Best AI papers explained

550 Episoade

1. PLAN-AND-ACT: LLM Agent Planning with Synthetic Data

   Publicat: 08.04.2025
2. SEARCH-R1: LLMs Learn to Reason and Search via Reinforcement Learning

   Publicat: 08.04.2025
3. The Theory of the Firm: Information, Incentives, and Organization

   Publicat: 08.04.2025
4. Four Formalizable Theories of the Firm

   Publicat: 08.04.2025
5. Efficient Tool Use with Chain-of-Abstraction Reasoning

   Publicat: 06.04.2025
6. CodeTool: Process Supervision for Enhanced LLM Tool Invocation

   Publicat: 06.04.2025
7. Evaluating LLM Agents in Multi-Turn Conversations: A Survey

   Publicat: 06.04.2025
8. Epistemic Alignment in User-LLM Knowledge Delivery

   Publicat: 06.04.2025
9. MCP is (not) all you need

   Publicat: 06.04.2025
10. AI, Human Skills, and Competitive Advantage in Chess

    Publicat: 05.04.2025
11. Inference-Time Scaling for Generalist Reward Modeling

    Publicat: 04.04.2025
12. Optimal Pure Exploration in Linear Bandits via Sampling

    Publicat: 04.04.2025
13. Presidential Address: The Economist as Designer in the Innovation Process for Socially Impactful Digital Products

    Publicat: 04.04.2025
14. Emergent Symbolic Mechanisms for Reasoning in Large Language Models

    Publicat: 03.04.2025
15. Inference-Time Alignment: Coverage, Scaling, and Optimality

    Publicat: 03.04.2025
16. Sharpe Ratio-Guided Active Learning for Preference Optimization

    Publicat: 03.04.2025
17. Active Learning for Adaptive In-Context Prompt Design

    Publicat: 03.04.2025
18. Visual Chain-of-Thought Reasoning for Vision-Language-Action Models

    Publicat: 03.04.2025
19. On the Biology of a Large Language Model

    Publicat: 01.04.2025
20. Async-TB: Asynchronous Trajectory Balance for Scalable LLM RL

    Publicat: 01.04.2025