List your company

Interactive Database Interaction on BIRD-Interact Phase 1

54.6Write Success RateDemo
23.514431.584739.65547.7253May 30, 2026

Evaluation results

MethodLinks
DemoMemory Strategy=No Memory, Backbone=GPT-5, User Simulator=GPT-4o2026.0554.618.3128.83
MERITMemory Strategy=Dynamic Memory, Backbone=GPT-5, User Simulator=GPT-4o2026.0553.4924.6433.01
BM25Memory Strategy=Static Memory, Backbone=GPT-5, User Simulator=GPT-4o2026.0552.8719.4829.17
Cosine SimilarityMemory Strategy=Static Memory, Backbone=GPT-5, User Simulator=GPT-4o2026.0551.7219.4828.83
MemRLMemory Strategy=Dynamic Memory, Backbone=GPT-5, User Simulator=GPT-4o2026.0551.1519.9529
MementoMemory Strategy=Dynamic Memory, Backbone=GPT-5, User Simulator=GPT-4o2026.0550.5719.7228.67
TopicKMemory Strategy=Static Memory, Backbone=GPT-5, User Simulator=GPT-4o2026.0548.8518.3127.17
No MemoryMemory Strategy=No Memory, Backbone=GPT-5, User Simulator=GPT-4o2026.0543.6815.0223.33
Vanilla GPT-5Memory Strategy=No Memory, Backbone=GPT-5, User Simulator=GPT-4o2026.0524.718.6913.33