Daily Papers of 2026-01-15

  1. DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation 121 upvotes, #1 of 2026-01-15
  2. Controlled Self-Evolution for Algorithmic Code Optimization 110 upvotes, #2 of 2026-01-15
  3. MAXS: Meta-Adaptive Exploration with LLM Agents 93 upvotes, #3 of 2026-01-15
  4. A^3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation 82 upvotes, #4 of 2026-01-15
  5. Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning 57 upvotes, #5 of 2026-01-15
  6. Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning 50 upvotes, #6 of 2026-01-15
  7. EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines 40 upvotes, #7 of 2026-01-15
  8. SkinFlow: Efficient Information Transmission for Open Dermatological Diagnosis via Dynamic Visual Encoding and Staged RL 37 upvotes, #8 of 2026-01-15
  9. OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG 32 upvotes, #9 of 2026-01-15
  10. OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding 25 upvotes, #10 of 2026-01-15
  11. TranslateGemma Technical Report 19 upvotes, #11 of 2026-01-15
  12. FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection 16 upvotes, #12 of 2026-01-15
  13. ExpSeek: Self-Triggered Experience Seeking for Web Agents 16 upvotes, #12 of 2026-01-15
  14. Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models 13 upvotes, #14 of 2026-01-15
  15. Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World Validity 12 upvotes, #15 of 2026-01-15
  16. Efficient Camera-Controlled Video Generation of Static Scenes via Sparse Diffusion and 3D Rendering 8 upvotes, #16 of 2026-01-15
  17. Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments 6 upvotes, #17 of 2026-01-15
  18. Geometric Stability: The Missing Axis of Representations 6 upvotes, #17 of 2026-01-15
  19. The AI Hippocampus: How Far are We From Human Memory? 5 upvotes, #19 of 2026-01-15
  20. No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning 4 upvotes, #20 of 2026-01-15
  21. Focal Guidance: Unlocking Controllability from Semantic-Weak Layers in Video Diffusion Models 4 upvotes, #20 of 2026-01-15
  22. SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning 3 upvotes, #22 of 2026-01-15
  23. Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning 3 upvotes, #22 of 2026-01-15
  24. DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing 3 upvotes, #22 of 2026-01-15
  25. sui-1: Grounded and Verifiable Long-Form Summarization 2 upvotes, #25 of 2026-01-15
  26. SampoNLP: A Self-Referential Toolkit for Morphological Analysis of Subword Tokenizers 1 upvotes, #26 of 2026-01-15
  27. Cluster Workload Allocation: Semantic Soft Affinity Using Natural Language Processing 1 upvotes, #26 of 2026-01-15

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.