| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Web Navigation and Shopping | Webshop | Score100 | 153 | |
| Interactive Decision Making | WebShop | Success Rate84.02 | 70 | |
| E-commerce Navigation and Search | WebShop semantic shift Hidden drift | Score100 | 63 | |
| Online Shopping | Webshop | Score91.5 | 61 | |
| Interactive web-based shopping tasks | WebShop | Score92.2 | 60 | |
| Online Shopping | WebShop (test) | Score95 | 59 | |
| Web Shopping Agent | WebShop | Score91.1 | 53 | |
| Agent Task | WebShop | Success Rate99 | 50 | |
| Agentic reasoning | WebShop | Success Rate65.58 | 45 | |
| Web-based Agent Interaction | WebShop (test) | Success Rate73 | 42 | |
| Web-based Agent Interaction | WebShop | CoT Match Rate100 | 41 | |
| Interactive Decision Making | WebShop (Seen) | Average Reward62.3 | 40 | |
| Interactive Decision Making | WebShop (test) | Success Rate97 | 37 | |
| Web navigation | WebShop | Success Rate76 | 32 | |
| Web-based Agent Interaction | WebShop (val) | Success Rate84.4 | 31 | |
| Mean Reward | WebShop | Mean Reward63.7 | 30 | |
| Online shopping agent navigation | WebShop 128 (val) | Score89.4 | 30 | |
| Web Navigation | WebShop Source | Success Rate100 | 27 | |
| Interactive Decision-making | WebShop | Real39 | 24 | |
| Prompt-level Targeted Bit-flip Attack | WebShop | CDA100 | 24 | |
| Internal-trigger targeted bit-flip attack | WebShop (test) | CDA0.95 | 24 | |
| Web Task | WebShop | Average Reward69.2 | 24 | |
| Interactive Environment Task Completion | WebShop (Seen) | Average Reward86.2 | 22 | |
| World Modeling | Webshop (test) | Search100 | 20 | |
| E-commerce product search and purchase | WebShop | Strict Success81.3 | 19 |