Retrieval, Reward, and Training Protocols: What Matters in Training Search Agents?
Paper • 2605.27881 • Published • 10
Search Agent Review
Official collection for paper Retrieval, Reward, and Training Protocols: What Matters in Training Search Agents? Include Wiki-fixed and all ckpts
-
-
ybyby624/wiki-fixed
Preview • Updated • 234 • 1 -
ybyby624/Qwen2_5-7B-Base-GiGPO-Hermes9k-1epoch-20steps-0408
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Base-GiGPO-SearchR19k-1epoch-280steps-0410
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Base-IGPO-Hermes9k-1epoch-281steps-0404
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Base-IGPO-Hermes9k-1epoch-40steps-0404
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Base-IGPO-SearchR19k-1epoch-160steps-0411
8B • Updated • 8 -
ybyby624/Qwen2_5-7B-Base-SearchR1-Hermes9k-1epoch-20steps-0402
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Base-SearchR1-Hermes9k-1epoch-281steps-0402
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Base-SearchR1-SearchR19k-1epoch-160steps-0409
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Base-TreeGRPO-SearchR19k-1epoch-60steps-0517
8B • Updated • 6 -
ybyby624/Qwen3-8B-SearchR1-SearchR19k-1epoch-140steps-0405
8B • Updated • 8 • 1 -
ybyby624/Qwen3-8B-TreeGRPO-SearchR19k-1epoch-60steps-0517
8B • Updated • 5 -
ybyby624/Qwen3-8B-IGPO-SearchR19k-1epoch-60steps-0410
8B • Updated • 11 -
ybyby624/Qwen3-8B-GiGPO-SearchR19k-1epoch-200steps-0409
8B • Updated • 4 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-260steps-0315
8B • Updated • 5 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-281steps-0315
8B • Updated • 3 -
ybyby624/Qwen2_5-7B-Base-GiGPO-Hermes9k-1epoch-0408
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Base-GiGPO-SearchR19k-1epoch-0410
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Base-IGPO-Hermes9k-1epoch-0404
8B • Updated • 3 -
ybyby624/Qwen2_5-7B-Base-IGPO-SearchR19k-1epoch-0411
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Base-SearchR1-Hermes9k-1epoch-0402
8B • Updated • 3 -
ybyby624/Qwen2_5-7B-Base-SearchR1-SearchR19k-1epoch-0409
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR115k-3epoch-0419-64bsz
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR145k-1epoch-703steps-0421-64bsz
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k-1epoch-0409
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k-1epoch-0427-128bsz
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k-1epoch-0427-256bsz
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k-1epoch-0427-64bsz
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k-1epoch-0501-rerun-1024dim
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k-5epoch-0420-64bsz
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k_clean-1epoch-0428
8B • Updated • 8 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-Hermes9k-1epoch-0403
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR115k-3epoch-64bsz
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR145k-1epoch-64bsz
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k-1epoch-0410
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k-1epoch-0414-128bsz
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k-1epoch-0414-256bsz
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k-1epoch-0414-64bsz
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k-1epoch-0427-512bsz
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k-5epoch-0423-64bsz
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k_clean-1epoch-0428
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k_clean-1epoch-0430-old_env
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-Hermes9k-1epoch-0404
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR115k-3epoch-0415-64bsz
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR145k-1epoch-0417-64bsz
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k-1epoch-0405
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k-1epoch-0412-128bsz
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k-1epoch-0412-64bsz
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k-1epoch-0413-256bsz
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k-1epoch-0413-512bsz
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k-5epoch-0415-64bsz
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k_clean-1epoch-0428
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k_clean-1epoch-0430-old_env
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-Hermes9k-1epoch-0515
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR115k-3epoch-0520
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR145k-1epoch-0520
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-0516
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-5epoch-0517
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k_clean-1epoch-0520
8B • Updated • 5 -
ybyby624/Qwen3-4B-GiGPO-Hermes9k-1epoch-0601
4B • Updated • 5 -
ybyby624/Qwen3-4B-SearchR1-Hermes9k-1epoch-0601
4B • Updated • 5 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-0328
8B • Updated • 6 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-0413-128bsz
8B • Updated • 6 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-0413-64bsz
8B • Updated • 4 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-0414-256bsz
8B • Updated • 4 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-0414-512bsz
8B • Updated • 6 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-0501-1024dim
8B • Updated • 5 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-0505-16turns
