February 24, 2026 front

ML Newsnew | past | best | rss | submit

Stories from February 24, 2026 (UTC)

Go back a day, month, or year. Go forward a day.

1.	Agents of Chaos: Breaches of trust in autonomous LLM agents (arxiv.org)
	4 points by cool-RR 222 days ago \| hide \| past \| pdf \| 1 comment
2.	Agents of Chaos (arxiv.org)
	3 points by wslh 221 days ago \| hide \| past \| pdf \| discuss
3.	AST-Guided Translation of Natural Language into First-Order Logic with LLMs (arxiv.org)
	2 points by PaulHoule 221 days ago \| hide \| past \| pdf \| discuss
4.	PersonaLive Expressive Portrait Image Animation for Live Streaming (arxiv.org)
	2 points by tamnd 221 days ago \| hide \| past \| pdf \| discuss
5.	Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines? (arxiv.org)
	2 points by yorwba 221 days ago \| hide \| past \| pdf \| discuss
6.	Towards a Science of AI Agent Reliability (arxiv.org)
	2 points by smartmic 222 days ago \| hide \| past \| pdf \| discuss
7.	Fast and Optimal Mapping for Accelerator Modeling and Evaluation (arxiv.org)
	2 points by PaulHoule 222 days ago \| hide \| past \| pdf \| discuss
8.	Improving Chain-of-Thought Monitorability Through Information Theory (arxiv.org)
	1 point by simonpure 222 days ago \| hide \| past \| pdf \| discuss
9.	The Landscape of Non-Equilibrium Memories with Neural Cellular Automata (arxiv.org)
	1 point by PaulHoule 222 days ago \| hide \| past \| pdf \| discuss
10.	Computer-Using World Model (arxiv.org)
	1 point by steamboatwillie 222 days ago \| hide \| past \| pdf \| discuss