Web Interaction on WebShop
39.2Pass@1Mem2Evolve
Evaluation Results
| Method | Links | |
|---|---|---|
| Mem2EvolveBackbone=GPT-5-Chat2026.04 | 39.2 | |
| AFLOWBackbone=GPT-5-Chat2026.04 | 37.9 | |
| EvoAgentBackbone=GPT-5-Chat2026.04 | 37.8 | |
| DyLANBackbone=GPT-5-Chat2026.04 | 36.4 | |
| DSPyBackbone=GPT-5-Chat2026.04 | 35.5 | |
| SwarmAgenticBackbone=GPT-5-Chat2026.04 | 34.12 | |
| AgentVerseBackbone=GPT-5-Chat2026.04 | 32.53 | |
| AutoAgentsBackbone=GPT-5-Chat2026.04 | 31.4 | |
| AlitaBackbone=GPT-5-Chat2026.04 | 30.21 | |
| GPT-5-Chat (CoT)Backbone=GPT-5-Chat2026.04 | 27.49 | |
| GPT-5-Chat (ReAct)Backbone=GPT-5-Chat2026.04 | 25.1 | |
| GPT-5-Chat (Direct)Backbone=GPT-5-Chat2026.04 | 22.31 |