8B • Updated • 5 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-0505-32turns
8B • Updated • 4 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-0505-8turns
8B • Updated • 6 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-0524-rerun-1
8B • Updated • 3 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-0524-rerun-2
8B • Updated • 5 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k_clean-1epoch-0428
8B • Updated • 5 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k_clean-1epoch-0429-old_env
8B • Updated • 5 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k_clean-1epoch-0430-last-ckpt
8B • Updated • 4 -
ybyby624/Qwen3-8B-GiGPO-SearchR19k-1epoch-0409
8B • Updated • 4 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-0403
8B • Updated • 4 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-0501-1024dim
8B • Updated • 5 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-0505-16turns
8B • Updated • 3 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-0506-32turns
8B • Updated • 3 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-0506-8turns
8B • Updated • 5 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-0507-32turns
8B • Updated • 6 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-0514-64bsz
8B • Updated • 4 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-0515-128bsz
8B • Updated • 7 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-0515-256bsz
8B • Updated • 37 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-0515-512bsz
8B • Updated • 53 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-0524-rerun-1
8B • Updated • 3 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-0524-rerun-2
8B • Updated • 5 -
ybyby624/Qwen3-8B-IGPO-Hermes9k_clean-1epoch-0428
8B • Updated • 6 -
ybyby624/Qwen3-8B-IGPO-Hermes9k_clean-1epoch-0430
8B • Updated • 4 -
ybyby624/Qwen3-8B-IGPO-Hermes9k_clean-1epoch-0430-old_env
8B • Updated • 3 -
ybyby624/Qwen3-8B-IGPO-SearchR19k-1epoch-0410
8B • Updated • 4 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-0315
8B • Updated • 5 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-0411-128bsz
8B • Updated • 4 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-0411-64bsz
8B • Updated • 4 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-0501-1024dim
8B • Updated • 3 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-0501-rerun-1024dim
8B • Updated • 3 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-0505-16turns
8B • Updated • 3 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-0505-32turns
8B • Updated • 5 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-0505-8turns
8B • Updated • 2 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-0514-256bsz
8B • Updated • 5 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-0514-512bsz
8B • Updated • 3 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-0525-rerun-1
8B • Updated • 5 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-0525-rerun-2
8B • Updated • 4 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k_clean-1epoch-0428
8B • Updated • 6 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k_clean-1epoch-0429-old_env
8B • Updated • 4 -
ybyby624/Qwen3-8B-SearchR1-SearchR19k-1epoch-0405
8B • Updated • 4 -
ybyby624/Qwen3-8B-SearchR1-SearchR19k-1epoch-0412-128bsz
8B • Updated • 3 -
ybyby624/Qwen3-8B-SearchR1-SearchR19k-1epoch-0412-64bsz
8B • Updated • 8 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-0515-128bsz
8B • Updated • 3 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-0515-64bsz
8B • Updated • 2 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-2-0515
8B • Updated • 3 -
ybyby624/Qwen2_5-7B-Base-TreeGRPO-SearchR19k-1epoch-0512
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-0509
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-0510-128bsz
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-0510-256bsz
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-0510-256bsz-run2
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-0512-512bsz
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k_clean-1epoch-0509
8B • Updated • 5 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-0508
8B • Updated • 4 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-0510-128bsz
8B • Updated • 4 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-0510-256bsz
8B • Updated • 4 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-0510-512bsz
8B • Updated • 4 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-0510-64bsz
8B • Updated • 3 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k_clean-1epoch-0509
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-Hermes9k-1epoch-281steps-0402
8B • Updated • 8 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-Hermes9k-1epoch-281steps-0408
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR115k-3epoch-380steps-0419-64bsz
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR145k-1epoch-380steps-0421-64bsz
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k-1epoch-100steps-0427-64bsz
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k-1epoch-17steps-0427-512bsz
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k-1epoch-240steps-0409
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k-1epoch-260steps-0501-rerun-1024dim
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k-1epoch-281steps-0426-old_env_train
8B • Updated • 8 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k-1epoch-30steps-0427-256bsz
