Best AI papers explained

442 Episodo

1. Cross-Environment Cooperation for Zero-Shot Multi-Agent Coordination

   Publicado: 20/4/2025
2. Sutton and Silver: The Era of Experience: Learning Beyond Human Data

   Publicado: 19/4/2025
3. Sample, Don't Search: Rethinking Test-Time Alignment for Language Models

   Publicado: 19/4/2025
4. AI Agents: Echoes of Past Technology Pivots?

   Publicado: 19/4/2025
5. Minimalist LLM Reasoning: Rejection Sampling to Reinforcement

   Publicado: 19/4/2025
6. Securing the Model Context Protocol in Enterprise Environments

   Publicado: 19/4/2025
7. Improving Multi-Turn Tool Use with Reinforcement Learning

   Publicado: 19/4/2025
8. Cultural Knowledge Conservation and Control in Large Language Models

   Publicado: 19/4/2025
9. Data Quality, Repetition, and Scaling of Language Models

   Publicado: 18/4/2025
10. Compute-Optimal Scaling Laws for Language Models Revisited

    Publicado: 18/4/2025
11. Concise Reasoning via Reinforcement Learning

    Publicado: 18/4/2025
12. Throughput Limits for LLM Inference and AI Agent Scheduling

    Publicado: 14/4/2025
13. RL Post-training Amplifies Pretraining Behaviors in Language Models

    Publicado: 14/4/2025
14. Fast Adaptation of Behavioral Foundation Models

    Publicado: 14/4/2025
15. Proprietary Reward Models: Sustaining Advantage in Agentic AI

    Publicado: 13/4/2025
16. Why Multi-Agent LLM Systems Fail: A Comprehensive Study

    Publicado: 12/4/2025
17. Play2Prompt: Zero-Shot Tool Instruction Optimization via Tool Play

    Publicado: 12/4/2025
18. Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems

    Publicado: 12/4/2025
19. API and GUI Agents: Divergence, Convergence, and Hybrid Approaches

    Publicado: 12/4/2025
20. AI, Chess, and Competitive Advantage: Substitution and Complementation

    Publicado: 12/4/2025