Multi-stage C+R Tcl generation on AutoEDA Tcl Benchmark 10k prompt-Tcl configuration pairs
280.74Token CountAutoEDA
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| AutoEDAGeneration Strategy=Microservice-Based LLM Agents, Base Model=Qwen3-0.6B2025.08 | 280.74 | 98.579 | 98.999 | |
| Baseline 1Generation Strategy=Direct Generation, Base Model=gpt-4o2025.08 | 1,608.65 | 0.974 | 11.882 | |
| Baseline 2Generation Strategy=In-Context Learning, Base Model=gpt-4o2025.08 | 10,155.43 | 98.268 | 98.799 |