Best AI papers explained

456 Episodes

1. Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search

   Published: 5/29/2025
2. Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning

   Published: 5/29/2025
3. Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL

   Published: 5/29/2025
4. Value-Guided Search for Efficient Chain-of-Thought Reasoning

   Published: 5/29/2025
5. Shallow Preference Signals: Large Language model aligns even better without truncated data?

   Published: 5/29/2025
6. Gaming Tool Preferences in Agentic LLMs

   Published: 5/29/2025
7. Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)

   Published: 5/29/2025
8. LLM Populations Form Social Conventions and Collective Bias

   Published: 5/29/2025
9. LLM Generated Persona is a Promise with a Catch

   Published: 5/29/2025
10. Large Language Models for Digital Twin Simulation

    Published: 5/29/2025
11. From RL Distillation to Autonomous LLM Agents

    Published: 5/29/2025
12. Prompting, Auto-Prompting, and Human-AI Communication

    Published: 5/29/2025
13. Textual Gradients for LLM Optimization

    Published: 5/29/2025
14. Large Language Models as Markov Chains

    Published: 5/28/2025
15. Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation

    Published: 5/28/2025
16. Selective induction heads: how transformers select causal structures in context

    Published: 5/28/2025
17. The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains

    Published: 5/28/2025
18. How Transformers Learn Causal Structure with Gradient Descent

    Published: 5/28/2025
19. Planning anything with rigor: general-purpose zero-shot planning with llm-based formalized programming

    Published: 5/28/2025
20. Automated Design of Agentic Systems

    Published: 5/28/2025