Pith Number

pith:JCNLFONE

pith:2026:JCNLFONENEST6JD5ZGA5W5UQH2

not attested not anchored not stored refs resolved

Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Models

Chuanxiu Liu, Jie Liu, Jinghang Li, Lei Zhang, Qing Jiang, Qing Lian, Tianming Zhang, Xiaoke Jiang, Yiran Ling

GTA-VLA lets users steer vision-language-action models with explicit spatial visual cues for better robot control.

arxiv:2605.13632 v1 · 2026-05-13 · cs.RO · 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{JCNLFONENEST6JD5ZGA5W5UQH2}

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

On the in-domain SimplerEnv WidowX benchmark, our framework achieves a state-of-the-art 81.2% success rate. Under OOD visual shifts and spatial ambiguities, a single visual interaction substantially improves task success over existing methods.

C2weakest assumption

That users will supply accurate, task-relevant spatial priors (points, boxes, traces) that the model can reliably integrate without introducing new errors or ambiguities.

C3one line summary

GTA-VLA conditions VLA models on user spatial priors to produce a unified spatial-visual chain-of-thought, reaching 81.2% success on SimplerEnv WidowX and improving performance under out-of-distribution shifts.

References

39 extracted · 39 resolved · 18 Pith anchors

[1] Qwen3-VL Technical Report 2025 · arXiv:2511.21631

[2] RT-H: Action Hierarchies Using Language 2024 · arXiv:2403.01823

[3] $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control 2024 · arXiv:2410.24164

[4] $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization 2025 · arXiv:2504.16054

[5] SAM 3: Segment Anything with Concepts 2025 · arXiv:2511.16719

Receipt and verification

First computed	2026-05-18T02:44:17.742606Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

489ab2b9a469253f247dc981db76903e88c59eacaeb830a297e9b5ff1219c761

Aliases

arxiv: 2605.13632 · arxiv_version: 2605.13632v1 · doi: 10.48550/arxiv.2605.13632 · pith_short_12: JCNLFONENEST · pith_short_16: JCNLFONENEST6JD5 · pith_short_8: JCNLFONE

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/JCNLFONENEST6JD5ZGA5W5UQH2 \
  | 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: 489ab2b9a469253f247dc981db76903e88c59eacaeb830a297e9b5ff1219c761

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "075dfc62fc83e16389d80508c1df17daceeea30b9f27618ea1709c58b3a5ed60",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2026-05-13T14:58:29Z",
    "title_canon_sha256": "3a0179fe064ee1dd6e92a15e7a2ee2102c754f687ca4ccf0f0a3a554fc5fd5f6"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13632",
    "kind": "arxiv",
    "version": 1
  }
}