8B • Updated • 8 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k-1epoch-60steps-0427-128bsz
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k-5epoch-80steps-0420-64bsz
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k_clean-1epoch-100steps-0428
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k_clean-1epoch-120steps-0429-old_env
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-Hermes9k-1epoch-20steps-0403
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR115k-3epoch-20steps-0421-64bsz
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR145k-1epoch-180steps-64bsz
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k-1epoch-20steps-0426-old_env_train
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k-1epoch-240steps-0425-old_env_train
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k-1epoch-32steps-0414-256bsz
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k-1epoch-40steps-0410
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k-1epoch-40steps-0414-64bsz
8B • Updated • 8 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k-1epoch-55steps-0414-128bsz
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k-1epoch-60steps-0501-rerun-1024dim
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k-1epoch-6steps-0427-512bsz
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k-5epoch-20steps-0420-64bsz
8B • Updated • 9 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k-5epoch-300steps-0423-64bsz
8B • Updated • 8 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k_clean-1epoch-80steps-0428
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-IGPO-SearchR19k_clean-1epoch-80steps-0430-old_env
8B • Updated • 8 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-Hermes9k-1epoch-220steps-0404
8B • Updated • 8 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k-1epoch-220steps-0405
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR115k-3epoch-400steps-0415-64bsz
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR145k-1epoch-140steps-0417-64bsz
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k-1epoch-100steps-0412-64bsz
8B • Updated • 8 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k-1epoch-100steps-0501-rerun-1024dim
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k-1epoch-140steps-0405
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k-1epoch-16steps-0413-512bsz
8B • Updated • 8 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k-1epoch-281steps-0426-old_env_train
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k-1epoch-32steps-0413-256bsz
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k-1epoch-55steps-0412-128bsz
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k-3epoch-440steps-0405
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-GiGPO-SearchR19k_clean-1epoch-0429-old_env
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k-5epoch-140steps-0415-64bsz
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k_clean-1epoch-120steps-0428
8B • Updated • 8 -
ybyby624/Qwen2_5-7B-Instruct-SearchR1-SearchR19k_clean-1epoch-160steps-0430-old_env
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-Hermes9k-1epoch-80steps-0515
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR115k-3epoch-20steps-0523-rerun
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR115k-3epoch-60steps-0520
8B • Updated • 8 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR145k-1epoch-100steps-0520
8B • Updated • 8 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-100steps-0516
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-11steps-0519-512bsz
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-20steps-0519-256bsz
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-30steps-0519-128bsz
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-50steps-0518-64bsz
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-5epoch-120steps-0517
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k_clean-1epoch-120steps-0522-old_env_train
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k_clean-1epoch-80steps-0520
8B • Updated • 6 -
ybyby624/Qwen3-4B-GiGPO-Hermes9k-1epoch-120steps-0601
4B • Updated • 8 -
ybyby624/Qwen3-4B-IGPO-Hermes9k-1epoch-281steps-0601
4B • Updated • 6 -
ybyby624/Qwen3-4B-SearchR1-Hermes9k-1epoch-240steps-0601
4B • Updated • 5 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-100steps-0505-8turns
8B • Updated • 6 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-110steps-0413-64bsz
8B • Updated • 9 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-120steps-0425-old_env_train
8B • Updated • 7 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-13steps-0414-512bsz
8B • Updated • 5 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-160steps-0501-1024dim
8B • Updated • 6 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-200steps-0505-16turns
8B • Updated • 6 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-200steps-0505-32turns
8B • Updated • 3 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-260steps-0524-rerun-1
8B • Updated • 5 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-260steps-0524-rerun-2
8B • Updated • 7 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-32steps-0414-256bsz
8B • Updated • 4 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k-1epoch-45steps-0413-128bsz
8B • Updated • 5 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k_clean-1epoch-0430-merged
8B • Updated • 5 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k_clean-1epoch-110steps-0429-old_env
