Microsoft Research

Microsoft Research on Hugging Face Daily Papers: 69 papers, 9 in the top 3 of their day, 3 paper of the day.

  1. SIRIS: Can LLMs Tell When Simulation Errors Matter in AI-Driven Systems Research 12 upvotes, #16 of 2026-11-10
  2. Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents 19 upvotes, #12 of 2026-11-05
  3. MemSteer: Turning User Histories into Supervision for Agent Memory Optimization 9 upvotes, #19 of 2026-11-02
  4. Agent World Model in the Wild: Computer-Use Agent Environment Synthesis 101 upvotes, #8 of 2026-10-22
  5. Self-Evolving Coding Agents via Harness-Policy Optimization 56 upvotes, #10 of 2026-10-20
  6. TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents 6 upvotes, #49 of 2026-10-19
  7. APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation 31 upvotes, #22 of 2026-10-15
  8. DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling 17 upvotes, #30 of 2026-10-07
  9. CUAWright: A Minimal Unified Interface for Digital Agents 6 upvotes, #64 of 2026-10-05
  10. Reinforcing Agentic Creativity in Scientific Ideation with Night Science 5 upvotes, #64 of 2026-09-29
  11. Agensh: Scaling Organizational Intelligence to 1,024 Agents 27 upvotes, #12 of 2026-09-23
  12. ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models 18 upvotes, #16 of 2026-09-22
  13. BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence 30 upvotes, #11 of 2026-09-21
  14. ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks 62 upvotes, #4 of 2026-09-17
  15. Expert-Space Exploration in MoE Reinforcement Learning 5 upvotes, #28 of 2026-09-15
  16. StudentSim: Training LLM-based Student Simulators 485 upvotes, #1 of 2026-09-02
  17. Dion3: Full-Stack Orthogonal Updates 9 upvotes, #19 of 2026-08-17
  18. Full-bandwidth transformer 22 upvotes, #13 of 2026-08-14
  19. Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning 13 upvotes, #13 of 2026-08-10
  20. Weak-to-Strong On-Policy Distillation 56 upvotes, #4 of 2026-08-03
  21. Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale 13 upvotes, #26 of 2026-07-31
  22. Multi-Turn On-Policy Distillation with Prefix Replay 12 upvotes, #14 of 2026-07-24
  23. LLMs Get Lost in Evolving User Intent 24 upvotes, #9 of 2026-07-24
  24. LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks 14 upvotes, #19 of 2026-07-21
  25. RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources 141 upvotes, #2 of 2026-07-20
  26. ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving 31 upvotes, #3 of 2026-07-02
  27. Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement 7 upvotes, #17 of 2026-06-29
  28. ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction 4 upvotes, #27 of 2026-06-11
  29. Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts 52 upvotes, #5 of 2026-06-10
  30. Latent Spatial Memory for Video World Models 66 upvotes, #4 of 2026-06-09
  31. ECHO: Terminal Agents Learn World Models for Free 7 upvotes, #36 of 2026-05-26
  32. From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills 29 upvotes, #9 of 2026-05-25
  33. SkillOpt: Executive Strategy for Self-Evolving Agent Skills 212 upvotes, #1 of 2026-05-25
  34. Video Models Can Reason with Verifiable Rewards 11 upvotes, #19 of 2026-05-20
  35. Orchard: An Open-Source Agentic Modeling Framework 19 upvotes, #20 of 2026-05-15
  36. Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR 16 upvotes, #16 of 2026-05-12
  37. World-R1: Reinforcing 3D Constraints for Text-to-Video Generation 34 upvotes, #2 of 2026-04-28
  38. Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs 1 upvotes, #35 of 2026-04-22
  39. MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation 6 upvotes, #20 of 2026-04-17
  40. Universal YOCO for Efficient Depth Scaling 17 upvotes, #13 of 2026-04-02
  41. BizGenEval: A Systematic Benchmark for Commercial Visual Content Generation 11 upvotes, #23 of 2026-04-01
  42. Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? 47 upvotes, #2 of 2026-03-26
  43. Online Experiential Learning for Language Models 55 upvotes, #10 of 2026-03-18
  44. Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty 11 upvotes, #19 of 2026-03-17
  45. Sparse-BitNet: 1.58-bit LLMs are Naturally Friendly to Semi-Structured Sparsity 4 upvotes, #27 of 2026-03-10
  46. Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems 5 upvotes, #24 of 2026-03-10
  47. Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models 5 upvotes, #24 of 2026-03-10
  48. Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces 15 upvotes, #12 of 2026-03-10
  49. Proact-VL: A Proactive VideoLLM for Real-Time AI Companions 31 upvotes, #4 of 2026-03-05
  50. Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use 11 upvotes, #13 of 2026-03-04
  51. Reinforcement World Model Learning for LLM-based Agents 25 upvotes, #11 of 2026-02-06
  52. Efficient Autoregressive Video Diffusion with Dummy Head 8 upvotes, #31 of 2026-02-05
  53. Self-Hinting Language Models Enhance Reinforcement Learning 27 upvotes, #13 of 2026-02-05
  54. LIVE: Long-horizon Interactive Video World Modeling 12 upvotes, #19 of 2026-02-04
  55. Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability 9 upvotes, #37 of 2026-02-03
  56. Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge 38 upvotes, #2 of 2026-01-20
  57. X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests 40 upvotes, #5 of 2026-01-13
  58. Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding 3 upvotes, #18 of 2025-12-04
  59. Black-Box On-Policy Distillation of Large Language Models 39 upvotes, #4 of 2025-11-14
  60. The Collaboration Gap 21 upvotes, #6 of 2025-11-05
  61. Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets 9 upvotes, #14 of 2025-10-31
  62. Code Aesthetics with Agentic Reward Feedback 7 upvotes, #21 of 2025-10-28
  63. LoongRL:Reinforcement Learning for Advanced Reasoning over Long Contexts 58 upvotes, #3 of 2025-10-23
  64. BitNet Distillation 47 upvotes, #8 of 2025-10-17
  65. Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning 1 upvotes, #36 of 2025-10-16
  66. DocReward: A Document Reward Model for Structuring and Stylizing 26 upvotes, #12 of 2025-10-14
  67. Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective 7 upvotes, #33 of 2025-10-01
  68. PixelCraft: A Multi-Agent System for High-Fidelity Visual Reasoning on Structured Images 4 upvotes, #56 of 2025-09-30
  69. VibeVoice Technical Report 118 upvotes, #1 of 2025-08-27

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.