List your company

Decision Making on ALFWorld Avg v1

59.88Success Rate (SR)BeliefMem
17.34428.38739.4350.473May 7, 2026

Evaluation results

MethodLinks
BeliefMemBackbone=Qwen3-Next-80B-A3B-Instruct, Memory Corpus Size=50%2026.0559.8829.56
BeliefMemBackbone=Qwen3-Next-80B-A3B-Instruct, Memory Corpus Size=Full2026.0558.6628.99
ReadAgentBackbone=Qwen3-Next-80B-A3B-Instruct2026.0554.0327.65
Mem0Backbone=Qwen3-Next-80B-A3B-Instruct2026.0539.8133.4
MemoryBankBackbone=Qwen3-Next-80B-A3B-Instruct2026.0537.9635.07
LangMemBackbone=Qwen3-Next-80B-A3B-Instruct2026.0534.2435.8
A-MEMBackbone=Qwen3-Next-80B-A3B-Instruct2026.0527.139.66
No-MemoryBackbone=Qwen3-Next-80B-A3B-Instruct2026.0522.3540.92
MemoryOSBackbone=Qwen3-Next-80B-A3B-Instruct2026.0518.9842.69