Daily Papers of 2026-02-10

  1. Weak-Driven Learning: How Weak Agents make Strong Agents Stronger 254 upvotes, #1 of 2026-02-10
  2. TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents 196 upvotes, #2 of 2026-02-10
  3. QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining 180 upvotes, #3 of 2026-02-10
  4. MOVA: Towards Scalable and Synchronized Video-Audio Generation 151 upvotes, #4 of 2026-02-10
  5. Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models 133 upvotes, #5 of 2026-02-10
  6. AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents 70 upvotes, #6 of 2026-02-10
  7. InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery 68 upvotes, #7 of 2026-02-10
  8. Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning 67 upvotes, #8 of 2026-02-10
  9. LLaDA2.1: Speeding Up Text Diffusion via Token Editing 66 upvotes, #9 of 2026-02-10
  10. RLinf-USER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI 53 upvotes, #10 of 2026-02-10
  11. Towards Agentic Intelligence for Materials Science 45 upvotes, #11 of 2026-02-10
  12. Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO 42 upvotes, #12 of 2026-02-10
  13. Improving Data and Reward Design for Scientific Reasoning in Large Language Models 39 upvotes, #13 of 2026-02-10
  14. GEBench: Benchmarking Image Generation Models as GUI Environments 38 upvotes, #14 of 2026-02-10
  15. Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition 28 upvotes, #15 of 2026-02-10
  16. Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory 27 upvotes, #16 of 2026-02-10
  17. GISA: A Benchmark for General Information-Seeking Assistant 26 upvotes, #17 of 2026-02-10
  18. LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth 24 upvotes, #18 of 2026-02-10
  19. AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research 21 upvotes, #19 of 2026-02-10
  20. Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration? 21 upvotes, #19 of 2026-02-10
  21. WorldCompass: Reinforcement Learning for Long-Horizon World Models 20 upvotes, #21 of 2026-02-10
  22. LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning 18 upvotes, #22 of 2026-02-10
  23. NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models 15 upvotes, #23 of 2026-02-10
  24. Context Compression via Explicit Information Transmission 14 upvotes, #24 of 2026-02-10
  25. Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models 13 upvotes, #25 of 2026-02-10
  26. RelayGen: Intra-Generation Model Switching for Efficient Reasoning 11 upvotes, #26 of 2026-02-10
  27. When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning 9 upvotes, #27 of 2026-02-10
  28. Reliable and Responsible Foundation Models: A Comprehensive Survey 8 upvotes, #28 of 2026-02-10
  29. How2Everything: Mining the Web for How-To Procedures to Evaluate and Improve LLMs 8 upvotes, #28 of 2026-02-10
  30. Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion 7 upvotes, #30 of 2026-02-10
  31. Thinking Makes LLM Agents Introverted: How Mandatory Thinking Can Backfire in User-Engaged Agents 7 upvotes, #30 of 2026-02-10
  32. CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs 6 upvotes, #32 of 2026-02-10
  33. Data Science and Technology Towards AGI Part I: Tiered Data Management 5 upvotes, #33 of 2026-02-10
  34. Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control 4 upvotes, #34 of 2026-02-10
  35. SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis 4 upvotes, #34 of 2026-02-10
  36. ECO: Energy-Constrained Optimization with Reinforcement Learning for Humanoid Walking 3 upvotes, #36 of 2026-02-10
  37. Optimal Turkish Subword Strategies at Scale: Systematic Evaluation of Data, Vocabulary, Morphology Interplay 3 upvotes, #36 of 2026-02-10
  38. Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality 3 upvotes, #36 of 2026-02-10
  39. WildReward: Learning Reward Models from In-the-Wild Human Interactions 3 upvotes, #36 of 2026-02-10
  40. MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE 3 upvotes, #36 of 2026-02-10
  41. Flexible Entropy Control in RLVR with Gradient-Preserving Perspective 3 upvotes, #36 of 2026-02-10
  42. Col-Bandit: Zero-Shot Query-Time Pruning for Late-Interaction Retrieval 2 upvotes, #42 of 2026-02-10
  43. KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs 2 upvotes, #42 of 2026-02-10
  44. Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning 2 upvotes, #42 of 2026-02-10
  45. Aster: Autonomous Scientific Discovery over 20x Faster Than Existing Methods 2 upvotes, #42 of 2026-02-10
  46. On Randomness in Agentic Evals 2 upvotes, #42 of 2026-02-10
  47. FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language Models 2 upvotes, #42 of 2026-02-10
  48. Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Exploration 1 upvotes, #48 of 2026-02-10
  49. AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization 1 upvotes, #48 of 2026-02-10
  50. Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attacks 1 upvotes, #48 of 2026-02-10
  51. Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model 1 upvotes, #48 of 2026-02-10
  52. GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design 1 upvotes, #48 of 2026-02-10
  53. Learning-guided Kansa collocation for forward and inverse PDEs beyond linearity 1 upvotes, #48 of 2026-02-10
  54. CauScale: Neural Causal Discovery at Scale 1 upvotes, #48 of 2026-02-10
  55. Statistical Learning Theory in Lean 4: Empirical Processes from Scratch 0 upvotes, #55 of 2026-02-10
  56. f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment 0 upvotes, #55 of 2026-02-10
  57. Reasoning-Augmented Representations for Multimodal Retrieval 0 upvotes, #55 of 2026-02-10
  58. dewi-kadita: A Python Library for Idealized Fish Schooling Simulation with Entropy-Based Diagnostics 0 upvotes, #55 of 2026-02-10

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.