Agent Task on AppWorld Average
59.5Average ScoreReAct + ACE
Evaluation Results
| Method | Links | |
|---|---|---|
| ReAct + ACEBase LLM=DeepSeek-V3.1-671B, Adaptation Mode=Online Adaptation, GT Labels=✗2025.10 | 59.5 | |
| ReAct + ACEBase LLM=DeepSeek-V3.1-671B, Adaptation Mode=Offline Adaptation, GT Labels=✓2025.10 | 59.4 | |
| ReAct + ACEBase LLM=DeepSeek-V3.1-671B, Adaptation Mode=Offline Adaptation, GT Labels=✗2025.10 | 57.2 | |
| ReAct + DC (CU)Base LLM=DeepSeek-V3.1-671B, Adaptation Mode=Online Adaptation, GT Labels=✗2025.10 | 51.9 | |
| ReAct + GEPABase LLM=DeepSeek-V3.1-671B, Adaptation Mode=Offline Adaptation, GT Labels=✓2025.10 | 46.4 | |
| ReAct + ICLBase LLM=DeepSeek-V3.1-671B, Adaptation Mode=Offline Adaptation, GT Labels=✓2025.10 | 46 | |
| ReActBase LLM=DeepSeek-V3.1-671B, Adaptation Mode=None2025.10 | 42.4 |