Recommendation on Goodreads InstructRec retrospective (test)
36.9HR@1ARS
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| ARSEvaluation Mode=Retrospective, Backbone LLM=Llama-4-Maverick-17B-128E-Instruct, History Window (Lmax)=152026.05 | 36.9 | 77 | 56.8 | 64.3 | |
| BPREvaluation Mode=Retrospective2026.05 | 34.1 | 72.2 | 53.9 | 62.7 | |
| LightGCNEvaluation Mode=Retrospective2026.05 | 28.5 | 64 | 46.6 | 58 | |
| MemRecEvaluation Mode=Retrospective, Backbone LLM=Llama-4-Maverick-17B-128E-Instruct, History Window (Lmax)=152026.05 | 25.7 | 74.1 | 50 | 58.4 | |
| SASRecEvaluation Mode=Retrospective2026.05 | 23.4 | 68.5 | 46.2 | 56.3 | |
| LLMRankEvaluation Mode=Retrospective, Backbone LLM=Llama-4-Maverick-17B-128E-Instruct2026.05 | 21.8 | 60.3 | 41.7 | 54 | |
| i2AgentEvaluation Mode=Retrospective, Backbone LLM=Llama-4-Maverick-17B-128E-Instruct, History Window (Lmax)=152026.05 | 16.4 | 66.2 | 41.7 | 52.2 | |
| iAgentEvaluation Mode=Retrospective, Backbone LLM=Llama-4-Maverick-17B-128E-Instruct, History Window (Lmax)=152026.05 | 16.2 | 59.3 | 37.7 | 50.5 | |
| AgentCFEvaluation Mode=Retrospective, Backbone LLM=Llama-4-Maverick-17B-128E-Instruct2026.05 | 12.4 | 38 | 25.1 | 43.8 |