Best AI papers explained

512 Episodes

1. Self-improving LLM agents at Test-Time

   Published: 27/10/2025
2. KL-Regularized Reinforcement Learning is designed to Mode Collapse

   Published: 27/10/2025
3. How do LLMs use their depth?

   Published: 27/10/2025
4. Thought Communication in Multiagent Collaboration

   Published: 27/10/2025
5. Reasoning with Sampling: Base Models Outperform RL

   Published: 26/10/2025
6. Continual Learning via Sparse Memory Finetuning

   Published: 26/10/2025
7. Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences

   Published: 24/10/2025
8. The Coverage Principle: How Pre-Training Enables Post-Training

   Published: 24/10/2025
9. The Era of Real-World Human Interaction: RL from User Conversations

   Published: 24/10/2025
10. Agent Learning via Early Experience

    Published: 24/10/2025
11. Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL

    Published: 22/10/2025
12. Rewriting History: A Recipe for Interventional Analyses to Study Data Effects on Model Behavior

    Published: 22/10/2025
13. A Definition of AGI

    Published: 22/10/2025
14. Provably Learning from Language Feedback

    Published: 21/10/2025
15. In-Context Learning for Pure Exploration

    Published: 21/10/2025
16. On the Role of Preference Variance in Preference Optimization

    Published: 20/10/2025
17. Training LLM Agents to Empower Humans

    Published: 20/10/2025
18. Richard Sutton Declares LLMs a Dead End

    Published: 20/10/2025
19. Demystifying Reinforcement Learning in Agentic Reasoning

    Published: 19/10/2025
20. Emergent coordination in multi-agent language models

    Published: 19/10/2025