mlsanityData to 7 Oct 2026

Yuan3.0 Flash: An Open Multimodal Large Language Model for Enterprise Applications

arXiv 2601.01718 ↗First posted 5 Jan 2026cs.AIcited by 2

On the map: LLM reasoning → Test-time compute and efficient thinking

also in 2 more
Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 48 of its 57 references that are in the map. First posted on arXiv 5 Jan 2026.

Builds on

48 of 57 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models3 Jul
  2. 2025AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning17 May

Other references · 46

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2023Visual Instruction Tuningcited by 7,792
  4. 2025Qwen2.5-VL Technical Reportcited by 5,418
  5. 2024GPT-4o System Cardcited by 4,467
  6. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  7. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  8. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  9. 2023Let's Verify Step by Stepcited by 3,598
  10. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  11. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  12. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
34 more
  1. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  2. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  3. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  4. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  5. 2019Towards VQA Models That Can Readcited by 1,696
  6. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,449
  7. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,288
  8. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,193
  9. 2023A Survey on Multimodal Large Language Modelscited by 898
  10. 2016A Diagram Is Worth A Dozen Imagescited by 793
  11. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 740
  12. 2020SummEval: Re-evaluating Summarization Evaluationcited by 666
  13. 2025Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoningcited by 540
  14. 2023RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedbackcited by 404
  15. 2023UltraFeedback: Boosting Language Models with Scaled AI Feedbackcited by 394
  16. 2024DataComp-LM: In search of the next generation of training sets for language modelscited by 381
  17. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  18. 2023JudgeLM: Fine-tuned Large Language Models are Scalable Judgescited by 351
  19. 2024Skywork-Reward: Bag of Tricks for Reward Modeling in LLMscited by 322
  20. 2024DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Headscited by 283
  21. 2025Inference-Time Scaling for Generalist Reward Modelingcited by 233
  22. 2024Aligning Modalities in Vision Large Language Models via Preference Fine-tuningcited by 197
  23. 2023Multimodal Large Language Models: A Surveycited by 193
  24. 2024Building and better understanding vision-language models: insights and future directionscited by 169
  25. 2019Mastering Complex Control in MOBA Games with Deep Reinforcement Learningcited by 150
  26. 2024RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthinesscited by 129
  27. 2024HelpSteer2-Preference: Complementing Ratings with Preferencescited by 129
  28. 2024OffsetBias: Leveraging Debiased Data for Tuning Evaluatorscited by 94
  29. 2024ChatQA: Surpassing GPT-4 on Conversational QA and RAGcited by 90
  30. 2025MM-RLHF: The Next Step Forward in Multimodal LLM Alignmentcited by 79
  31. 2024WildVision: Evaluating Vision-Language Models in the Wild with Human Preferencescited by 76
  32. 2024VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignmentcited by 56
  33. 2023YUAN 2.0: A Large Language Model with Localized Filtering-based Attentioncited by 9
  34. 2025MMTABREAL: Real-World Benchmark for Multimodal Table Understandingcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Yuan3.0 Ultra: A Trillion-Parameter Enterprise-Oriented MoE LLMcited by 0
  2. 2026A First-Principles Theory of Slow Thinking and Active Perceptioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
  2. 2025FlashThink: An Early Exit Method For Efficient Reasoning
  3. 2026JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency
  4. 2025Compute-Accuracy Pareto Frontiers for Open-Source Reasoning Large Language Models
  5. 2025Introducing LongCat-Flash-Thinking: A Technical Report
  6. 2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale
  7. 2026LongCat-Flash-Thinking-2601 Technical Report
  8. 2025Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models