Best AI papers explained

550 Episodes

1. PREFDISCO: Evaluating Proactive Personalization through Interactive Preference Discovery

   Published: 11/12/2025
2. Reusing pre-training data at test time is a compute multiplier

   Published: 11/10/2025
3. Scaling Agent Learning via Experience Synthesis

   Published: 11/9/2025
4. Continuous Autoregressive Language Models

   Published: 11/8/2025
5. Toward a Theory of Agents as Tool-Use Decision-Makers

   Published: 11/7/2025
6. Nested Learning: The Illusion of Deep Learning Architectures

   Published: 11/5/2025
7. GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding

   Published: 11/5/2025
8. Beyond a million tokens: benchmarking and enhancing long-term memory in llms

   Published: 11/4/2025
9. Agentic Economic Modeling

   Published: 11/3/2025
10. Emergent Introspective Awareness in Large Language Models

    Published: 11/3/2025
11. Can Large reasoning models self-train?

    Published: 11/1/2025
12. ALITA-G: Self-Evolving Generative Agent for Agent Generation

    Published: 11/1/2025
13. Self-improving LLM agents at test-time

    Published: 10/30/2025
14. Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization

    Published: 10/30/2025
15. Language models are injective and hence invertible

    Published: 10/30/2025
16. ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

    Published: 10/29/2025
17. RLAD: Training LLMs to Discover Abstractions

    Published: 10/29/2025
18. How to Train Your Advisor: Steering Black-Box LLMs with ADVISOR MODELS

    Published: 10/29/2025
19. Self-improving LLM agents at Test-Time

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

    Published: 10/27/2025