Pith Number

pith:LOONUOBW

pith:2026:LOONUOBW5MYO435TEP2ZCTPVBM

not attested not anchored not stored refs resolved

AgentModernize: Preserving Business Logic in Legacy Modernization with Multi-Agent LLMs and Behavioral Specification Graphs

Marnim Galib, Sheikh Nazib Ahmed

A multi-agent framework with an explicit behavioral graph preserves business logic during legacy modernization where direct LLM translation loses it.

arxiv:2605.17535 v1 · 2026-05-17 · cs.SE

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{LOONUOBW5MYO435TEP2ZCTPVBM}

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

Full AgentModernize with feedback was the only configuration with non-zero mean BER under every backbone. SP-LLM and CoT-LLM scored 0.0% on every scenario, on every backbone. The BSG captures 91.2% of gold-standard rules, confirming that the bottleneck is code generation, not extraction.

C2weakest assumption

The gold-standard tests used in the LegacyModernize-8 evaluation comprehensively cover all implicit business logic, edge cases, and cross-module constraints present in the original legacy systems (evaluation section).

C3one line summary

A multi-agent LLM framework with Behavioral Specification Graphs preserves business logic in legacy modernization, achieving non-zero mean BER on all tested scenarios where baseline LLM approaches scored zero.

References

26 extracted · 26 resolved · 4 Pith anchors

[1] A survey of legacy system modernization approaches, 2000

[2] A systematic review of software architecture evolution research, 2012 · doi:10.1016/j.infsof.2011.08.002

[3] Requirements for integrating software architecture and reengineering models: CORUM II, 1998 · doi:10.1109/wcre.1998.723185

[4] Model-driven reverse engi- neering, 2004 · doi:10.1109/ms.2004.23

[5] Evaluating Large Language Models Trained on Code 2021 · arXiv:2107.03374

Receipt and verification

First computed	2026-05-20T00:04:44.496925Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5b9cda3836eb30ee6fb323f5914df50b057d0b1702bb2509250717572918082a

Aliases

arxiv: 2605.17535 · arxiv_version: 2605.17535v1 · doi: 10.48550/arxiv.2605.17535 · pith_short_12: LOONUOBW5MYO · pith_short_16: LOONUOBW5MYO435T · pith_short_8: LOONUOBW

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/LOONUOBW5MYO435TEP2ZCTPVBM \
  | 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: 5b9cda3836eb30ee6fb323f5914df50b057d0b1702bb2509250717572918082a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "53153e26dcb4232b7ddf3a028c2d47f6bc18ad1f7005061bf37447853d33f1c6",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2026-05-17T16:39:48Z",
    "title_canon_sha256": "1ed5af40e049e8bdcc44ed79515bb4137cfe379a2a655830ea7e03d4b0125d8e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.17535",
    "kind": "arxiv",
    "version": 1
  }
}