Research
AI Agents are Vulnerable to Radicalization (opens in a new tab)
arXiv cs.AI ·
Your next cue,
from NOCUE.
Research
Reach Into The CHOIR: Free-List Elicitation Uncovers Distinct Model Voices in LLM Ensembles (opens in a new tab)
arXiv cs.AI ·
Research
Can an AI Agent Rediscover a Blaschke-Curve Invariant? (opens in a new tab)
arXiv cs.AI ·
Research
Decode-Latency Feedback Prefill: A Model-Free Controller and Its Generalization Limits (opens in a new tab)
arXiv cs.AI ·
Research
AgBench: Agentic AI Benchmarks for Personal AI Devices (opens in a new tab)
arXiv cs.AI ·
Research
Improving OCR Faithfulness via Gated and Attenuated On-Policy Distillation (opens in a new tab)
arXiv cs.AI ·
Research
AIM: Agentic Idea Management for Automated Research (opens in a new tab)
arXiv cs.AI ·
Research
Examining Variation in How Guided AI Tutors Resolve Student Impasses (opens in a new tab)
arXiv cs.AI ·
Research
Defining and Categorising Human-AI Interactions in Clinical Trials: A Multidimensional Human-AI Classification Approach (opens in a new tab)
arXiv cs.AI ·