List your company

Knowledge-Intensive Reasoning on 2Wiki

0.89Average ScoreAutoTraj
0.72360.76680.810.8532Jan 30, 2026

Evaluation results

MethodLinks
AutoTrajCategory=SFT-RL TIR Methods2026.010.89
R1-SearcherCategory=RL-only TIR Methods2026.010.87
AutoTIRCategory=RL-only TIR Methods2026.010.86
ReSearchCategory=RL-only TIR Methods2026.010.81
Tool-Star-SFTCategory=SFT-only TIR Methods2026.010.79
Qwen2.5-7B-InstructFramework=Multi-Dimensional Trajectory Evaluation2026.010.78
Tool-StarCategory=SFT-RL TIR Methods2026.010.77
Vanilla SFT-RL TIRCategory=SFT-RL TIR Methods2026.010.75
ToRLCategory=RL-only TIR Methods2026.010.73