Pith Number

pith:WTB4XYYZ

pith:2022:WTB4XYYZU6OKHGSFJTRP5PODD2

not attested not anchored not stored refs resolved

Code as Policies: Language Model Programs for Embodied Control

Andy Zeng, Brian Ichter, Fei Xia, Jacky Liang, Karol Hausman, Peng Xu, Pete Florence, Wenlong Huang

Language models write executable robot policies by composing code from a few example commands.

arxiv:2209.07753 v4 · 2022-09-16 · cs.RO

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{WTB4XYYZU6OKHGSFJTRP5PODD2}

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

When provided as input several example language commands (formatted as comments) followed by corresponding policy code (via few-shot prompting), LLMs can take in new commands and autonomously re-compose API calls to generate new policy code respectively.

C2weakest assumption

That the LLM-generated code will execute correctly and safely on physical robots for novel commands without runtime errors or the need for additional verification layers.

C3one line summary

Language models generate robot policy code from natural language commands via few-shot prompting, enabling spatial-geometric reasoning, generalization, and precise control on real robots.

References

145 extracted · 145 resolved · 17 Pith anchors

[1] Evaluating Large Language Models Trained on Code 2021 · arXiv:2107.03374

[2] Mdetr-modulated detection for end-to-end multi-modal understanding, 2021

[3] Open-vocabulary Object Detection via Vision and Language Knowledge Distillation 2021 · arXiv:2104.13921

[4] Robots that use language, 2020

[5] Procedures as a representation for data in a computer program for understanding natural language, 1971

Formal links

2 machine-checked theorem links

Cited by

33 papers in Pith

CODE-SHARP: Continuous Open-ended Discovery and Evolution of Skills as Hierarchical Reward Programs

How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning

DexHoldem: Playing Texas Hold'em with Dexterous Embodied System

Agent AI: Surveying the Horizons of Multimodal Interaction

Neuro-Symbolic Control with Large Language Models for Language-Guided Spatial Tasks

Receipt and verification

First computed	2026-05-17T23:39:19.692326Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b4c3cbe319a79ca39a454ce2febdc31eb538734577ae4c4fb5971639d80d1925

Aliases

arxiv: 2209.07753 · arxiv_version: 2209.07753v4 · doi: 10.48550/arxiv.2209.07753 · pith_short_12: WTB4XYYZU6OK · pith_short_16: WTB4XYYZU6OKHGSF · pith_short_8: WTB4XYYZ

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/WTB4XYYZU6OKHGSFJTRP5PODD2 \
  | 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: b4c3cbe319a79ca39a454ce2febdc31eb538734577ae4c4fb5971639d80d1925

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d8ced9d954021ac1db8d3ff885f46eac81e76c8d8f3f3b8123b2e38e4ecce031",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2022-09-16T07:17:23Z",
    "title_canon_sha256": "480718d0058d1c2f38bcafeb7fc1609a083acbe6c53019337a21fb929fa1a8b3"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2209.07753",
    "kind": "arxiv",
    "version": 4
  }
}