Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper introduces Yuan3.0 Flash, an open-source 40B parameter MoE multimodal LLM with 3.7B activated parameters, optimized for enterprise applications. To mitigate overthinking in large reasoning models, they propose Reflection-aware Adaptive Policy Optimization (RAPO), a novel RL training algorithm. Yuan3.0 Flash achieves superior performance on enterprise tasks like RAG and table understanding, while maintaining competitive general-purpose reasoning with significantly fewer tokens compared to frontier models.
Enterprise LLMs can achieve state-of-the-art performance with significantly fewer active parameters and tokens by using a Mixture-of-Experts architecture and a novel RL training method to reduce overthinking.
We introduce Yuan3.0 Flash, an open-source Mixture-of-Experts (MoE) MultiModal Large Language Model featuring 3.7B activated parameters and 40B total parameters, specifically designed to enhance performance on enterprise-oriented tasks while maintaining competitive capabilities on general-purpose tasks. To address the overthinking phenomenon commonly observed in Large Reasoning Models (LRMs), we propose Reflection-aware Adaptive Policy Optimization (RAPO), a novel RL training algorithm that effectively regulates overthinking behaviors. In enterprise-oriented tasks such as retrieval-augmented generation (RAG), complex table understanding, and summarization, Yuan3.0 Flash consistently achieves superior performance. Moreover, it also demonstrates strong reasoning capabilities in domains such as mathematics, science, etc., attaining accuracy comparable to frontier model while requiring only approximately 1/4 to 1/2 of the average tokens. Yuan3.0 Flash has been fully open-sourced to facilitate further research and real-world deployment: https://github.com/Yuan-lab-LLM/Yuan3.0.