Best AI papers explained

425 Episodes

1. When and Why LLMs Fail to Reason Globally

   Published: 5/31/2025
2. IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis

   Published: 5/31/2025
3. No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference

   Published: 5/31/2025
4. Accelerating RL for LLM Reasoning with Optimal Advantage Regression

   Published: 5/31/2025
5. Statistical Inference for Online Algorithms

   Published: 5/31/2025
6. Prismatic Synthesis for Diverse LLM Reasoning Data

   Published: 5/31/2025
7. Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents

   Published: 5/31/2025
8. The Agentic Economy

   Published: 5/30/2025
9. Statistics for Large Language Models

   Published: 5/29/2025
10. Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search

    Published: 5/29/2025
11. Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning

    Published: 5/29/2025
12. Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL

    Published: 5/29/2025
13. Value-Guided Search for Efficient Chain-of-Thought Reasoning

    Published: 5/29/2025
14. Shallow Preference Signals: Large Language model aligns even better without truncated data?

    Published: 5/29/2025
15. Gaming Tool Preferences in Agentic LLMs

    Published: 5/29/2025
16. Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)

    Published: 5/29/2025
17. LLM Populations Form Social Conventions and Collective Bias

    Published: 5/29/2025
18. LLM Generated Persona is a Promise with a Catch

    Published: 5/29/2025
19. Large Language Models for Digital Twin Simulation

    Published: 5/29/2025
20. From RL Distillation to Autonomous LLM Agents

    Published: 5/29/2025