List your company

Agentic Reasoning on ScienceWorld

82.2Original ScoreCAMEL
52.97660.56368.1575.737May 10, 2026

Evaluation results

MethodLinks
CAMELMemory System=A-Mem, Backbone=LLAMA-42026.0582.210.435.823.4
CAMELMemory System=G-Mem., Backbone=LLAMA-42026.0579.416.344.130.3
VanillaMemory System=A-Mem, Backbone=LLAMA-42026.0574.627.455.141.8
DeCoTMemory System=G-Mem., Backbone=LLAMA-42026.0574.623.146.345.4
CAMELMemory System=Mem0, Backbone=LLAMA-42026.0573.812.540.425.9
JTTMemory System=G-Mem., Backbone=LLAMA-42026.0573.128.747.243.2
VanillaMemory System=G-Mem., Backbone=LLAMA-42026.0571.835.363.448.7
DeCoTMemory System=Mem0, Backbone=LLAMA-42026.0570.824.150.636.5
IPWMemory System=G-Mem., Backbone=LLAMA-42026.0569.436.861.249.3
JTTMemory System=A-Mem, Backbone=LLAMA-42026.0569.130.257.437.8
IPWMemory System=Mem0, Backbone=LLAMA-42026.0569.123.656.337.8
DeCoTMemory System=A-Mem, Backbone=LLAMA-42026.0568.333.856.440.7
VanillaMemory System=Mem0, Backbone=LLAMA-42026.0566.231.559.744.3
IPWMemory System=A-Mem, Backbone=LLAMA-42026.0565.235.849.749.1
CAMELMemory System=AriGraph, Backbone=LLAMA-42026.056430.85844.7
JTTMemory System=Mem0, Backbone=LLAMA-42026.0562.834.860.142.3
DeCoTMemory System=AriGraph, Backbone=LLAMA-42026.0558.242.870.156.4
IPWMemory System=AriGraph, Backbone=LLAMA-42026.0557.247.174.660.3
VanillaMemory System=AriGraph, Backbone=LLAMA-42026.0556.449.877.363.1
JTTMemory System=AriGraph, Backbone=LLAMA-42026.0554.151.278.660.4