Pith Number

pith:7ZUQ5KB5

pith:2026:7ZUQ5KB5VEW526FSQILW53V57T

not attested not anchored not stored refs resolved

TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints

Shubhashis Roy Dipta, Zabir Al Nazi

Language models lack the ability to prospectively plan task selection and compute allocation under fixed token budgets.

arxiv:2605.13414 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{7ZUQ5KB5VEW526FSQILW53V57T}

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

current language models exhibit substantial gaps in prospective metacognitive control, revealing a previously unmeasured capability dimension with direct implications for resource-efficient agent deployment.

C2weakest assumption

That an oracle with full knowledge of each problem's solvability and cost for the model provides a valid and unbiased benchmark for measuring prospective control, and that calibrating the token budget to the model's baseline cost does not introduce hindsight or selection effects.

C3one line summary

TRIAGE evaluates LLMs on prospective metacognitive control by requiring a single plan for task selection, sequencing, and token allocation under a calibrated budget, revealing substantial gaps in current models across math, science, code, and knowledge tasks.

References

64 extracted · 64 resolved · 4 Pith anchors

[1] Snell, Charlie and Lee, Jaehoon and Xu, Kelvin and Kumar, Aviral , booktitle =. Scaling. 2025 , note = 2025

[2] Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in

[3] Chen, Xingyu and Xu, Jiahao and Liang, Tian and He, Zhiwei and Pang, Jianhui and Yu, Dian and Song, Linfeng and Liu, Qiuzhi and Zhou, Mengfei and Zhang, Zhuosheng and Wang, Rui and Tu, Zhaopeng and Mi

[4] Thoughts Are All Over the Place: On the Underthinking of o1-Like 2025

[5] The danger of overthinking: Examining the reasoning-action dilemma in agentic tasks

Receipt and verification

First computed	2026-05-18T02:44:47.394932Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

fe690ea83da92ddd78b282176eeebdfceeb2934820d5c20d88f090c454aebc12

Aliases

arxiv: 2605.13414 · arxiv_version: 2605.13414v1 · doi: 10.48550/arxiv.2605.13414 · pith_short_12: 7ZUQ5KB5VEW5 · pith_short_16: 7ZUQ5KB5VEW526FS · pith_short_8: 7ZUQ5KB5

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/7ZUQ5KB5VEW526FSQILW53V57T \
  | 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: fe690ea83da92ddd78b282176eeebdfceeb2934820d5c20d88f090c454aebc12

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "44d0f49b9c04793a66614f6aea207565aa160c2cc22fddedee1562109460ff92",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-13T12:10:05Z",
    "title_canon_sha256": "a375e050a58cd644c5cef07bb34107fe6d03402acdea9d48dec3a0033e003c02"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13414",
    "kind": "arxiv",
    "version": 1
  }
}