pith:Z54RYTFE
From Next Token Prediction to (STRIPS) World Models
Next-token prediction on action traces yields STRIPS world models accurate enough for planning on unseen states and goals.
arxiv:2509.13389 v7 · 2025-09-16 · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{Z54RYTFEABGFK6WD2F6Z7W7JC5}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Both the STRIPS Transformer and a standard transformer with stick-breaking attention can be used to produce models that support planning with off-the-shelf STRIPS planners over exponentially many unseen initial states and goals.
The learned next-token models are sufficiently accurate and complete to serve as drop-in STRIPS action models for arbitrary unseen states and goals, with correctness evaluated exactly in the symbolic setting (abstract, evaluation section implied by results on generalization and planning performance).
Transformers trained via next-token prediction on action traces can learn STRIPS action models that support planning over exponentially many unseen initial states and goals.
Cited by
Receipt and verification
| First computed | 2026-05-26T02:05:02.079507Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
cf791c4ca4004c557ac3d17d9fdbe917643c867d8fed2eb7b2e50905b5cd78cc
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/Z54RYTFEABGFK6WD2F6Z7W7JC5 \
| 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: cf791c4ca4004c557ac3d17d9fdbe917643c867d8fed2eb7b2e50905b5cd78cc
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "f5c3b28e3735b7c63a2649dc552be9bf0267af4481943e7f836a5a8fe1758a4b",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.AI",
"submitted_at": "2025-09-16T14:03:58Z",
"title_canon_sha256": "04fffbe5ca69d4e35db0406b1d7bafa4a7543d8fdfba3bf3cded295d6c0f8e90"
},
"schema_version": "1.0",
"source": {
"id": "2509.13389",
"kind": "arxiv",
"version": 7
}
}