MiniMaxAI/MiniMax-H3
Image-Text-to-Video • 33B • Updated • 3.61M • • 5.68k
Monica L
Data-Omni
·
AI & ML interests
None yet
Recent Activity
liked a model about 1 month ago
MiniMaxAI/MiniMax-H3 updated a Space over 1 year ago
Data-Omni/projects1 published a Space over 1 year ago
Data-Omni/projects1Organizations
None yet
liked a
model about 1 month ago
updated a
Space over 1 year ago
published a
Space over 1 year ago
reacted to merterbak's post with 🔥 over 1 year ago
Post
3641
FlowReasoner is a new system that builds a custom set of small AI agents for every user question. Unlike search based methods it uses reasoning driven optimization with external execution feedback.
✅ First, it distills reasoning data using DeepSeek R1-671B to build multi agent systems. 🤖
✅ Then, reasoning data used for DeepSeek-R1-Distill-Qwen-7B via supervised fine tuning for basic reasoning skills. 💡
✅ Finally, RL with GRPO (optimizes by comparing response groups from queries/tasks) to improve reasoning.
FlowReasoner: Reinforcing Query-Level Meta-Agents (2504.15257)
Code: https://github.com/sail-sg/flowreasoner
✅ First, it distills reasoning data using DeepSeek R1-671B to build multi agent systems. 🤖
✅ Then, reasoning data used for DeepSeek-R1-Distill-Qwen-7B via supervised fine tuning for basic reasoning skills. 💡
✅ Finally, RL with GRPO (optimizes by comparing response groups from queries/tasks) to improve reasoning.
FlowReasoner: Reinforcing Query-Level Meta-Agents (2504.15257)
Code: https://github.com/sail-sg/flowreasoner