Best AI papers explained

456 Episodes

1. All Roads Lead to Likelihood: RL for Fine-Tuning Value

   Published: 4/8/2025
2. ATLAS: Tuning Agents via Critical Step Learning

   Published: 4/8/2025
3. Thinking Faster by Writing Less: Chain of Draft Reasoning

   Published: 4/8/2025
4. Meta Plan Optimization for Boosting LLM Agents

   Published: 4/8/2025
5. L1: Length Controlled Reasoning with Reinforcement Learning

   Published: 4/8/2025
6. WikiBigEdit: Benchmarking Lifelong Knowledge Editing in LLMs

   Published: 4/8/2025
7. PLAN-AND-ACT: LLM Agent Planning with Synthetic Data

   Published: 4/8/2025
8. SEARCH-R1: LLMs Learn to Reason and Search via Reinforcement Learning

   Published: 4/8/2025
9. The Theory of the Firm: Information, Incentives, and Organization

   Published: 4/8/2025
10. Four Formalizable Theories of the Firm

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

    Published: 4/6/2025
12. CodeTool: Process Supervision for Enhanced LLM Tool Invocation

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

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

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

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

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

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

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

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

    Published: 4/3/2025