8B • Updated • 7 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k_clean-1epoch-150steps-0430
8B • Updated • 6 -
ybyby624/Qwen3-8B-GiGPO-Hermes9k_clean-1epoch-170steps-0428
8B • Updated • 5 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-100steps-0403
8B • Updated • 4 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-120steps-0501-1024dim
8B • Updated • 4 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-180steps-0506-32turns
8B • Updated • 4 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-20steps-0507-32turns
8B • Updated • 4 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-20steps-0515-256bsz
8B • Updated • 4 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-220steps-0425-old_env_train
8B • Updated • 6 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-280steps-0403
8B • Updated • 5 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-280steps-0524-rerun-1
8B • Updated • 4 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-40steps-0505-16turns
8B • Updated • 5 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-40steps-0515-128bsz
8B • Updated • 5 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-50steps-0514-64bsz
8B • Updated • 4 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-60steps-0427-old_env_train
8B • Updated • 4 -
ybyby624/Qwen3-8B-IGPO-Hermes9k-1epoch-80steps-0506-8turns
8B • Updated • 4 -
ybyby624/Qwen3-8B-IGPO-Hermes9k_clean-1epoch-140steps-0430-old_env
8B • Updated • 4 -
ybyby624/Qwen3-8B-IGPO-Hermes9k_clean-1epoch-160steps-0430
8B • Updated • 4 -
ybyby624/Qwen3-8B-IGPO-Hermes9k_clean-1epoch-40steps-0428
8B • Updated • 5 -
ybyby624/Qwen3-8B-Rubric-Hermes9k-1epoch-100steps-0407
8B • Updated • 6 -
ybyby624/Qwen3-8B-Rubric-Hermes9k-1epoch-110steps-0407
8B • Updated • 6 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-100steps-0505-8turns
8B • Updated • 3 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-100steps-0525-rerun-1
8B • Updated • 4 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-120steps-0411-64bsz
8B • Updated • 5 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-14steps-0514-512bsz
8B • Updated • 5 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-200steps-0424-old_env_train
8B • Updated • 4 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-200steps-0505-16turns
8B • Updated • 5 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-200steps-0505-32turns
8B • Updated • 4 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-260steps-0501-rerun-1024dim
8B • Updated • 6 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-260steps-0525-rerun-2
8B • Updated • 5 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-32steps-0514-256bsz
8B • Updated • 5 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-65steps-0411-128bsz
8B • Updated • 4 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k-1epoch-80steps-0501-1024dim
8B • Updated • 6 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k_clean-1epoch-120steps-0428
8B • Updated • 7 -
ybyby624/Qwen3-8B-SearchR1-Hermes9k_clean-1epoch-160steps-0429-old_env
8B • Updated • 4 -
ybyby624/Qwen3-8B-SearchR1-SearchR19k-1epoch-130steps-0412-64bsz
8B • Updated • 5 -
ybyby624/Qwen3-8B-SearchR1-SearchR19k-1epoch-60steps-0412-128bsz
8B • Updated • 4 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-100steps-0518-16turns
8B • Updated • 3 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-120steps-0521-old_env_train
8B • Updated • 4 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-17steps-0515-512bsz
8B • Updated • 4 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-220steps-0515
8B • Updated • 5 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-35steps-0515-256bsz
8B • Updated • 5 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-60steps-0518-8turns
8B • Updated • 6 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-60steps-0519-32turns
8B • Updated • 4 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-65steps-0515-128bsz
8B • Updated • 5 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-90steps-0515-64bsz
8B • Updated • 4 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k_clean-1epoch-140steps-0522-old_env_train
8B • Updated • 7 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k_clean-1epoch-177steps-0520
8B • Updated • 4 -
ybyby624/Qwen2_5-7B-Base-TreeGRPO-SearchR19k-1epoch-260steps-0512
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-Hermes9k-1epoch-281steps-0510
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-12steps-0512-512bsz
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-140steps-0511-64bsz
8B • Updated • 5 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-160steps-0509
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-22steps-0510-256bsz
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-34steps-0510-256bsz-run2
8B • Updated • 6 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k-1epoch-40steps-0510-128bsz
8B • Updated • 7 -
ybyby624/Qwen2_5-7B-Instruct-TreeGRPO-SearchR19k_clean-1epoch-160steps-0509
8B • Updated • 6 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-0510-34steps-256bsz
8B • Updated • 8 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-120steps-0508
8B • Updated • 5 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-15steps-0510-512bsz
8B • Updated • 7 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-50steps-0510-128bsz
8B • Updated • 6 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k-1epoch-60steps-0510-64bsz
8B • Updated • 6 -
ybyby624/Qwen3-8B-TreeGRPO-Hermes9k_clean-1epoch-160steps-0509
8B • Updated • 5