List your company

Interactive Agent Task on ALFWorld unseen

99.3Success Rate (SR)SKILL-DISCO + CodeAct
44.90859.02973.1587.271Jun 25, 2026

Evaluation results

MethodLinks
SKILL-DISCO + CodeActBackbone=GPT-4o2026.0699.33.2
CodeActBackbone=GPT-4o2026.0696.33.6
SKILL-DISCO + ReActBackbone=GPT-4o2026.0692.48.8
ReActBackbone=GPT-4o2026.068219.3
AWMofflineBackbone=GPT-4o2026.0654.511.3
ASIofflineBackbone=GPT-4o2026.064711.4