Research
Worse Together: How Performance Breaks Down in Multi-User Multi-Agent Teams (opens in a new tab)
arXiv cs.AI ·
Your next cue,
from NOCUE.
Research
Robust Is Salient: An Informed Adversary Moves the Optimal Signal onto the Salience Pole (opens in a new tab)
arXiv cs.AI ·
Research
When Do Causal World Models Help Modular LLM Agents (opens in a new tab)
arXiv cs.AI ·
Research
Rules to Tools: Executable Checks for LLM Agents in Scientific Computing (opens in a new tab)
arXiv cs.AI ·
Research
Knowing When to Yield: Grounded Arbitration of User Corrections in Text-Based Embodied Agents (opens in a new tab)
arXiv cs.AI ·
Safety
Greg Kroah-Hartman – Security in the LLM Age [video] (opens in a new tab)
Hacker News ·
Safety
Nvidia agent safety push raises questions about who governs AI autonomy (opens in a new tab)
AI Business ·
Industry
We don’t need to panic about AI. We need to hold its creators accountable when things go wrong | John Quiggin (opens in a new tab)
The Guardian AI ·
Products
Cloudflare Releases Clef and Clef-flash: Open-Weight Decision Models That Return Typed Probabilities Instead of Text (opens in a new tab)
MarkTechPost ·