Best AI papers explained

145 Episodes

1. CodeTool: Process Supervision for Enhanced LLM Tool Invocation

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

   Published: 4/6/2025
3. Epistemic Alignment in User-LLM Knowledge Delivery

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

   Published: 4/6/2025
5. AI, Human Skills, and Competitive Advantage in Chess

   Published: 4/5/2025
6. Inference-Time Scaling for Generalist Reward Modeling

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

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

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

   Published: 4/3/2025
10. Inference-Time Alignment: Coverage, Scaling, and Optimality

    Published: 4/3/2025
11. Sharpe Ratio-Guided Active Learning for Preference Optimization

    Published: 4/3/2025
12. Active Learning for Adaptive In-Context Prompt Design

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

    Published: 4/3/2025
14. On the Biology of a Large Language Model

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

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

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

    Published: 3/31/2025
18. Why MCP won

    Published: 3/31/2025
19. SWEET-RL: Training LLM Agents for Collaborative Reasoning

    Published: 3/31/2025
20. TheoryCoder: Bilevel Planning with Synthesized World Models

    Published: 3/30/2025