List your company

Embodied Task Completion on ALFWorld

94Success RateReAct
37.8452.426781.58Mar 10, 2026Mar 24, 2026Apr 7, 2026Apr 21, 2026May 5, 2026May 19, 2026Jun 3, 2026

Evaluation results

MethodLinks
ReActBackbone=DeepSeek-R12026.039490.3
DECENTMEMBackbone=GEMMA4-E4B, Framework=AutoGen2026.0592.28—
AutoAgentBackbone=DeepSeek-R12026.039187.3
G-MemoryBackbone=GEMMA4-E4B, Framework=AutoGen2026.0589.17—
ChatDevBackbone=GEMMA4-E4B, Framework=AutoGen2026.0588.99—
MetaGPTBackbone=GEMMA4-E4B, Framework=AutoGen2026.0586.27—
G-MemoryBackbone=GEMMA4-E4B, Framework=DyLAN2026.0584.49—
EQUIMEMFramework=AutoGen, Memory=G-Memory2026.0584.4—
DECENTMEMBackbone=GEMMA4-E4B, Framework=DyLAN2026.0584.21—
AutoAgentBackbone=QwQ-32B2026.0382.882
No memoryBackbone=GEMMA4-E4B, Framework=AutoGen2026.0582.73—
G-MemoryBackbone=GEMMA4-E4B, Framework=AgentNet2026.0582.39—
EQUIMEMFramework=DyLAN, Memory=Voyager2026.0581.6—
ChatDevBackbone=GEMMA4-E4B, Framework=AgentNet2026.0581.59—
DECENTMEMBackbone=GEMMA4-E4B, Framework=AgentNet2026.0581.46—
EQUIMEMFramework=AutoGen, Memory=AriGraph2026.0580.5—
MetaGPTBackbone=GEMMA4-E4B, Framework=DyLAN2026.0580.49—
DeepAgentBackbone=QwQ-32B2026.0379.987.9
EQUIMEMFramework=AutoGen, Memory=MemBank2026.0579.2—
PPL FilterFramework=AutoGen, Memory=G-Memory2026.0578.4—
MetaGPTBackbone=GEMMA4-E4B, Framework=AgentNet2026.0577.47—
ChatDevBackbone=GEMMA4-E4B, Framework=DyLAN2026.0577.23—
LLM AuditFramework=AutoGen, Memory=G-Memory2026.0576.6—
EQUIMEMFramework=AutoGen, Memory=Voyager2026.0576.5—
PPL FilterFramework=AutoGen, Memory=AriGraph2026.0576.5—
EQUIMEMFramework=DyLAN, Memory=G-Memory2026.0576.3—
No memoryBackbone=GEMMA4-E4B, Framework=DyLAN2026.0576.28—
No memoryBackbone=GEMMA4-E4B, Framework=AgentNet2026.0575.67—
LLM AuditFramework=AutoGen, Memory=AriGraph2026.0575.2—
ChatDevBackbone=GEMMA4-E2B, Framework=AutoGen2026.0574.59—
A-MemGuardFramework=DyLAN, Memory=Voyager2026.0574.3—
EQUIMEMFramework=MacNet, Memory=G-Memory2026.0574.2—
A-MemGuardFramework=AutoGen, Memory=MemBank2026.0574—
DECENTMEMBackbone=GEMMA4-E2B, Framework=AutoGen2026.0573.43—
EQUIMEMFramework=MacNet, Memory=AriGraph2026.0573.1—
EQUIMEMFramework=DyLAN, Memory=AriGraph2026.0573.1—
A-MemGuardFramework=AutoGen, Memory=Voyager2026.0572.7—
PPL FilterFramework=MacNet, Memory=G-Memory2026.0572.6—
VanillaFramework=AutoGen, Memory=G-Memory2026.0572.1—
PPL FilterFramework=DyLAN, Memory=G-Memory2026.0571.5—
EQUIMEMFramework=DyLAN, Memory=MemBank2026.0571.3—
LLM AuditFramework=DyLAN, Memory=AriGraph2026.0571.1—
PPL FilterFramework=AutoGen, Memory=MemBank2026.0570.9—
DECENTMEMBackbone=GEMMA4-E2B, Framework=AgentNet2026.0570.8—
EQUIMEMFramework=MacNet, Memory=Voyager2026.0570.4—
DECENTMEMBackbone=GEMMA4-E2B, Framework=DyLAN2026.0569.53—
