Best AI papers explained

442 Episodo

1. MSL: Enhancing LLM Recommenders via Masked Softmax Loss

   Publicado: 11/4/2025
2. Self-Supervised Deep Reinforcement Learning for Optimal Question Ranking

   Publicado: 11/4/2025
3. Adaptive Language Elicitation for Latent Information Discovery

   Publicado: 10/4/2025
4. LLM Persona Bias: Promise and Peril in Simulation

   Publicado: 10/4/2025
5. AutoTools: Automating Tool Use for Large Language Models

   Publicado: 10/4/2025
6. Tool Learning with Large Language Models: A Comprehensive Survey

   Publicado: 10/4/2025
7. All Roads Lead to Likelihood: RL for Fine-Tuning Value

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

   Publicado: 8/4/2025
9. Thinking Faster by Writing Less: Chain of Draft Reasoning

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

    Publicado: 8/4/2025
11. L1: Length Controlled Reasoning with Reinforcement Learning

    Publicado: 8/4/2025
12. WikiBigEdit: Benchmarking Lifelong Knowledge Editing in LLMs

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

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

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

    Publicado: 8/4/2025
16. Four Formalizable Theories of the Firm

    Publicado: 8/4/2025
17. Efficient Tool Use with Chain-of-Abstraction Reasoning

    Publicado: 6/4/2025
18. CodeTool: Process Supervision for Enhanced LLM Tool Invocation

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

    Publicado: 6/4/2025
20. Epistemic Alignment in User-LLM Knowledge Delivery

    Publicado: 6/4/2025