Research
MEA: A Reward-Driven Multi-Agent System for Faithful Model Explanations (opens in a new tab)
arXiv cs.AI ·
Your next cue,
from NOCUE.
Research
The AI Risk Observatory: What Can We Learn from AI Disclosures in Annual Reports About Societal Resilience? (opens in a new tab)
arXiv cs.AI ·
Research
How To Train Your World Model: Fine-tuning vs RAG for LM-based World Modeling (opens in a new tab)
arXiv cs.AI ·
Research
HXAI: Hierarchical Privacy-Preserving Explainable AI in Distributed Energy Systems (opens in a new tab)
arXiv cs.AI ·
Research
How to Have a Sensitive Debate: An Instance-Optimal Protocol for AI Debate (opens in a new tab)
arXiv cs.AI ·
Research
Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents (opens in a new tab)
arXiv cs.AI ·
Research
On-Premises Multi-Course RAG Tutoring for Business Education: Hardware-Software Trade-offs in a Campus AI Tutor (opens in a new tab)
arXiv cs.AI ·
Research
Right Order, Wrong Scale: Auditing LLM Judges for Occupational AI Measurement (opens in a new tab)
arXiv cs.AI ·
Research
Mitigating Social Sycophancy via Pluralistic Preference Optimization (opens in a new tab)
arXiv cs.AI ·