VanillaFramework=AutoGen, Memory=AriGraph2026.0569.4—
LLM AuditFramework=AutoGen, Memory=MemBank2026.0568.6—
LLM AuditFramework=MacNet, Memory=G-Memory2026.0568.5—
G-MemoryBackbone=GEMMA4-E2B, Framework=AgentNet2026.0568.47—
G-MemoryBackbone=GEMMA4-E2B, Framework=DyLAN2026.0568.11—
A-MemGuardFramework=DyLAN, Memory=MemBank2026.0567.5—
MetaGPTBackbone=GEMMA4-E2B, Framework=AutoGen2026.0567.49—
LLM AuditFramework=DyLAN, Memory=G-Memory2026.0567.4—
VanillaFramework=MacNet, Memory=G-Memory2026.0567.1—
G-MemoryBackbone=GEMMA4-E2B, Framework=AutoGen2026.0566.73—
LLM AuditFramework=AutoGen, Memory=Voyager2026.0566.5—
PPL FilterFramework=MacNet, Memory=AriGraph2026.0566.4—
No memoryBackbone=GEMMA4-E2B, Framework=AutoGen2026.0566.38—
PPL FilterFramework=DyLAN, Memory=AriGraph2026.0566.2—
LLM AuditFramework=DyLAN, Memory=Voyager2026.0566.1—
EQUIMEMFramework=MacNet, Memory=MemBank2026.0566—
A-MemGuardFramework=MacNet, Memory=Voyager2026.0565.8—
VanillaFramework=AutoGen, Memory=Voyager2026.0565—
VanillaFramework=AutoGen, Memory=MemBank2026.0564.9—
LLM AuditFramework=MacNet, Memory=AriGraph2026.0564.8—
PPL FilterFramework=DyLAN, Memory=Voyager2026.0564.8—
MetaGPTBackbone=GEMMA4-E2B, Framework=DyLAN2026.0564.51—
PPL FilterFramework=AutoGen, Memory=Voyager2026.0564.2—
VanillaFramework=DyLAN, Memory=AriGraph2026.0564.1—
MetaGPTBackbone=GEMMA4-E2B, Framework=AgentNet2026.0563.37—
ChatDevBackbone=GEMMA4-E2B, Framework=DyLAN2026.0563—
PPL FilterFramework=DyLAN, Memory=MemBank2026.0562.8—
No memoryBackbone=GEMMA4-E2B, Framework=DyLAN2026.0562.29—
ChatDevBackbone=GEMMA4-E2B, Framework=AgentNet2026.0562.27—
No-memoryFramework=AutoGen, Memory=Stateless2026.0562.1—
VanillaFramework=DyLAN, Memory=Voyager2026.0561.9—
No memoryBackbone=GEMMA4-E2B, Framework=AgentNet2026.0560.43—
LLM AuditFramework=MacNet, Memory=MemBank2026.0560.3—
PPL FilterFramework=MacNet, Memory=Voyager2026.0560.1—
LLM AuditFramework=DyLAN, Memory=MemBank2026.0559.3—
VanillaFramework=DyLAN, Memory=G-Memory2026.0559.1—
A-MemGuardFramework=MacNet, Memory=MemBank2026.0558.5—
VanillaFramework=MacNet, Memory=AriGraph2026.0558.3—
AutoAgentBackbone=Qwen3-30B-A3B2026.0358.261.2
LLM AuditFramework=MacNet, Memory=Voyager2026.0557.2—
PPL FilterFramework=MacNet, Memory=MemBank2026.0557.2—
VanillaFramework=MacNet, Memory=Voyager2026.0556.4—
VanillaFramework=DyLAN, Memory=MemBank2026.0555.2—
No-memoryFramework=DyLAN, Memory=Stateless2026.0553.8—
VanillaFramework=MacNet, Memory=MemBank2026.0548.9—
DeepAgentBackbone=Qwen3-30B-A3B2026.0348.576.6
No-memoryFramework=MacNet, Memory=Stateless2026.0547.3—
Long context2026.0646.7—
SimpleMem2026.0643.3—
LightMem2026.0643.3—
ReActBackbone=QwQ-32B2026.0341.840.3
DCI-Lite2026.0641.7—
DeepAgentBackbone=DeepSeek-R12026.0340.362.4
HippoRAG2026.0640—