December 28, 2025 front

ML Newsnew | past | best | rss | submit

Stories from December 28, 2025 (UTC)

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

1.	Designing Predictable LLM-Verifier Systems for Formal Method Guarantee (arxiv.org)
	59 points by PaulHoule 279 days ago \| hide \| past \| pdf \| 13 comments
2.	Beyond Context: Large Language Models Failure to Grasp Users Intent (arxiv.org)
	4 points by mpweiher 280 days ago \| hide \| past \| pdf \| discuss
3.	A Profit-Based Measure of Lending Discrimination (arxiv.org)
	3 points by neehao 279 days ago \| hide \| past \| pdf \| discuss
4.	Automating Deception: Scalable Multi-Turn LLM Jailbreaks (arxiv.org)
	3 points by PaulHoule 279 days ago \| hide \| past \| pdf \| discuss
5.	Toward Training Superintelligent Software Agents Through Self-Play SWE-RL (arxiv.org)
	2 points by klipt 280 days ago \| hide \| past \| pdf \| discuss
6.	ChatGPT: Excellent Paper Accept It. Editor: Imposter Found Review Rejected (arxiv.org)
	1 point by belter 279 days ago \| hide \| past \| pdf \| discuss
7.	Toward Training Superintelligent Software Agents Through Self-Play SWE-RL (arxiv.org)
	1 point by pama 279 days ago \| hide \| past \| pdf \| discuss
8.	Towards a Science of Scaling Agent Systems (arxiv.org)
	1 point by Anon84 280 days ago \| hide \| past \| pdf \| discuss