GoGoTB: Agentic RTL Verification with Specification-Grounded Coverage Closure
Quick Answer
GoGoTB introduces an agentic framework for RTL verification, achieving 100% environment generation success and high coverage metrics (98.4% line, 97.2% branch) without human intervention.
Quick Take
This addresses critical gaps in existing -based verification methods by integrating specification-grounded coverage closure and an evolvable knowledge system.
Key Points
- GoGoTB consists of three subsystems: execution control, knowledge system, and coverage framework.
- Achieved 100% environment generation success on 8 RTL designs without human intervention.
- Coverage metrics include 98.4% line, 97.2% branch, and 83.2% functional coverage.
- Addresses interface mismatches and disconnects in existing LLM-based verification approaches.
- No prior work has achieved similar verification environment completeness on these benchmarks.
DeepSignal Analysis
What happened
GoGoTB is a newly introduced framework for register transfer level (RTL) verification that operates without human intervention. It has achieved a 100% success rate in environment generation and high coverage metrics, including 98.4% line and 97.2% branch coverage, across eight RTL designs.
Key evidence
- GoGoTB achieves 100% environment generation success and high coverage metrics of 98.4% line and 97.2% branch coverage.
- The framework integrates three subsystems: an agentic execution control layer, an evolvable knowledge system, and specification-grounded coverage closure.
- GoGoTB was tested on eight RTL designs, demonstrating its capability to generate a complete verification environment without human intervention.
Why it matters
The introduction of GoGoTB addresses significant limitations in existing LLM-based verification methods, which often fail to maintain context across components. By ensuring that coverage is connected to specification requirements, GoGoTB could reduce the risk of undetected interface mismatches and costly bugs in integrated circuits.
What to watch
Paper Resources
📖 Reader Mode
~2 min readAuthors:Xin Xin, Jincheng Lou, Junhui Li, Jinglin Yan, Panda Xiao, Di Wu, Haixiao Li, Weicong Lu, Weijian Fan, Xinyu Qu, Yuxiang Zhao, Min Yu, Zhixiong Di, Yibo Lin
Abstract:Functional verification dominates integrated circuit (IC) front-end engineering effort, and a single missed bug that escapes to silicon can trigger a costly respin. Recent large language models (LLMs) offer new opportunities to automate this process, yet existing LLM-based approaches generate each component through independent single-turn calls with no shared context, leaving interface mismatches undetected and reported coverage disconnected from specification requirements. To address these challenges, we present GoGoTB, an agentic framework that achieves end-to-end verification closure through three subsystems: an agentic execution control layer, an evolvable knowledge system, and specification-grounded coverage closure. The execution control layer separates deterministic enforcement from LLM reasoning at every tool and stage boundary. The knowledge system dispatches methodology and design-specific expertise on demand. The coverage framework anchors every bin to a named specification behavior so that each residual gap has a diagnosable root cause and a targeted remedy. Tested on 8 register transfer level (RTL) designs without any human intervention, GoGoTB achieves 100\% environment generation success and averages 98.4\% line, 97.2\% branch, 97.0\% toggle, and 83.2\% functional coverage. No prior work successfully generates a complete verification environment or achieves meaningful coverage on the same benchmarks.
| Comments: | 9 pages, 7 figures, 3 tables. Xin Xin and Jincheng Lou contributed equally to this work and share first authorship |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.26181 [cs.AI] |
| (or arXiv:2607.26181v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.26181 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jincheng Lou [view email]
[v1]
Tue, 28 Jul 2026 18:40:35 UTC (814 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.