Best AI papers explained

550 Avsnitt

1. PREFDISCO: Evaluating Proactive Personalization through Interactive Preference Discovery

   Publicerades: 2025-11-12
2. Reusing pre-training data at test time is a compute multiplier

   Publicerades: 2025-11-10
3. Scaling Agent Learning via Experience Synthesis

   Publicerades: 2025-11-09
4. Continuous Autoregressive Language Models

   Publicerades: 2025-11-08
5. Toward a Theory of Agents as Tool-Use Decision-Makers

   Publicerades: 2025-11-07
6. Nested Learning: The Illusion of Deep Learning Architectures

   Publicerades: 2025-11-05
7. GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding

   Publicerades: 2025-11-05
8. Beyond a million tokens: benchmarking and enhancing long-term memory in llms

   Publicerades: 2025-11-04
9. Agentic Economic Modeling

   Publicerades: 2025-11-03
10. Emergent Introspective Awareness in Large Language Models

    Publicerades: 2025-11-03
11. Can Large reasoning models self-train?

    Publicerades: 2025-11-01
12. ALITA-G: Self-Evolving Generative Agent for Agent Generation

    Publicerades: 2025-11-01
13. Self-improving LLM agents at test-time

    Publicerades: 2025-10-30
14. Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization

    Publicerades: 2025-10-30
15. Language models are injective and hence invertible

    Publicerades: 2025-10-30
16. ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

    Publicerades: 2025-10-29
17. RLAD: Training LLMs to Discover Abstractions

    Publicerades: 2025-10-29
18. How to Train Your Advisor: Steering Black-Box LLMs with ADVISOR MODELS

    Publicerades: 2025-10-29
19. Self-improving LLM agents at Test-Time

    Publicerades: 2025-10-27
20. KL-Regularized Reinforcement Learning is designed to Mode Collapse

    Publicerades: 2025-10-27