Placement Tcl generation on AutoEDA Tcl Benchmark 10k prompt-Tcl configuration pairs
13,340.68Token CountBaseline 2
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Baseline 2Generation Strategy=In-Context Learning, Base Model=gpt-4o2025.08 | 13,340.68 | 98.8 | 99.004 | |
| Baseline 1Generation Strategy=Direct Generation, Base Model=gpt-4o2025.08 | 1,781.46 | 0.03 | 5.775 | |
| AutoEDAGeneration Strategy=Microservice-Based LLM Agents, Base Model=Qwen3-0.6B2025.08 | 312.2 | 98.899 | 99.035 |