Pith Number

pith:XGUY3L4K

pith:2026:XGUY3L4KPM2JZUWBXFPZFV2G5U

not attested not anchored not stored refs resolved

Large Language Models as Optimization Controllers: Adaptive Continuation for SIMP Topology Optimization

Jun Wang, Shaoliang Yang, Yunsheng Wang

A large language model can act as a real-time controller for SIMP topology optimization by choosing parameters from current state observations instead of a fixed schedule.

arxiv:2603.25099 v2 · 2026-03-26 · cs.CE · 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{XGUY3L4KPM2JZUWBXFPZFV2G5U}

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

The LLM agent achieves the lowest final compliance on every benchmark: -5.7% to -18.1% relative to the fixed baseline, with all solutions fully binary.

C2weakest assumption

The structured observation vector (compliance, grayness index, stagnation counter, checkerboard measure, volume fraction, budget consumption) plus the LLM's learned mapping is sufficient to produce superior real-time parameter decisions that the ablation study attributes to the agent's intervention rather than schedule geometry alone.

C3one line summary

An LLM acting as real-time controller for SIMP topology optimization parameters outperforms fixed schedules and heuristics, delivering 5.7-18.1% lower compliance on 2D and 3D benchmarks.

References

74 extracted · 74 resolved · 5 Pith anchors

[1] Lazarov, and Ole Sigmund 2017 · doi:10.1038/nature23911

[2] Abueidda, Seid Koric, and Nahed A 2020 · doi:10.1016/j.compstruc.2020.106283

[3] Automated dynamic algorithm configuration.Journal of Artificial Intelligence Research, 75:1633–1699, 2022 2022 · doi:10.1613/jair.1.13922

[4] Lazarov, and Ole Sig- mund 2011 · doi:10.1007/s00158-010-0594-7

[5] The Claude model card and evaluations 2024

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

IterSIMP-{\sigma}: Evaluating LLM-Assisted Spatial Interventions in Stress-Aware Topology Optimization

Receipt and verification

First computed	2026-05-20T00:01:40.627232Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b9a98daf8a7b349cd2c1b95f92d746ed0ef6968251c23249369fb3d094ec43aa

Aliases

arxiv: 2603.25099 · arxiv_version: 2603.25099v2 · doi: 10.48550/arxiv.2603.25099 · pith_short_12: XGUY3L4KPM2J · pith_short_16: XGUY3L4KPM2JZUWB · pith_short_8: XGUY3L4K

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/XGUY3L4KPM2JZUWBXFPZFV2G5U \
  | 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: b9a98daf8a7b349cd2c1b95f92d746ed0ef6968251c23249369fb3d094ec43aa

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ac1869ebb49d744436cd2740d3721ba7f1fd980016e41d29a588ada048be05b9",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.CE",
    "submitted_at": "2026-03-26T07:14:31Z",
    "title_canon_sha256": "a0de68fd469be5ddd2a42f4a02bbef118c72dce6e427b632810498d04340eeb0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.25099",
    "kind": "arxiv",
    "version": 2
  }
}