Daily Papers of 2026-05-28

  1. Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players 419 upvotes, #1 of 2026-05-28
  2. ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation 87 upvotes, #2 of 2026-05-28
  3. Agent Explorative Policy Optimization for Multimodal Agentic Reasoning 87 upvotes, #2 of 2026-05-28
  4. From Pixels to Words -- Towards Native One-Vision Models at Scale 72 upvotes, #4 of 2026-05-28
  5. Self-Improving Language Models with Bidirectional Evolutionary Search 59 upvotes, #5 of 2026-05-28
  6. ResearchMath-14K: Scaling Research-Level Mathematics via Agents 49 upvotes, #6 of 2026-05-28
  7. DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes 46 upvotes, #7 of 2026-05-28
  8. GEM: Generative Supervision Helps Embodied Intelligence 41 upvotes, #8 of 2026-05-28
  9. MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems 39 upvotes, #9 of 2026-05-28
  10. Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents 38 upvotes, #10 of 2026-05-28
  11. ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence 35 upvotes, #11 of 2026-05-28
  12. Rethinking Memory as Continuously Evolving Connectivity 34 upvotes, #12 of 2026-05-28
  13. Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems 31 upvotes, #13 of 2026-05-28
  14. SkillGrad: Optimizing Agent Skills Like Gradient Descent 27 upvotes, #14 of 2026-05-28
  15. AI Research Agents Narrow Scientific Exploration 25 upvotes, #15 of 2026-05-28
  16. OSP-Next: Efficient High-Quality Video Generation with Sparse Sequence Parallelism, HiF8 Quantization, and Reinforcement Learning 24 upvotes, #16 of 2026-05-28
  17. Triplet-Block Diffusion RWKV 23 upvotes, #17 of 2026-05-28
  18. Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization 23 upvotes, #17 of 2026-05-28
  19. GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar Reselection 23 upvotes, #17 of 2026-05-28
  20. How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning 20 upvotes, #20 of 2026-05-28
  21. Advancing Creative Physical Intelligence in Large Multimodal Models 19 upvotes, #21 of 2026-05-28
  22. Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving 17 upvotes, #22 of 2026-05-28
  23. GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation 17 upvotes, #22 of 2026-05-28
  24. Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders 15 upvotes, #24 of 2026-05-28
  25. VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild 15 upvotes, #24 of 2026-05-28
  26. HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs 15 upvotes, #24 of 2026-05-28
  27. LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know? 15 upvotes, #24 of 2026-05-28
  28. CubePart: An Open-Vocabulary Part-Controllable 3D Generator 14 upvotes, #28 of 2026-05-28
  29. Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution 13 upvotes, #29 of 2026-05-28
  30. Less is More: Early Stopping Rollout for On-Policy Distillation 13 upvotes, #29 of 2026-05-28
  31. Lost in Sampling: Assessing Lexical Reachability in LLMs via the Word Coverage Score (WCS) 13 upvotes, #29 of 2026-05-28
  32. GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning 12 upvotes, #32 of 2026-05-28
  33. The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages 12 upvotes, #32 of 2026-05-28
  34. AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation 11 upvotes, #34 of 2026-05-28
  35. OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration 11 upvotes, #34 of 2026-05-28
  36. Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory 10 upvotes, #36 of 2026-05-28
  37. Category-Level 3D Correspondence in Camera Space via Morphable Object Priors 9 upvotes, #37 of 2026-05-28
  38. AgensFlow: A Coordination-Policy Substrate for Multi-Agent Systems 8 upvotes, #38 of 2026-05-28
  39. Models That Know How Evaluations Are Designed Score Safer 8 upvotes, #38 of 2026-05-28
  40. PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective 8 upvotes, #38 of 2026-05-28
  41. PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft 7 upvotes, #41 of 2026-05-28
  42. LACUNA: Safe Agents as Recursive Program Holes 7 upvotes, #41 of 2026-05-28
  43. AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning 6 upvotes, #43 of 2026-05-28
  44. AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions 6 upvotes, #43 of 2026-05-28
  45. Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization 6 upvotes, #43 of 2026-05-28
  46. ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations 6 upvotes, #43 of 2026-05-28
  47. OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents 6 upvotes, #43 of 2026-05-28
  48. Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration 6 upvotes, #43 of 2026-05-28
  49. Breaking the Chains of Probability: Neutrosophic Logic as a New Framework for Epistemic Uncertainty in Large Language Models 5 upvotes, #49 of 2026-05-28
  50. Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets 5 upvotes, #49 of 2026-05-28
  51. Unified Panoramic Geometry Estimation via Multi-View Foundation Models 4 upvotes, #51 of 2026-05-28
  52. Chartographer: Counterfactual Chart Generation for Evaluating Vision-Language Models 3 upvotes, #52 of 2026-05-28
  53. Revealing Algorithmic Deductive Circuits for Logical Reasoning 2 upvotes, #53 of 2026-05-28
  54. Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification 1 upvotes, #54 of 2026-05-28
  55. Growing a Neural Network in Breadth, Depth, and Time 1 upvotes, #54 of 2026-05-28
  56. BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting 1 upvotes, #54 of 2026-05-28
  57. Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems 1 upvotes, #54 of 2026-05-28
  58. Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion 0 upvotes, #58 of 2026-05-28
  59. How Accurate are Video Quality Models for Diffusion-Based Video Super-Resolution? 1 upvotes, #58 of 2026-05-28
  60. Clark Hash: Stateless Sparse Johnson-Lindenstrauss Quantization for Neural Embeddings 0 upvotes, #58 of 2026-05-28

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.