmental noise does not introduce new biases or artifacts that change how models interpret tool arguments or intent in ways that the preserved gold labels fail to capture.
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio versions via TTS and noise, showing model-dependent performance with small text-to-voice gaps of 1.8-4.8 points on Confetti and When2Call.
Receipt and verification
| First computed | 2026-05-17T21:40:25.803035Z |
|---|---|
| Last reissued | 2026-05-17T21:57:19.134793Z |
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | unsigned_v0 |
| Schema | pith-number/v1.0 |
Canonical hash
fa15e42ed003eea63c8d9dcb49982068273784102384f097c27a1235d436fc3c
Aliases
· · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/7IK6ILWQAPXKMPENTXFUTGBANA \
| 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: fa15e42ed003eea63c8d9dcb49982068273784102384f097c27a1235d436fc3c
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "0ca004fe3ea5eccd10deb2c2fa2bcf5406961f23c64776f168d631d878553e81",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CL",
"submitted_at": "2026-05-14T17:22:42Z",
"title_canon_sha256": "8e5b9e5718a5ec88afa0d84104e3d88ac3579debb8b5b46b0b714e9896a94ae2"
},
"schema_version": "1.0",
"source": {
"id": "2605.15104",
"kind": "arxiv",
"version": 1
}
}