List your company

Agent Task on AppWorld Average

59.5Average ScoreReAct + ACE
41.71646.33350.9555.567Oct 6, 2025

Evaluation results

MethodLinks
ReAct + ACEBase LLM=DeepSeek-V3.1-671B, Adaptation Mode=Online Adaptation, GT Labels=✗2025.1059.5
ReAct + ACEBase LLM=DeepSeek-V3.1-671B, Adaptation Mode=Offline Adaptation, GT Labels=✓2025.1059.4
ReAct + ACEBase LLM=DeepSeek-V3.1-671B, Adaptation Mode=Offline Adaptation, GT Labels=✗2025.1057.2
ReAct + DC (CU)Base LLM=DeepSeek-V3.1-671B, Adaptation Mode=Online Adaptation, GT Labels=✗2025.1051.9
ReAct + GEPABase LLM=DeepSeek-V3.1-671B, Adaptation Mode=Offline Adaptation, GT Labels=✓2025.1046.4
ReAct + ICLBase LLM=DeepSeek-V3.1-671B, Adaptation Mode=Offline Adaptation, GT Labels=✓2025.1046
ReActBase LLM=DeepSeek-V3.1-671B, Adaptation Mode=None2025.1042.4