pith. sign in
Pith Number

pith:RHDIGH5I

pith:2026:RHDIGH5IE65MHCSA3A37EDLUQA
not attested not anchored not stored refs resolved

AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents

Hailin Zhong, Shengxin Zhu

Software-engineering capability for foundation-model agents emerges from a model-harness-environment system rather than from the model alone.

arxiv:2605.13357 v1 · 2026-05-13 · cs.SE · cs.AI

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{RHDIGH5IE65MHCSA3A37EDLUQA}

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

We propose a different locus: software-engineering capability emerges from a model-harness-environment system, in which a runtime substrate -- the harness -- mediates how a foundation-model agent observes a project, acts on it, receives feedback, and establishes that a change is complete.

C2weakest assumption

That defining eleven component responsibilities and a four-level ladder will systematically improve agent reliability and verifiability, an assumption stated without supporting data or derivation in the abstract.

C3one line summary

The paper defines AI Harness Engineering as a runtime substrate with eleven components and a four-level ladder that reframes agent reliability as a model-harness-environment system property rather than model capability alone.

References

18 extracted · 18 resolved · 2 Pith anchors

[1] Evaluating Large Language Models Trained on Code 2021 · arXiv:2107.03374
[2] Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, et al 2020
[3] Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan 2024
[4] Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press 2024
[5] Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, Hoang H 2025

Formal links

1 machine-checked theorem link

Receipt and verification
First computed 2026-05-18T02:44:48.199273Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

89c6831fa827bac38a40d837f20d74801a0673750c947c322a7e0d895a918d29

Aliases

arxiv: 2605.13357 · arxiv_version: 2605.13357v1 · doi: 10.48550/arxiv.2605.13357 · pith_short_12: RHDIGH5IE65M · pith_short_16: RHDIGH5IE65MHCSA · pith_short_8: RHDIGH5I
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/RHDIGH5IE65MHCSA3A37EDLUQA \
  | 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: 89c6831fa827bac38a40d837f20d74801a0673750c947c322a7e0d895a918d29
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "363e8ca21e15174c72e05081c081de279e31f39b66662fd97f6560d405c1840b",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2026-05-13T11:14:59Z",
    "title_canon_sha256": "0912d0135db6157edf6996788b44b8c6fc70f8493c993ae6a8820ef3774e9d02"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13357",
    "kind": "arxiv",
    "version": 1
  }
}