Pith Number

pith:5HFFABOH

pith:2026:5HFFABOHUAADQPPIVV6HT6GB3W

not attested not anchored not stored refs resolved

Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models

Changxing Liu, Minhao Xiong, Siheng Chen, Weixin Li, Yichen Xiong, Yuanzhuo Ding, Zhipeng Zhang, Zixing Lei

Splitting long robot tasks between a high-level planner and specialized action tools raises success rates on extended sequences.

arxiv:2605.13119 v1 · 2026-05-13 · cs.RO · cs.AI · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{5HFFABOHUAADQPPIVV6HT6GB3W}

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

VLAs-as-Tools improves the success rate of π_{0.5} by 4.8 points on LIBERO-Long and 23.1 points on RoboTwin, and further enhances invocation fidelity by 15.0 points as measured by Non-biased Rate.

C2weakest assumption

That the VLA tool-family interface and Tool-Aligned Post-Training produce specialized tools that reliably follow high-level agent invocations with low error rates and without introducing new failure modes in closed-loop execution.

C3one line summary

VLAs-as-Tools pairs a VLM planner with specialized VLA executors via a new interface and Tool-Aligned Post-Training to raise long-horizon robot success rates on LIBERO-Long and RoboTwin benchmarks.

References

34 extracted · 34 resolved · 20 Pith anchors

[1] Do As I Can, Not As I Say: Grounding Language in Robotic Affordances · arXiv:2204.01691

[2] RT-H: Action Hierarchies Using Language · arXiv:2403.01823

[3] $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control · arXiv:2410.24164

[4] RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control · arXiv:2307.15818

[5] Robo2vlm: Visual question answering from large-scale in-the-wild robot manipulation datasets, 2025a

Receipt and verification

First computed	2026-05-18T03:08:58.002505Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e9ca5005c7a000383de8ad7c79f8c1dda0ac53d1d2a095208107ceae3679a179

Aliases

arxiv: 2605.13119 · arxiv_version: 2605.13119v1 · doi: 10.48550/arxiv.2605.13119 · pith_short_12: 5HFFABOHUAAD · pith_short_16: 5HFFABOHUAADQPPI · pith_short_8: 5HFFABOH

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/5HFFABOHUAADQPPIVV6HT6GB3W \
  | 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: e9ca5005c7a000383de8ad7c79f8c1dda0ac53d1d2a095208107ceae3679a179

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "dac523e85f8918124104ede11ef4abaf7537da90c1a1fd2a7511cca42e2b6c69",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2026-05-13T07:40:34Z",
    "title_canon_sha256": "1f83632ae041f82943bd5deb286f243aa452eda9516c7b4efc1d374462c793f8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13119",
    "kind": "arxiv",
    "version": 1
  }
}