Latest Research in Artificial Intelligence

Top Research Topics in Artificial Intelligence

• Machine Learning — 114 papers
• Artificial Intelligence — 86 papers
• Computation and Language — 74 papers
• Computer Vision and Pattern Recognition — 32 papers
• Ferroelectric and Negative Capacitance Devices — 6 papers
• Sound — 4 papers
• Natural Language Processing Techniques — 4 papers
• Language and cultural evolution — 3 papers
• Mathematics, Computing, and Information Processing — 2 papers
• Computability, Logic, AI Algorithms — 2 papers

Highest-Cited Papers

1. LEMMA: Learned Guidance for Evidence-Carrying Long-Horizon Symbolic Rewriting
2. LEMMA: Learned Guidance for Evidence-Carrying Long-Horizon Symbolic Rewriting
3. Measuring What a Human Adds to a Machine Baseline: A Problem Statement
4. Beyond On-Policy Exploration: Integrating External Policy Rollouts for Reinforcement Learning in Diffusion Language Models
5. Attention Has a Coordinate but No Commitment: The Selection Gap in Softmax Attention, with Two Measurements on GPT-2
6. Semantic Neighborhood Fidelity of NN-Descent Graphs for Text Embeddings
7. Attention Has a Coordinate but No Commitment: The Selection Gap in Softmax Attention, with Two Measurements on GPT-2
8. Neuromorphic-Inspired Language Identification for Low-Resource Code-Switched Texts Using Spiking Neural Networks
9. Reach or Solve? Attributing Agentic RL Gains with Checkpoint Handoffs
10. EPIG-Tree: Compute-Optimal Branching for Gradient-Efficient Reinforcement Learning
11. Score Centering Stabilizes Off-policy Reinforcement Learning
12. MaSCoD: A Multi-Agent Framework for Structural-Context-Guided Candidate Causal Graph Generation
13. Co-Skill: A Collaborative Communication Framework for Skill Evolution
14. An Architecture for Long-Horizon Agents: Levels, Ticks and Cascaded Intelligence
15. UnifiedPlayers: Enhance Tool-Integrated Reasoning in Agentic Reinforcement Learning
16. When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation
17. Rollback the World, Keep the Reflection: Rollback-Induced Reflection for Long-Horizon LLM Agents
18. TripScore: Aligning LLMs for Real-World Travel Planning via Expert-Calibrated Reward
19. How to Compress KV Cache in RL Post-Training? Shadow Mask Distillation for Memory-Efficient Alignment
20. Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling