List your company

Decision Making on ALFWorld Unseen v1

61.19Success Rate (SR)BeliefMem
16.958828.441939.92551.4081May 7, 2026

Evaluation results

MethodLinks
BeliefMemBackbone=Qwen3-Next-80B-A3B-Instruct, Memory Corpus Size=50%2026.0561.1929.34
ReadAgentBackbone=Qwen3-Next-80B-A3B-Instruct2026.0554.4827.41
BeliefMemBackbone=Qwen3-Next-80B-A3B-Instruct, Memory Corpus Size=Full2026.0553.7530.49
Mem0Backbone=Qwen3-Next-80B-A3B-Instruct2026.0541.0433.16
MemoryBankBackbone=Qwen3-Next-80B-A3B-Instruct2026.0538.0634.99
LangMemBackbone=Qwen3-Next-80B-A3B-Instruct2026.0531.3437.17
A-MEMBackbone=Qwen3-Next-80B-A3B-Instruct2026.0529.139.04
No-MemoryBackbone=Qwen3-Next-80B-A3B-Instruct2026.0526.1239.35
MemoryOSBackbone=Qwen3-Next-80B-A3B-Instruct2026.0518.6642.95