mlsanityData to 7 Oct 2026

Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity

arXiv 2607.00248 ↗First posted 30 Jun 2026cs.AIcited by 48

Not on the map. Why?

Abstract (arXiv)

We present Seed2.0, a model series that takes a meaningful step toward solving complex, real-world tasks. Our approach begins with identifying users' genuine needs and constructing a reliable, forward-looking evaluation system by selecting and abstracting benchmarks grounded in these needs and in realistic, complex scenarios. Guided by this evaluation system, Seed2.0 targets two persistent challenges, long-tail knowledge and complex instruction following, substantially improving the model's reliability on intricate, long-horizon tasks. Beyond these, Seed2.0 delivers world-leading reasoning intelligence, visual understanding, and search capabilities that address the most common needs of a broad user base. Through extensive real-world use cases documented in this model card, we demonstrate that Seed2.0 begins to exhibit the ability to handle initial complex real-world tasks, delivering greater value to hundreds of millions of users.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Jun 2026.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 48.

48 papers.

Sort:

By area:

  1. 2026HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Bettercited by 14
  2. 2026UI-MOPD: Multi-Platform On-Policy Distillation for Unified GUI Agentscited by 7
  3. 2026Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoningcited by 6
  4. 2026SceneActBench: Can Agents Act on the 3D Scenes They See?cited by 3
  5. 2026Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agentscited by 3
  6. 2026StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understandingcited by 3
  7. 2026SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Taskcited by 2
  8. 2026Douyin Multimodal Embedding Model Technical Reportcited by 2
  9. 2026FIRM-Video: Check Before You Score for Reliable Text-to-Video Reward Modelingcited by 2
  10. 2026Qwen3.8-Omni: Towards Native Omni-Modal Agentscited by 2
  11. 2026Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reportscited by 1
  12. 2026ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignmentcited by 1
36 more
  1. 2026Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMscited by 1
  2. 2026UrbanGround: From Local Perception to Spatial Agency in a Real-Scale Citycited by 1
  3. 2026LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigationcited by 1
  4. 2026UI-Venus-2 Technical Reportcited by 1
  5. 2026Thinking with Cameras: Active Visual Reasoning via Dynamic Viewpoint Control for Surveillance Video Understandingcited by 1
  6. 2026Online Video Agent Harness for Long Video Understandingcited by 1
  7. 2026Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal Interactioncited by 1
  8. 2026Enhancing Fitness Intelligence through Domain-Specific LLM Post-Trainingcited by 0
  9. 2026UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemmacited by 0
  10. 2026DecoupleMix: Decoupled Ratio Search and Convex Allocation for Scalable VLM Data Recipescited by 0
  11. 2026Models as Tools: An Agentic Coordination Framework for Unified Multimodal Visual Trackingcited by 0
  12. 2026MT-Web2Code: Benchmarking Coding Agents on Multi-Turn Regional Reconstruction and Localized Modificationcited by 0
  13. 2026FactorDrive: Adaptive Multi-Step Reasoning Driven by Planning-Critical Factors for End-to-End Autonomous Drivingcited by 0
  14. 2026VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understandingcited by 0
  15. 2026OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMscited by 0
  16. 2026Repo2Skill-Evo: Repository Skills Go Stale in Silencecited by 0
  17. 2026Real-World Knowledge-Guided Change Data Synthesis for Remote Sensingcited by 0
  18. 2026Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding Scenarioscited by 0
  19. 2026Ancient-Bench: A Comprehensive Multi-millennial, Multi-medium, and Multi-script Benchmark for Ancient Chinese Artifact Text Recognitioncited by 0
  20. 2026CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Languagecited by 0
  21. 2026RealCADBench: Benchmarking Parametric CAD Modeling from Industrial Design Intentscited by 0
  22. 2026VisCAD: A Foundation Model Suite with Multimodal Industrial CAD Intelligencecited by 0
  23. 2026DAREBench: Deployment-Aware and Reliable Evaluation of Models as Agentscited by 0
  24. 2026V-ICAL Bench: Evaluating Video In-Context Learning for Multimodal Agents in Interactive Environmentscited by 0
  25. 2026NoteVQA: Benchmarking VLMs on Real-Life Questions from Human Communitiescited by 0
  26. 2026OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialoguecited by 0
  27. 2026OptiSkill: A Hierarchical and Evolving SkillBank for LLM-Based Optimization Modelingcited by 0
  28. 2026TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Tracescited by 0
  29. 2026PhysFieldBench: Can Multimodal Models Understand Physical Fields?cited by 0
  30. 2026Xiaomi-OCR-0 Technical Reportcited by 0
  31. 2026EviRover: Reinforcing Agentic Perception Beyond a Glancecited by 0
  32. 2026Video Prediction Policy 2: Predict Better, Act Bettercited by 0
  33. 2026SAVU-BENCH: A Real-World Benchmark for Spatial Audio-Visual Understandingcited by 0
  34. 2026When History Helps and Hurts: Selective History Use across Multimodal Turnscited by 0
  35. 2026OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Videocited by 0
  36. 2026OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioningcited by 0