ipfipfipf/Qwen3.5-9B-sdpo-react-mathcodesearch-grpo-arm-e-step29 Text Generation • 9B • Updated 28 days ago • 251
ipfipfipf/Qwen3.5-9B-sdpo-react-mathcodesearch-grpo-arm-e-step29 Text Generation • 9B • Updated 28 days ago • 251
Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism Paper • 2606.00408 • Published May 29 • 64
ipfipfipf/Qwen3.5-4B-sdpo-react-mathcodesearch-sdpo-arm-e Image-Text-to-Text • 4B • Updated Aug 23 • 11
ipfipfipf/Qwen3.5-4B-sdpo-react-mathcodesearch-sdpo-arm-e Image-Text-to-Text • 4B • Updated Aug 23 • 11
ipfipfipf/Qwen3.5-4B-sdpo-react-mathcodesearch-sdpo-arm-a Image-Text-to-Text • 4B • Updated Aug 22 • 10
ipfipfipf/Qwen3.5-4B-sdpo-react-mathcodesearch-sdpo-arm-a Image-Text-to-Text • 4B • Updated Aug 22 • 10
ipfipfipf/Qwen3.5-4B-sdpo-react-mathcodesearch-grpo-arm-e Image-Text-to-Text • 4B • Updated Aug 22 • 17
ipfipfipf/Qwen3.5-4B-sdpo-react-mathcodesearch-grpo-arm-e Image-Text-to-Text • 4B • Updated Aug 22 • 17
ipfipfipf/Qwen3.5-9B-sdpo-react-mathcodesearch-rlsd-arm-e Image-Text-to-Text • 9B • Updated Aug 20 • 11
ipfipfipf/Qwen3.5-9B-sdpo-react-mathcodesearch-rlsd-arm-a Image-Text-to-Text • 9B • Updated Aug 20 • 8
ipfipfipf/Qwen3.5-9B-sdpo-react-mathcodesearch-rlsd-arm-a Image-Text-to-Text • 9B • Updated Aug 20 • 8
ipfipfipf/Qwen3.5-9B-sdpo-react-mathcodesearch-sdpo-arm-e Image-Text-to-Text • 9B • Updated Aug 18 • 12
ipfipfipf/Qwen3.5-9B-sdpo-react-mathcodesearch-sdpo-arm-e Image-Text-to-Text • 9B • Updated Aug 18 • 12
ipfipfipf/Qwen3.5-9B-sdpo-react-mathcodesearch-sdpo-arm-a Image-Text-to-Text • 9B • Updated Aug 18 • 10
ipfipfipf/Qwen3.5-9B-sdpo-react-mathcodesearch-sdpo-arm-a Image-Text-to-Text • 9B • Updated Aug 18 • 10
ipfipfipf/Qwen3.5-9B-sdpo-react-mathcodesearch-rlsd-arm-e Image-Text-to-Text • 9B • Updated Aug 20 • 11
ipfipfipf/Qwen3.5-9B-sdpo-react-mathcodesearch-grpo-arm-f Image-Text-to-Text • 9B • Updated Aug 18 • 5
ipfipfipf/Qwen3.5-9B-sdpo-react-mathcodesearch-grpo-arm-f Image-Text-to-Text • 9B • Updated Aug 18 • 5
ipfipfipf/Qwen3.5-9B-sdpo-react-mathcodesearch-grpo-arm-e Image-Text-to-Text • 9B • Updated Aug 18 • 11