Daily Papers of 2025-09-11

  1. A Survey of Reinforcement Learning for Large Reasoning Models 156 upvotes, #1 of 2025-09-11
  2. RewardDance: Reward Scaling in Visual Generation 65 upvotes, #2 of 2025-09-11
  3. 3D and 4D World Modeling: A Survey 55 upvotes, #3 of 2025-09-11
  4. AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning 55 upvotes, #3 of 2025-09-11
  5. CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models 28 upvotes, #5 of 2025-09-11
  6. P3-SAM: Native 3D Part Segmentation 16 upvotes, #6 of 2025-09-11
  7. The Majority is not always right: RL training for solution aggregation 16 upvotes, #6 of 2025-09-11
  8. Hunyuan-MT Technical Report 13 upvotes, #8 of 2025-09-11
  9. <think> So let's replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs 11 upvotes, #9 of 2025-09-11
  10. Statistical Methods in Generative AI 10 upvotes, #10 of 2025-09-11
  11. EnvX: Agentize Everything with Agentic AI 6 upvotes, #11 of 2025-09-11
  12. HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants 3 upvotes, #12 of 2025-09-11

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.