List your company

Multi-turn embodied reasoning on AlfWorld

92Success RateReMem
8.830.45273.6Nov 25, 2025

Evaluation results

MethodLinks
ReMemLLM Backbone=Claude 3.7 Sonnet2025.119296
ExpRAGLLM Backbone=Claude 3.7 Sonnet2025.117489
ReMemLLM Backbone=Gemini 2.5 Flash2025.116681
ExpRecentLLM Backbone=Claude 3.7 Sonnet2025.116683
ExpRAGLLM Backbone=Gemini 2.5 Flash2025.115979
SelfRAGLLM Backbone=Claude 3.7 Sonnet2025.115275
ReActLLM Backbone=Claude 3.7 Sonnet2025.115175
Mem0LLM Backbone=Claude 3.7 Sonnet2025.115174
HistoryLLM Backbone=Claude 3.7 Sonnet2025.115073
DC-CuLLM Backbone=Claude 3.7 Sonnet2025.115074
DC-RSLLM Backbone=Claude 3.7 Sonnet2025.115074
AWMLLM Backbone=Claude 3.7 Sonnet2025.114973
AmemLLM Backbone=Claude 3.7 Sonnet2025.114873
ExpRecentLLM Backbone=Gemini 2.5 Flash2025.113765
HistoryLLM Backbone=Gemini 2.5 Flash2025.112860
Mem0LLM Backbone=Gemini 2.5 Flash2025.112761
DC-RSLLM Backbone=Gemini 2.5 Flash2025.112760
AWMLLM Backbone=Gemini 2.5 Flash2025.112659
AmemLLM Backbone=Gemini 2.5 Flash2025.112559
SelfRAGLLM Backbone=Gemini 2.5 Flash2025.112559
DC-CuLLM Backbone=Gemini 2.5 Flash2025.112559
ReActLLM Backbone=Gemini 2.5 Flash2025.112456
BaselineLLM Backbone=Claude 3.7 Sonnet2025.111849
BaselineLLM Backbone=Gemini 2.5 Flash2025.111234