Daily Papers of 2026-11-04

  1. Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systems 94 upvotes, #1 of 2026-11-04
  2. Words Caught in the Heart: Simulating Person-Specific Expression for Self-Opaque Clients in Psychotherapy 66 upvotes, #2 of 2026-11-04
  3. Think Less, Locally: Local Preference Learning for Reasoning Compression 64 upvotes, #3 of 2026-11-04
  4. MoviEdit: Long-form Multi-Shot Video Editing Made Easy 60 upvotes, #4 of 2026-11-04
  5. Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling 48 upvotes, #5 of 2026-11-04
  6. DreamX: Video Diffusion Model is a Universal Latent Action Learner 46 upvotes, #6 of 2026-11-04
  7. RoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wild 42 upvotes, #7 of 2026-11-04
  8. Factorized MLLM Embeddings for Composed Image Retrieval 41 upvotes, #8 of 2026-11-04
  9. Axion 1.0: Open Agent Foundation Models, Simplified 38 upvotes, #9 of 2026-11-04
  10. ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents 33 upvotes, #10 of 2026-11-04
  11. YANAMI: A Large-Scale Multimodal Dataset and Benchmark for Multiturn Stateful Interaction 26 upvotes, #11 of 2026-11-04
  12. EvoTeam: Multi-Agent Collaboration via Evolving Teams 23 upvotes, #12 of 2026-11-04
  13. VidUEU-Agent: A Data-Curation Agent for Multimodal Understanding, Editing, and Unified Tasks 23 upvotes, #12 of 2026-11-04
  14. WebHarbor: Docking Real Websites for Evolving GUI Agent Environments 19 upvotes, #14 of 2026-11-04
  15. ParetoSaddler: Pareto-Guided Optimization of Agent Harnesses for Quality and Cost 16 upvotes, #15 of 2026-11-04
  16. MoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery 15 upvotes, #16 of 2026-11-04
  17. SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding 15 upvotes, #16 of 2026-11-04
  18. Mage-VL-Cowork: A Full Training Recipe to Learn Hybrid Computer Use From Evolved Harnesses 11 upvotes, #18 of 2026-11-04
  19. "Shall We Approve?" Consequence-Aware Approval for Autonomous Coding Agents 11 upvotes, #18 of 2026-11-04
  20. Recursa: Toward Recursively Self-Improving Foundation Model Systems 10 upvotes, #20 of 2026-11-04
  21. FlowTranslator: Training-Free In-Image Machine Translation with Flow-Based Editing 9 upvotes, #21 of 2026-11-04
  22. PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations 9 upvotes, #21 of 2026-11-04
  23. Every Token Needs Its Own Teacher: Multi-teacher Adaptive On-policy Self-distillation 8 upvotes, #23 of 2026-11-04
  24. Near-Zero Token Embeddings Silently Stall Training in Gated Sequence Models 7 upvotes, #24 of 2026-11-04
  25. Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks? 6 upvotes, #25 of 2026-11-04
  26. Can AI Reviewers See Your Efforts to Improve Your Paper? A Large-Scale Study of Paper Revision Trajectories 6 upvotes, #25 of 2026-11-04
  27. LOLPlay: Benchmarking Real-Time Visual Agents in League of Legends 6 upvotes, #25 of 2026-11-04
  28. Adversarial Speculative Reasoning Improves Long Horizon Agents 6 upvotes, #25 of 2026-11-04
  29. You don't need long context 5 upvotes, #29 of 2026-11-04
  30. Dory1.0-4B: A Looped Normalized-GPT 4 upvotes, #30 of 2026-11-04
  31. RoboTryOn: Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On 4 upvotes, #30 of 2026-11-04
  32. Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena 3 upvotes, #32 of 2026-11-04
  33. SeMo3D: Unifying 3D Generation, Editing, and Completion via Selective Modeling 3 upvotes, #32 of 2026-11-04
  34. Do We Need an LLM to Know Why Sources Conflict? Decision Models for Knowledge-Conflict Typing in RAG 2 upvotes, #34 of 2026-11-04
  35. Muon Makes the First Mixture-of-Experts Layer Harder to Balance 2 upvotes, #34 of 2026-11-04
  36. Where to Learn and How Far to Roll Out: Efficient Adaptive Training for GUI Agents 2 upvotes, #34 of 2026-11-04
  37. What We Keep of What We Forget: Replacement Operators and Routing Semantics in Training-Free MoE Expert Pruning 2 upvotes, #34 of 2026-11-04
  38. Is Your Long-Horizon Benchmark Really Deep? Measuring and Synthesizing Depth in Terminal Tasks 2 upvotes, #34 of 2026-11-04
  39. Every Pixel Is an Option: A System One Model for Medical Ultrasound Biometry 2 upvotes, #34 of 2026-11-04
  40. BEND 2.0: Benchmarking the Capabilities Needed to Design DNA 2 upvotes, #34 of 2026-11-04
  41. Is Forgetting Unified? Exploring Concept Unlearning in Unified Multimodal Models 2 upvotes, #34 of 2026-11-04
  42. GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data 1 upvotes, #42 of 2026-11-04
  43. Auto-Research Agent on MSA Organization to Improve Protein-Protein Complex Structure Prediction 1 upvotes, #42 of 2026-11-04
  44. Enhancing Stock Market Information Retrieval with Retrieval-Augmented Generation 1 upvotes, #42 of 2026-11-04
  45. Kierston & KierstonBench: Simulation of Allentown, PA and Evaluation of Language Models in Crime Investigation and Surveillance Tasks 1 upvotes, #42 of 2026-11-04
  46. Going Deeper With Memories 1 upvotes, #42 of 2026-11-04

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.