List your company

ALFWorld task success on ALFWorld Eval-seen (50 tasks)

49Success Count (Seen Tasks)TraceRetain-CEM
38.641.34446.7Jun 28, 2026

Evaluation results

MethodLinks
TraceRetain-CEMCapacity=502026.064990,100
FIFOCapacity=502026.06488,799
TraceRetain-LinearCapacity=502026.06488,799
Unbounded2026.06478,498
No memory2026.06396,587