Multi-stage P+C Tcl generation on AutoEDA Tcl Benchmark 10k prompt-Tcl configuration pairs
14,035.13Token CountBaseline 2
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Baseline 2Generation Strategy=In-Context Learning, Base Model=gpt-4o2025.08 | 14,035.13 | 97.703 | 98.37 | |
| Baseline 1Generation Strategy=Direct Generation, Base Model=gpt-4o2025.08 | 2,220.78 | 0.991 | 10.093 | |
| AutoEDAGeneration Strategy=Microservice-Based LLM Agents, Base Model=Qwen3-0.6B2025.08 | 427.38 | 97.703 | 98.474 |