# LLM4Cov: Execution-Aware Agentic Learning for High-coverage Testbench Generation

arXiv: https://arxiv.org/abs/2602.16953 · HTML: https://mlsanity.com/paper/2602.16953/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 20 of 20)

- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [VerilogEval: Evaluating Large Language Models for Verilog Code Generation](https://mlsanity.com/paper/2309.07544/) (2023)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [Scaling Long-Horizon LLM Agent via Context-Folding](https://mlsanity.com/paper/2510.11967/) (2025)
- [VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Tool](https://mlsanity.com/paper/2408.08927/) (2024)
- [Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training](https://mlsanity.com/paper/2501.11425/) (2025)
- [AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories](https://mlsanity.com/paper/2410.07706/) (2024)
- [Comprehensive Verilog Design Problems: A Next-Generation Benchmark Dataset for Evaluating Large Language Models and Agents on RTL Design and Verification](https://mlsanity.com/paper/2506.14074/) (2025)
- [STeCa: Step-level Trajectory Calibration for LLM Agent Learning](https://mlsanity.com/paper/2502.14276/) (2025)
- [QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation](https://mlsanity.com/paper/2505.24183/) (2025)
- [MAGE: A Multi-Agent Engine for Automated RTL Code Generation](https://mlsanity.com/paper/2412.07822/) (2024)
- [CorrectBench: Automatic Testbench Generation with Functional Self-Correction using LLMs for HDL Design](https://mlsanity.com/paper/2411.08510/) (2024)
- [Imitation Learning for Multi-turn LM Agents via On-policy Expert Corrections](https://mlsanity.com/paper/2512.14895/) (2025)
- [VeriReason: Reinforcement Learning with Testbench Feedback for Reasoning-Enhanced Verilog Generation](https://mlsanity.com/paper/2505.11849/) (2025)
- [Progressive distillation induces an implicit curriculum](https://mlsanity.com/paper/2410.05464/) (2024)
- [Exploring Expert Failures Improves LLM Agent Tuning](https://mlsanity.com/paper/2504.13145/) (2025)
- [PRO-V-R1: Reasoning Enhanced Programming Agent for RTL Verification](https://mlsanity.com/paper/2506.12200/) (2025)
- [EDGE: Efficient Data Selection for LLM Agents via Guideline Effectiveness](https://mlsanity.com/paper/2502.12494/) (2025)
- [TB or Not TB: Coverage-Driven Direct Preference Optimization for Verilog Stimulus Generation](https://mlsanity.com/paper/2511.15767/) (2025)

## Built on by (most cited first, 5 of 5)

- [HAVEN: Hybrid Automated Verification ENgine for UVM Testbench Synthesis with LLMs](https://mlsanity.com/paper/2604.27643/) (2026)
- [Exploring the Agentic Frontier of Verilog Code Generation](https://mlsanity.com/paper/2603.19347/) (2026)
- [CHORUS: Complementary Experts for High-Coverage Testbench Stimulus Generation](https://mlsanity.com/paper/2608.10090/) (2026)
- [CovR: Coverage-Aware Hardware Verification via Reasoning-Guided Reinforcement Learning](https://mlsanity.com/paper/2609.19189/) (2026)
- [A Survey on LLM-Integrated Hardware Design Verification](https://mlsanity.com/paper/2610.10580/) (2026)

## Abstract (arXiv)

Execution-aware LLM agents offer a promising paradigm for learning from tool feedback, but such feedback can be expensive and slow to obtain, making online reinforcement learning (RL) less practical in certain scenarios. High-coverage hardware verification exemplifies this challenge due to its reliance on industrial simulators and non-differentiable execution signals. We propose LLM4Cov, an offline agent-learning framework that models verification as single-step state transitions guided by deterministic evaluators. Building on this formulation, we introduce execution-validated data curation, policy-aware agentic data synthesis, and worst-state-prioritized sampling to enable scalable learning under execution constraints. We further curate a reality-aligned benchmark adapted from an existing verification suite through a revised evaluation protocol. Using the proposed pipeline, a compact 4B-parameter model achieves 69.2% pass rate and 90.4% average coverage in CVDP-ECov under agentic evaluation, outperforming its teacher by 5.3% and 10.5%, demonstrating competitive performance against models an order of magnitude larger.