Best AI papers explained

527 Episodo

1. Four Formalizable Theories of the Firm

   Publicado: 8/4/2025
2. Efficient Tool Use with Chain-of-Abstraction Reasoning

   Publicado: 6/4/2025
3. CodeTool: Process Supervision for Enhanced LLM Tool Invocation

   Publicado: 6/4/2025
4. Evaluating LLM Agents in Multi-Turn Conversations: A Survey

   Publicado: 6/4/2025
5. Epistemic Alignment in User-LLM Knowledge Delivery

   Publicado: 6/4/2025
6. MCP is (not) all you need

   Publicado: 6/4/2025
7. AI, Human Skills, and Competitive Advantage in Chess

   Publicado: 5/4/2025
8. Inference-Time Scaling for Generalist Reward Modeling

   Publicado: 4/4/2025
9. Optimal Pure Exploration in Linear Bandits via Sampling

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

    Publicado: 4/4/2025
11. Emergent Symbolic Mechanisms for Reasoning in Large Language Models

    Publicado: 3/4/2025
12. Inference-Time Alignment: Coverage, Scaling, and Optimality

    Publicado: 3/4/2025
13. Sharpe Ratio-Guided Active Learning for Preference Optimization

    Publicado: 3/4/2025
14. Active Learning for Adaptive In-Context Prompt Design

    Publicado: 3/4/2025
15. Visual Chain-of-Thought Reasoning for Vision-Language-Action Models

    Publicado: 3/4/2025
16. On the Biology of a Large Language Model

    Publicado: 1/4/2025
17. Async-TB: Asynchronous Trajectory Balance for Scalable LLM RL

    Publicado: 1/4/2025
18. Instacart's Economics Team: A Hybrid Role in Tech

    Publicado: 31/3/2025
19. Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework

    Publicado: 31/3/2025
20. Why MCP won

    Publicado: 31/3/2025