Pith Number

pith:53B2XUSX

pith:2026:53B2XUSXTAI6VENF5SH432EBEO

not attested not anchored not stored refs pending

To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling

Abhilasha Ravichander, Arijit Nag, Krishna P. Gummadi, Mahsa Amani, Muhammad Bilal Zafar, Qinyuan Wu, Seungeon Lee, Soumi Das

LLMs often misjudge when calling tools like web search is truly necessary or useful, but estimators built from their internal hidden states can make better calls and raise task performance.

arxiv:2605.00737 v2 · 2026-05-01 · 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{53B2XUSXTAI6VENF5SH432EBEO}

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

Models' perceived need and utility of tool calls are often misaligned with their true need and utility. Building on this framework, we train lightweight estimators of need and utility based on models' hidden states. Our estimators enable simple controllers that can improve decision quality and lead to stronger task performance than the self-perceived set up across three tasks and six models.

C2weakest assumption

That true need and utility can be reliably inferred from an optimal allocation of tool calls to serve as ground truth for training the estimators, and that this inference generalizes across tasks without introducing selection bias.

C3one line summary

LLMs often misalign their self-perceived need for tools with true need and utility, but lightweight estimators trained on hidden states can improve tool-calling decisions and task performance across multiple models and tasks.

Receipt and verification

First computed	2026-06-08T01:04:06.264125Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

eec3abd2579811ea91a5ec8fcde881239ff18dd71ed97c77ab4215f0af386388

Aliases

arxiv: 2605.00737 · arxiv_version: 2605.00737v2 · doi: 10.48550/arxiv.2605.00737 · pith_short_12: 53B2XUSXTAI6 · pith_short_16: 53B2XUSXTAI6VENF · pith_short_8: 53B2XUSX

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/53B2XUSXTAI6VENF5SH432EBEO \
  | 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: eec3abd2579811ea91a5ec8fcde881239ff18dd71ed97c77ab4215f0af386388

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c668fcd8094d98646cbbf9665fb0b6d8071744882c162ae7d46858cd577a92c4",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-01T15:38:13Z",
    "title_canon_sha256": "0f33d388722aee89912de8e63e90f6ad1289ecdda749845883f04934c5b2cd16"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.00737",
    "kind": "arxiv",
    "version": 2
  }
}