Pith Number

pith:H22O2LDL

pith:2026:H22O2LDL42NJGVILKAUNKA7WAK

not attested not anchored not stored refs resolved

RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing Agents

Chengfu Liu, Cheng Yang, Dongyang Hou, Haifeng Li, Hanwen Yu, Kai Ouyang, Liangtian Liu, Wentao Yang, Zeyuan Wang, Zichao Tang, Ziyu Li

RS-Claw lets remote sensing agents actively explore tools via hierarchical skill trees, achieving up to 86% token compression while outperforming flat and RAG baselines.

arxiv:2605.13391 v1 · 2026-05-13 · 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{H22O2LDL42NJGVILKAUNKA7WAK}

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

RS-Claw's active exploration mechanism effectively filters semantic noise and substantially frees up reasoning space, achieving an input token compression ratio of up to 86%, and comprehensively outperforming existing Flat and RAG baselines across complex reasoning evaluations on the Earth-Bench benchmark.

C2weakest assumption

That hierarchically structuring tool descriptions via skill encapsulation allows the agent to perform on-demand sequential decision-making that accurately hits critical tools without omissions during long-horizon reasoning in the massive heterogeneous RS tool ecosystem.

C3one line summary

RS-Claw enables remote sensing agents to actively explore tools via hierarchical skill trees, achieving up to 86% token compression and outperforming flat registration and RAG baselines on Earth-Bench.

References

45 extracted · 45 resolved · 5 Pith anchors

[1] Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models 2023 · arXiv:2305.04091

[2] Toolformer: Language models can teach themselves to use tools, 2023

[3] HuggingGPT: Solving AI tasks with ChatGPT and its friends in Hugging Face, 2023

[4] A survey on large language model based autonomous agents 2024

[5] OpenClaw: Open-source personal AI assistant, 2026

Receipt and verification

First computed	2026-05-18T02:44:47.712860Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

3eb4ed2c6be69a93550b5028d503f60298c472f6b3209e101c9c77540b8f63ee

Aliases

arxiv: 2605.13391 · arxiv_version: 2605.13391v1 · doi: 10.48550/arxiv.2605.13391 · pith_short_12: H22O2LDL42NJ · pith_short_16: H22O2LDL42NJGVIL · pith_short_8: H22O2LDL

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/H22O2LDL42NJGVILKAUNKA7WAK \
  | 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: 3eb4ed2c6be69a93550b5028d503f60298c472f6b3209e101c9c77540b8f63ee

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f238e2396f82ace79c7f1e43ae5b40508e44e1aa3db2cb9962ba3714af1d5f9e",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-13T11:49:18Z",
    "title_canon_sha256": "6e92538b8c53720e3e36a92751f4f7fb77171578d6a2db9c84edf54245990596"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13391",
    "kind": "arxiv",
    "version": 1
  }
}