Long survey generation on AutoSurvey
7.63LLM-as-a-Judge Score (1-10)EXTAGENTS
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| EXTAGENTSLLM=gpt-4o-mini2025.05 | 7.63 | 191 | 1.09 | 1.8 | |
| AutoSurveyLLM=gpt-4o-mini2025.05 | 6.75 | 113 | 1 | 2.41 |
Loading the SOTA2 catalog…
| Method | Links | ||||
|---|---|---|---|---|---|
| EXTAGENTSLLM=gpt-4o-mini2025.05 | 7.63 | 191 | 1.09 | 1.8 | |
| AutoSurveyLLM=gpt-4o-mini2025.05 | 6.75 | 113 | 1 | 2.41 |