AgentModernize: Preserving Business Logic in Legacy Modernization with Multi-Agent LLMs and Behavioral Specification Graphs
Sheikh Nazib Ahmed, Marnim Galib

TL;DR
AgentModernize is a multi-agent framework that preserves business logic during legacy system modernization by using behavioral specification graphs, outperforming syntax-based approaches across multiple scenarios.
Contribution
It introduces a novel multi-agent approach with behavioral specification graphs to explicitly preserve business logic in legacy modernization.
Findings
Full AgentModernize with feedback outperforms other configurations in preserving rules.
Behavioral Specification Graphs capture 91.2% of gold-standard rules.
Code generation is identified as the main bottleneck in rule preservation.
Abstract
Legacy modernization breaks business logic. Most tools and LLM-based approaches treat modernization as syntax translation, losing implicit rules, edge-case handling, and cross-module constraints. We present AgentModernize, a multi-agent framework that treats modernization as a behavioral preservation problem. Four specialized agents handle extraction, specification, code generation, and validation. The key intermediate artifact -- a Behavioral Specification Graph (BSG) -- forces extracted business logic to be explicit and inspectable before any code is generated. We evaluated on LegacyModernize-8, eight scenarios spanning telecom and banking, using three models (GPT-4o-mini, GPT-4o, GPT-5.3-codex) under a fair protocol: same gold-standard tests, 3 trials, temperature 0.0. Full AgentModernize with feedback was the only configuration with non-zero mean BER under every backbone. SP-LLM and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
