List your company

Search-augmented Multi-turn Tool Calling on PopQA

45.82Success RateENVRL-GiGPO
41.982442.978743.97544.9713Jun 16, 2026

Evaluation results

MethodLinks
ENVRL-GiGPOBackbone=Qwen2.5-3B-Instruct2026.0645.82
GiGPOBackbone=Qwen2.5-3B-Instruct2026.0642.13