Best AI papers explained

534 Episoade

1. Thinking Faster by Writing Less: Chain of Draft Reasoning

   Publicat: 08.04.2025
2. Meta Plan Optimization for Boosting LLM Agents

   Publicat: 08.04.2025
3. L1: Length Controlled Reasoning with Reinforcement Learning

   Publicat: 08.04.2025
4. WikiBigEdit: Benchmarking Lifelong Knowledge Editing in LLMs

   Publicat: 08.04.2025
5. PLAN-AND-ACT: LLM Agent Planning with Synthetic Data

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

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

   Publicat: 08.04.2025
8. Four Formalizable Theories of the Firm

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

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

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

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

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

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

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

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

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

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

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

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

    Publicat: 03.04.2025