List your company

Agentic Reasoning on ALFWorld (Detailed Metrics)

91Success Rate (Org.)CAMEL
50.9661.35571.7582.145May 10, 2026

Evaluation results

MethodLinks
CAMELMemory System=G-Mem., Backbone=LLAMA-42026.059122.938.315.8
JTTMemory System=G-Mem., Backbone=LLAMA-42026.0586.435.641.728.4
IPWMemory System=G-Mem., Backbone=LLAMA-42026.0584.139.754.831.6
VanillaMemory System=G-Mem., Backbone=LLAMA-42026.0583.441.957.634.2
CAMELMemory System=AriGraph, Backbone=LLAMA-42026.0583.227.242.520.3
DeCoTMemory System=G-Mem., Backbone=LLAMA-42026.0577.848.452.639.8
JTTMemory System=AriGraph, Backbone=LLAMA-42026.0572.642.462.133.7
IPWMemory System=AriGraph, Backbone=LLAMA-42026.0572.443.858.435.9
VanillaMemory System=AriGraph, Backbone=LLAMA-42026.0571.646.261.838.7
CAMELMemory System=Mem0, Backbone=LLAMA-42026.0567.417.434.611.3
CAMELMemory System=A-Mem, Backbone=LLAMA-42026.056612.7296.5
DeCoTMemory System=AriGraph, Backbone=LLAMA-42026.0565.152.467.144.2
JTTMemory System=A-Mem, Backbone=LLAMA-42026.0563.725.442.615.8
JTTMemory System=Mem0, Backbone=LLAMA-42026.0562.230.344.725.7
DeCoTMemory System=Mem0, Backbone=LLAMA-42026.0560.434.248.624.3
DeCoTMemory System=A-Mem, Backbone=LLAMA-42026.0559.828.544.114.3
VanillaMemory System=Mem0, Backbone=LLAMA-42026.0559.836.453.929.7
VanillaMemory System=A-Mem, Backbone=LLAMA-42026.0558.431.748.324.9
IPWMemory System=A-Mem, Backbone=LLAMA-42026.0554.139.350.722.6
IPWMemory System=Mem0, Backbone=LLAMA-42026.0552.541.150.832.4