Best AI papers explained

529 Episodes

1. SEARCH-R1: LLMs Learn to Reason and Search via Reinforcement Learning

   Published: 8/04/2025
2. The Theory of the Firm: Information, Incentives, and Organization

   Published: 8/04/2025
3. Four Formalizable Theories of the Firm

   Published: 8/04/2025
4. Efficient Tool Use with Chain-of-Abstraction Reasoning

   Published: 6/04/2025
5. CodeTool: Process Supervision for Enhanced LLM Tool Invocation

   Published: 6/04/2025
6. Evaluating LLM Agents in Multi-Turn Conversations: A Survey

   Published: 6/04/2025
7. Epistemic Alignment in User-LLM Knowledge Delivery

   Published: 6/04/2025
8. MCP is (not) all you need

   Published: 6/04/2025
9. AI, Human Skills, and Competitive Advantage in Chess

   Published: 5/04/2025
10. Inference-Time Scaling for Generalist Reward Modeling

    Published: 4/04/2025
11. Optimal Pure Exploration in Linear Bandits via Sampling

    Published: 4/04/2025
12. Presidential Address: The Economist as Designer in the Innovation Process for Socially Impactful Digital Products

    Published: 4/04/2025
13. Emergent Symbolic Mechanisms for Reasoning in Large Language Models

    Published: 3/04/2025
14. Inference-Time Alignment: Coverage, Scaling, and Optimality

    Published: 3/04/2025
15. Sharpe Ratio-Guided Active Learning for Preference Optimization

    Published: 3/04/2025
16. Active Learning for Adaptive In-Context Prompt Design

    Published: 3/04/2025
17. Visual Chain-of-Thought Reasoning for Vision-Language-Action Models

    Published: 3/04/2025
18. On the Biology of a Large Language Model

    Published: 1/04/2025
19. Async-TB: Asynchronous Trajectory Balance for Scalable LLM RL

    Published: 1/04/2025
20. Instacart's Economics Team: A Hybrid Role in Tech

    Published: 31/03/2025