Pith Number

pith:SVCNNRA2

pith:2026:SVCNNRA26ASJCGYBUMBBVILSP4

not attested not anchored not stored refs resolved

Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use

Chenrui Fan, Keivan Rezaei, Mahdi JafariRaviz, Soheil Feiz, Yize Cheng

LLMs recognize when tools are needed but frequently fail to call them, exposing a knowing-doing gap in their decision process.

arxiv:2605.14038 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{SVCNNRA26ASJCGYBUMBBVILSP4}

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

These results reveal a knowing-doing gap in LLM tool-use: improving tool-use reliability requires not only better recognition of when tools are needed, but also better translation of that recognition into action.

C2weakest assumption

That the model-adaptive definition of tool necessity (grounded in each model's empirical performance) correctly captures what 'should' trigger a tool call, and that linear probes on hidden states faithfully reflect the internal cognition stage without significant distortion from the probing method itself.

C3one line summary

LLMs show a knowing-doing gap in tool use: they often recognize when tools are needed via internal states but fail to translate that into actual tool calls, with mismatches of 26-54% on arithmetic and factual tasks.

References

38 extracted · 38 resolved · 14 Pith anchors

[1] Introducing the model context protocol, November 2024 2024

[2] Teaching large language models to express knowledge boundary from their own signals, 2024 2024

[3] Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time Perception 2026 · arXiv:2510.23853

[4] Therefore I am. I Think 2026 · arXiv:2604.01202

[5] Balasub- ramanian, Parsa Hosseini, and S 2025

Receipt and verification

First computed	2026-05-17T23:39:12.770962Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9544d6c41af024911b01a3021aa1727f03812a022c511e1918cd04266f968bbd

Aliases

arxiv: 2605.14038 · arxiv_version: 2605.14038v1 · doi: 10.48550/arxiv.2605.14038 · pith_short_12: SVCNNRA26ASJ · pith_short_16: SVCNNRA26ASJCGYB · pith_short_8: SVCNNRA2

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/SVCNNRA26ASJCGYBUMBBVILSP4 \
  | 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: 9544d6c41af024911b01a3021aa1727f03812a022c511e1918cd04266f968bbd

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c10e58c6b16d00b5162ad7af4827c9645e267d7ecc8bd1f5bc6997255fef4638",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-13T18:59:28Z",
    "title_canon_sha256": "9736ae99b4e71c38a1dc56525868ab6426fc735d44f0f8f82ec87d6c3fe0442a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14038",
    "kind": "arxiv",
    "version": 1
  }
}