Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Home

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multi-turn information acquisitionHome
Success Rate (SR)89.78
25
Sequential RecommendationHome
Recall@103.64
18
Sequential RecommendationHome (test)
NDCG@50.0168
15
Next-basket RecommendationHome
Recall@101.6
14
Sequential RecommendationHome
HR@52.03
14
Candidate retrievalHome
Precision74.8
12
Counterfactual Explanationshome
Validity34.1
10
Autonomous ExplorationHome Simulated
Success Rate83
4
Showing 8 of 8 rows