Best AI papers explained

440 Avsnitt

1. Training a Generally Curious Agent

   Publicerades: 2025-06-12
2. Estimation of Treatment Effects Under Nonstationarity via Truncated Difference-in-Q’s

   Publicerades: 2025-06-12
3. Strategy Coopetition Explains the Emergence and Transience of In-Context Learning

   Publicerades: 2025-06-12
4. Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

   Publicerades: 2025-06-11
5. Agentic Supernet for Multi-agent Architecture Search

   Publicerades: 2025-06-11
6. Sample Complexity and Representation Ability of Test-time Scaling Paradigms

   Publicerades: 2025-06-11
7. Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators

   Publicerades: 2025-06-10
8. LLMs Get Lost In Multi-Turn Conversation

   Publicerades: 2025-06-09
9. PromptPex: Automatic Test Generation for Prompts

   Publicerades: 2025-06-08
10. General Agents Need World Models

    Publicerades: 2025-06-08
11. The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models

    Publicerades: 2025-06-07
12. Decisions With Algorithms

    Publicerades: 2025-06-07
13. Adapting, fast and slow: Causal Approach to Few-Shot Sequence Learning

    Publicerades: 2025-06-06
14. Conformal Arbitrage for LLM Objective Balancing

    Publicerades: 2025-06-06
15. Simulation-Based Inference for Adaptive Experiments

    Publicerades: 2025-06-06
16. Agents as Tool-Use Decision-Makers

    Publicerades: 2025-06-06
17. Quantitative Judges for Large Language Models

    Publicerades: 2025-06-06
18. Self-Challenging Language Model Agents

    Publicerades: 2025-06-06
19. Learning to Explore: An In-Context Learning Approach for Pure Exploration

    Publicerades: 2025-06-06
20. How Bidirectionality Helps Language Models Learn Better via Dynamic Bottleneck Estimation

    Publicerades: 2025-06-06