Research
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks (opens in a new tab)
arXiv cs.AI ·
Your next cue,
from NOCUE.
Research
When Scientific Contradictions Are Lost in Translation (opens in a new tab)
arXiv cs.AI ·
Research
Budget Boundary Effects in Test-Time Mathematical Reasoning (opens in a new tab)
arXiv cs.AI ·
Research
MoFlow: Multi-Objective Agentic Workflow Generation (opens in a new tab)
arXiv cs.AI ·
Research
CARAT: Do Materials LLMs Reason or Recite? (opens in a new tab)
arXiv cs.AI ·
Industry
Ask HN: If AI took your job tomorrow, what is your plan? (opens in a new tab)
Hacker News ·
Industry
Is sandboxing sufficient to contain rogue agents? (opens in a new tab)
Hacker News ·
Products
Perplexity Releases pplx-embed-v2-context-9b-preview: A Contextual Embedding Model That Retrieves Answers and Their Supporting Evidence (opens in a new tab)
MarkTechPost ·
Safety
How AI could ‘supercharge’ election risks across south-east Asia (opens in a new tab)
The Guardian AI ·