Research map / Reinforcement learning / RL from feedback
LLM4Cov: Execution-Aware Agentic Learning for High-coverage Testbench Generation
Hejia Zhang, Zhongming Yu, Chia-Tung Ho, Haoxing Ren, Brucek Khailany, Jishen Zhao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add execution-based filtering to SFT data (ablation) | SFT dataset · CVDP-ECov Syn Pass (agentic) | syntax pass rate (%): 79.5 -> 87.7 | Improved |
| add execution-based filtering to SFT data (ablation) | SFT dataset · CVDP-ECov Syn Pass (direct inference) | syntax pass rate (%): 70.6 -> 83.9 | Improved |
| add augmented spec for the teacher (ablation) | Teacher · CVDP-ECov Syn Pass (direct inference) | syntax pass rate (%): 53.3 -> 71.1 | Improved |
| add augmented spec for the teacher (ablation) | Teacher · CVDP-ECov Syn Pass (agentic) | syntax pass rate (%): 85.1 -> 85.8 | No clear effect |
| add Stage 0 SFT | Qwen3-4B-2507 · CVDP-ECov (agentic) | coverage pass rate (%): 28.4 -> 60.2 | Improved |
| add Stage 1 after Stage 0 | LLM4Cov · CVDP-ECov (agentic) | coverage pass rate (%): 60.2 -> 67.0 | Improved |
| add Stage 2 after Stage 1 | LLM4Cov · CVDP-ECov (agentic) | coverage pass rate (%): 67.0 -> 69.2 | Improved |
| add Stage 2 after Stage 1 | LLM4Cov · CVDP-ECov (direct inference) | coverage pass rate (%): 48.2 -> 50.6 | Improved |
| add Stage 2 after Stage 1 | LLM4Cov · AutoEval-ECov (agentic) | coverage pass rate (%): 83.6 -> 85.0 | Improved |
| increase agentic rounds from R=0 to R=3 (ablation) | LLM4Cov Stage 2 · CVDP-ECov | coverage pass rate (%): 48.2 -> 69.2 | Improved |
| use worst-state-prioritized intermediate state selection instead of best, uniform, median (ablation) | LLM4Cov Stage 1 · CVDP-ECov (agentic) | coverage pass rate | Improved |
| train progressively stage by stage instead of naive data augmentation (ablation) | LLM4Cov · CVDP-ECov (agentic) | coverage pass rate | Improved |
Closest papers by meaning
- Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench (NeurIPS 2026 · similarity 0.87)
- ReVeal: Self-Evolving Code Agents via Reliable Self-Verification (ICLR 2026 · similarity 0.86)
- Tool Verification for Test-Time Reinforcement Learning (NeurIPS 2026 · similarity 0.86)
- Automata from Agent Traces: Failure and Next-Step Prediction (NeurIPS 2026 · similarity 0.86)
- ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling (NeurIPS 2026 · similarity 0.85)
- UltraHorizon: Benchmarking LLM-Agent Capabilities in Ultra Long-Horizon Scenarios (ICML 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
