paper-with-me

홈 › Papers

Veri-Sure: A Contract-Aware Multi-Agent Framework with Temporal Tracing and Formal Verification for Correct RTL Code Generation

2026-01-27 · Jiale Liu, Taiyu Zhou, Tianqi Jiang arxiv

In the rapidly evolving field of Electronic Design Automation (EDA), the deployment of Large Language Models (LLMs) for Register-Transfer Level (RTL) design has emerged as a promising direction. However, silicon-grade correctness remains bottlenecked by: (i) limited test coverage and reliability of simulation-centric evaluation, (ii) regressions and repair hallucinations introduced by iterative debugging, and (iii) semantic drift as intent is reinterpreted across agent handoffs. In this work, we propose Veri-Sure, a multi-agent framework that establishes a design contract to align agents' intent and uses a patching mechanism guided by static dependency slicing to perform precise, localized repairs. By integrating a multi-branch verification pipeline that combines trace-driven temporal analysis with formal verification consisting of assertion-based checking and boolean equivalence proofs, Veri-Sure enables functional correctness beyond pure simulations. We also introduce VerilogEval-v2-EXT, extending the original benchmark with 53 more industrial-grade design tasks and stratified difficulty levels, and show that Veri-Sure achieves state-of-the-art verified-correct RTL code generation performance, surpassing standalone LLMs and prior agentic systems.

📄 PDF Abstract BibTeX arXiv:2601.19747

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

ContractHIL-HLS: Contract-Aligned Multi-Agent Workflow with Hardware-in-the-Loop Feedback for HLS Design

2026-07-28 · Jingbo Zhang, Haoxiang Sun, Wenbo Wang, Wenbo Zhang arxiv

This paper presents ContractHIL-HLS, a contract-aligned multi-agent workflow for practical high-level synthesis (HLS) engineering. The workflow makes three contributions. First, it introduces a structured contract as the…

GeoDisaster: Benchmarking Orchestrated Agents for Operational Disaster Geo-Intelligence

2026-06-15 · Maram Hasan, Aman Verma, Savitra Roy, Hariseetharam Gunduboina 외 arxiv

Remote-sensing vision-language models (RS-VLMs) have advanced Earth-observation analysis toward visual interpretation and instruction-following, yet fall short of operational geo-intelligence, which demands tool-grounded…

Reinforcement LearningSpatial Reasoning

SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries

2026-08-06 · Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu 외 arxiv

Large Language Models (LLMs) increasingly act as agents whose procedural knowledge is stored in reusable skill packages and loaded at inference time. As skill libraries grow, a central challenge is to expose the smallest…

Sovereign Assurance Boundary: Certificate-Bound Admission for Agentic Infrastructure

2026-06-10 · Jun He, Deying Yu arxiv

Agentic infrastructure introduces a critical control-plane authorization problem: non-deterministic reasoning systems can propose high-stakes mutations to production resources, yet existing security mechanisms -- such as…

GasAgent: A Multi-Agent Framework for Automated Gas Optimization in Smart Contracts

2025-07-21 · Jingyi Zheng, Zifan Peng, Yule Liu, Junfeng Wang 외 arxiv

Smart contracts are trustworthy, immutable, and automatically executed programs on the blockchain. Their execution requires the Gas mechanism to ensure efficiency and fairness. However, due to non-optimal coding practice…