Pith Number

pith:3PFFSBOT

pith:2026:3PFFSBOTJ4WIK6L4A573HEVZ4U

not attested not anchored not stored refs resolved

Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation

Chao Hao, Guangcong Wang, Ji Du, Jun Xu, Shuo Ye, Xiaodong Cun, Xubin Zheng, Zitong Yu, Ziyue Qiao

Seg-Agent lets off-the-shelf multimodal LLMs segment images from language instructions by running an iterative visual reasoning loop over marked regions on the image itself.

arxiv:2605.12953 v1 · 2026-05-13 · cs.CV · 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{3PFFSBOTJ4WIK6L4A573HEVZ4U}

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

This explicit multimodal interaction enables Seg-Agent to achieve performance comparable to state-of-the-art training-based methods without any parameter updates.

C2weakest assumption

That off-the-shelf MLLMs, when given Set-of-Mark visual prompts, can reliably perform spatial selection and refinement in the visual domain without any fine-tuning or additional training data.

C3one line summary

Seg-Agent performs language-guided segmentation without training by using Set-of-Mark visual prompts to enable explicit multimodal chain-of-reasoning in three stages: generation, selection, and refinement.

References

53 extracted · 53 resolved · 10 Pith anchors

[1] Visual instruction tuning.Advances in neural infor- mation processing systems, 36:34892–34916, 2023 2023

[2] GPT-4 Technical Report 2023 · arXiv:2303.08774

[3] Qwen2.5-VL Technical Report 2025 · arXiv:2502.13923

[4] Schwing, and Alexander Kirillov 2021

[5] Schwing, Alexander Kirillov, and Rohit Girdhar 2022

Receipt and verification

First computed	2026-05-18T03:09:09.359460Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

dbca5905d34f2c85797c077fb392b9e50a8706ed252b6fb9ae609463ec214b1f

Aliases

arxiv: 2605.12953 · arxiv_version: 2605.12953v1 · doi: 10.48550/arxiv.2605.12953 · pith_short_12: 3PFFSBOTJ4WI · pith_short_16: 3PFFSBOTJ4WIK6L4 · pith_short_8: 3PFFSBOT

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/3PFFSBOTJ4WIK6L4A573HEVZ4U \
  | 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: dbca5905d34f2c85797c077fb392b9e50a8706ed252b6fb9ae609463ec214b1f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c6de3220d38c5bb0bb238dab329644b42a90c09b9802db94b99b69a3e9d5c74b",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T03:36:44Z",
    "title_canon_sha256": "1d638688c214b9c910920670d63eb82ade729e2881007a82a725e6b85d45e068"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12953",
    "kind": "arxiv",
    "version": 1
  }
}