Pith Number

pith:X3JC64AS

pith:2025:X3JC64ASYRLPMMN4XIJCZCZ2Z7

not attested not anchored not stored refs resolved

Small Language Models are the Future of Agentic AI

Greg Heinrich, Pavlo Molchanov, Peter Belcak, Saurav Muralidharan, Shizhe Diao, Xin Dong, Yingyan Celine Lin, Yonggan Fu

Small language models will replace large ones in most agentic AI applications due to better suitability and economy for specialized tasks.

arxiv:2506.02153 v2 · 2025-06-02 · 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{X3JC64ASYRLPMMN4XIJCZCZ2Z7}

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

SLMs are sufficiently powerful, inherently more suitable, and necessarily more economical for many invocations in agentic systems, and are therefore the future of agentic AI.

C2weakest assumption

That the specialized, low-variation tasks in current and near-future agentic systems do not require the full general capabilities that only large models currently provide.

C3one line summary

Small language models are sufficiently capable, more suitable, and far more economical than large models for the repetitive tasks that dominate agentic AI systems.

References

87 extracted · 87 resolved · 11 Pith anchors

[1] Small language models vs 2024

[2] Small language models vs 2024

[3] Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone 2024 · arXiv:2404.14219

[4] The economics of ai training and inference: How deepseek broke the cost curve, February 2025 2025

[5] Delift: Data efficient language model instruction fine tuning.arXiv preprint arXiv:2411.04425, 2024 2024

Formal links

2 machine-checked theorem links

Cited by

38 papers in Pith

Large Language Models for Multi-Robot Systems: A Survey

High-quality generation of dynamic game content via small language models: A proof of concept

Llamas on the Web: Memory-Efficient, Performance-Portable, and Multi-Precision LLM Inference with WebGPU

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy

Beyond Scaling: Agents Are Heading to the Edge

Receipt and verification

First computed	2026-05-17T23:38:47.966178Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

bed22f7012c456f631bcba122c8b3acfd91202c709f2f8a95fe690a779293b1b

Aliases

arxiv: 2506.02153 · arxiv_version: 2506.02153v2 · doi: 10.48550/arxiv.2506.02153 · pith_short_12: X3JC64ASYRLP · pith_short_16: X3JC64ASYRLPMMN4 · pith_short_8: X3JC64AS

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/X3JC64ASYRLPMMN4XIJCZCZ2Z7 \
  | 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: bed22f7012c456f631bcba122c8b3acfd91202c709f2f8a95fe690a779293b1b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "8886f67a67aecd07adfb707313cfa51995b02364b9bbee8a66f7140e6921edb5",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-06-02T18:35:16Z",
    "title_canon_sha256": "0f7eb6283ded3977bbf0e5bc2f853c3034c617bbbf507a95be609e5198cdd54a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2506.02153",
    "kind": "arxiv",
    "version": 2
  }
}