pith:KF6EAGED
FitText: Evolving Agent Tool Ecologies via Memetic Retrieval
Embedding evolutionary retrieval inside an agent's reasoning loop allows dynamic adaptation to evolving task needs in large tool ecosystems.
arxiv:2605.02411 v2 · 2026-05-04 · cs.AI · cs.IR · cs.LG · cs.MA
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{KF6EAGEDSAYTRWNAMZEL5UHPOH}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
On ToolRet (43k tools, 4 domains), FitText improves average retrieval rank from 8.81 to 2.78; on StableToolBench (16,464 APIs), it achieves a 0.73 average pass rate--a 24-point absolute gain over static query retrieval.
The base model must be capable of acting as a competent semantic operator for generating and refining pseudo-tool descriptions; under weaker models the evolutionary search inverts and amplifies noise.
FitText embeds memetic evolutionary retrieval inside the agent's reasoning loop to iteratively refine pseudo-tool descriptions, raising retrieval rank from 8.81 to 2.78 on ToolRet and pass rate to 0.73 on StableToolBench.
Formal links
Receipt and verification
| First computed | 2026-06-11T01:09:36.720464Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
517c401883903138d9a06648bed0ef71e71d1099c0f0a967573fcd6d3b2387e4
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/KF6EAGEDSAYTRWNAMZEL5UHPOH \
| 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: 517c401883903138d9a06648bed0ef71e71d1099c0f0a967573fcd6d3b2387e4
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "d8e2f52bf3175be91768d008e363e66629b420f606a21cb5a03bcad20d934216",
"cross_cats_sorted": [
"cs.IR",
"cs.LG",
"cs.MA"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-05-04T10:01:24Z",
"title_canon_sha256": "9df02b7fea2af15228bc64847699625900c421b8e1b688756d237e31d50872ae"
},
"schema_version": "1.0",
"source": {
"id": "2605.02411",
"kind": "arxiv",
"version": 2
}
}