List your company

Interactive Task Solving on ALFWorld Small context window

95.8Pick Success RateSlide Window
48.16860.53472.985.266Jun 10, 2026

Evaluation results

MethodLinks
Slide WindowBackbone=Claude Sonnet 4.5, Memory Type=Internal Static Memory, Context Input Token Limit=1950 tokens2026.0695.800066.723.529.1
FoldBackbone=Claude Sonnet 4.5, Memory Type=Internal Dynamic Memory, Context Input Token Limit=1950 tokens2026.0687.500016.7017.9
HORMABackbone=Claude Sonnet 4.5, Memory Type=External Dynamic Memory, Context Input Token Limit=1950 tokens2026.0687.574.221.74.872.270.656.7
HIAGENTBackbone=Claude Sonnet 4.5, Memory Type=Internal Dynamic Memory, Context Input Token Limit=1950 tokens2026.0683.36.54.34.833.335.327
ReSumBackbone=Claude Sonnet 4.5, Memory Type=Internal Dynamic Memory, Context Input Token Limit=1950 tokens2026.0683.300027.8018.7
EmbeddingBackbone=Claude Sonnet 4.5, Memory Type=Internal Static Memory, Context Input Token Limit=1950 tokens2026.06750005.6014.2
AconBackbone=Claude Sonnet 4.5, Memory Type=Internal Dynamic Memory, Context Input Token Limit=1950 tokens2026.0670.800016.7015
TruncationBackbone=Claude Sonnet 4.5, Memory Type=Internal Static Memory, Context Input Token Limit=1950 tokens2026.06503.21323.8017.617.9