List your company

Exploration on ALFWorld (val)

97.9Success RateMemRL
83.02886.88990.7594.611Jan 6, 2026

Evaluation results

MethodLinks
MemRLModel=GPT-5-mini2026.0197.9
RAGModel=GPT-5-mini2026.0195
Self-RAGModel=GPT-5-mini2026.0195
Mem0Model=GPT-5-mini2026.0195
MemPModel=GPT-5-mini2026.0192.1
No MemoryModel=GPT-5-mini2026.0183.6