Pith Number

pith:DSAMPC5N

pith:2026:DSAMPC5NOOKQ7XV5CJZ6GZNULA

not attested not anchored not stored refs resolved

Good to Go: The LOOP Skill Engine That Hits 99% Success and Slashes Token Usage by 99% via One-Shot Recording and Deterministic Replay

Chao Han, Kai Yu, Liang Wang, Xiaohua Wang, XuXiao Liang

The LOOP Skill Engine records one LLM execution of a periodic agent task and converts it into a deterministic Loop Skill that replays without any further LLM calls.

arxiv:2605.14237 v1 · 2026-05-14 · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{DSAMPC5NOOKQ7XV5CJZ6GZNULA}

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

achieves a combined 99% success rate and 99% token reduction for periodic agent tasks through a one-shot recording, deterministic replay paradigm

C2weakest assumption

that the greedy length-descending template extraction algorithm can always produce a branch-free Loop Skill that captures the task's functional intent without losing necessary conditional logic or requiring ongoing LLM reasoning

C3one line summary

The LOOP Skill Engine records one LLM-powered run of a periodic task and converts it into a deterministic replay template that eliminates further LLM usage while maintaining high success rates.

References

15 extracted · 15 resolved · 9 Pith anchors

[1] ReAct: Synergizing Reasoning and Acting in Language Models 2023 · arXiv:2210.03629

[2] Toolformer: Language Models Can Teach Themselves to Use Tools 2023 · arXiv:2302.04761

[3] Reflexion: Language Agents with Verbal Reinforcement Learning 2023 · arXiv:2303.11366

[4] S. Gravitas. AutoGPT: Autonomous Task Management with LLMs. GitHub, 2023 2023

[5] LangChain: Building Applications with LLMs through Composability 2022

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:10.687059Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

1c80c78bad73950fdebd1273e365b4583d89a9d7685ac1543727ad448bab048d

Aliases

arxiv: 2605.14237 · arxiv_version: 2605.14237v1 · doi: 10.48550/arxiv.2605.14237 · pith_short_12: DSAMPC5NOOKQ · pith_short_16: DSAMPC5NOOKQ7XV5 · pith_short_8: DSAMPC5N

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/DSAMPC5NOOKQ7XV5CJZ6GZNULA \
  | 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: 1c80c78bad73950fdebd1273e365b4583d89a9d7685ac1543727ad448bab048d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "195c6f70eee1272792a3bf24174929538b69aae9ad1fa126e3f8011c5bc6482a",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-14T01:05:35Z",
    "title_canon_sha256": "33b58ed1d5a9727f0f37a4127166359d48a89671b00a2c8ae77a3d166d62fe0a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14237",
    "kind": "arxiv",
    "version": 1
  }
}