Daily Papers of 2026-04-29

  1. Recursive Multi-Agent Systems 238 upvotes, #1 of 2026-04-29
  2. Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora 90 upvotes, #2 of 2026-04-29
  3. DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios 42 upvotes, #3 of 2026-04-29
  4. AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery 30 upvotes, #4 of 2026-04-29
  5. Meta-CoT: Enhancing Granularity and Generalization in Image Editing 25 upvotes, #5 of 2026-04-29
  6. Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models 24 upvotes, #6 of 2026-04-29
  7. Mutual Forcing: Dual-Mode Self-Evolution for Fast Autoregressive Audio-Video Character Generation 17 upvotes, #7 of 2026-04-29
  8. Co-Director: Agentic Generative Video Storytelling 16 upvotes, #8 of 2026-04-29
  9. Step-Audio-R1.5 Technical Report 16 upvotes, #8 of 2026-04-29
  10. Toward Scalable Terminal Task Synthesis via Skill Graphs 11 upvotes, #10 of 2026-04-29
  11. The Last Harness You'll Ever Build 7 upvotes, #11 of 2026-04-29
  12. TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents 7 upvotes, #11 of 2026-04-29
  13. BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate 7 upvotes, #11 of 2026-04-29
  14. GoClick: Lightweight Element Grounding Model for Autonomous GUI Interaction 6 upvotes, #14 of 2026-04-29
  15. MAIC-UI: Making Interactive Courseware with Generative UI 6 upvotes, #14 of 2026-04-29
  16. Preferences of a Voice-First Nation: Large-Scale Pairwise Evaluation and Preference Analysis for TTS in Indian Languages 3 upvotes, #16 of 2026-04-29
  17. Seeing Isn't Believing: Uncovering Blind Spots in Evaluator Vision-Language Models 3 upvotes, #16 of 2026-04-29
  18. V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think 3 upvotes, #16 of 2026-04-29
  19. AutoGUI-v2: A Comprehensive Multi-Modal GUI Functionality Understanding Benchmark 3 upvotes, #16 of 2026-04-29
  20. Offline Evaluation Measures of Fairness in Recommender Systems 1 upvotes, #20 of 2026-04-29
  21. IAM: Identity-Aware Human Motion and Shape Joint Generation 1 upvotes, #20 of 2026-04-29
  22. A Systematic Post-Train Framework for Video Generation 1 upvotes, #20 of 2026-04-29

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.