LockForge: Automating Paper-to-Code for Logic Locking with Multi-Agent Reasoning LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912733997301760 |
|---|---|
| author | Saha, Akashdeep Wang, Zeng Roy, Prithwish Basu Knechtel, Johann Sinanoglu, Ozgur Karri, Ramesh |
| author_facet | Saha, Akashdeep Wang, Zeng Roy, Prithwish Basu Knechtel, Johann Sinanoglu, Ozgur Karri, Ramesh |
| contents | Despite rapid progress in logic locking (LL), reproducibility remains a challenge as codes are rarely made public. We present LockForge, a first-of-its-kind, multi-agent large language model (LLM) framework that turns LL descriptions in papers into executable and tested code. LockForge provides a carefully crafted pipeline realizing forethought, implementation, iterative refinement, and a multi-stage validation, all to systematically bridge the gap between prose and practice for complex LL schemes. For validation, we devise (i) an LLM-as-Judge stage with a scoring system considering behavioral checks, conceptual mechanisms, structural elements, and reproducibility on benchmarks, and (ii) an independent LLM-as-Examiner stage for ground-truth assessment. We apply LockForge to 10 seminal LL schemes, many of which lack reference implementations. Our evaluation on multiple SOTA LLMs, including ablation studies, reveals the significant complexity of the task. We show that an advanced reasoning model and a sophisticated, multi-stage framework like LockForge are required. We release all implementations and benchmarks, providing a reproducible and fair foundation for evaluation of further LL research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_18531 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LockForge: Automating Paper-to-Code for Logic Locking with Multi-Agent Reasoning LLMs Saha, Akashdeep Wang, Zeng Roy, Prithwish Basu Knechtel, Johann Sinanoglu, Ozgur Karri, Ramesh Cryptography and Security Programming Languages Despite rapid progress in logic locking (LL), reproducibility remains a challenge as codes are rarely made public. We present LockForge, a first-of-its-kind, multi-agent large language model (LLM) framework that turns LL descriptions in papers into executable and tested code. LockForge provides a carefully crafted pipeline realizing forethought, implementation, iterative refinement, and a multi-stage validation, all to systematically bridge the gap between prose and practice for complex LL schemes. For validation, we devise (i) an LLM-as-Judge stage with a scoring system considering behavioral checks, conceptual mechanisms, structural elements, and reproducibility on benchmarks, and (ii) an independent LLM-as-Examiner stage for ground-truth assessment. We apply LockForge to 10 seminal LL schemes, many of which lack reference implementations. Our evaluation on multiple SOTA LLMs, including ablation studies, reveals the significant complexity of the task. We show that an advanced reasoning model and a sophisticated, multi-stage framework like LockForge are required. We release all implementations and benchmarks, providing a reproducible and fair foundation for evaluation of further LL research. |
| title | LockForge: Automating Paper-to-Code for Logic Locking with Multi-Agent Reasoning LLMs |
| topic | Cryptography and Security Programming Languages |
| url | https://arxiv.org/abs/2511.18531 |