List your company

Decision Making on ALFWorld Seen v1

63.57Success Rate (SR)BeliefMem
16.7728.9241.0753.22May 7, 2026

Evaluation results

MethodLinks
BeliefMemBackbone=Qwen3-Next-80B-A3B-Instruct, Memory Corpus Size=Full2026.0563.5727.49
BeliefMemBackbone=Qwen3-Next-80B-A3B-Instruct, Memory Corpus Size=50%2026.0558.5729.77
ReadAgentBackbone=Qwen3-Next-80B-A3B-Instruct2026.0553.5727.88
Mem0Backbone=Qwen3-Next-80B-A3B-Instruct2026.0538.5733.64
MemoryBankBackbone=Qwen3-Next-80B-A3B-Instruct2026.0537.8635.15
LangMemBackbone=Qwen3-Next-80B-A3B-Instruct2026.0537.1434.42
A-MEMBackbone=Qwen3-Next-80B-A3B-Instruct2026.052540.28
MemoryOSBackbone=Qwen3-Next-80B-A3B-Instruct2026.0519.2942.43
No-MemoryBackbone=Qwen3-Next-80B-A3B-Instruct2026.0518.5742.48