July 29, 2026 front

ML Newsnew | past | best | rss | submit

Stories from July 29, 2026 (UTC)

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

1.	Handbook.md shows that long policy documents do not reliably govern agents (arxiv.org)
	325 points by spIrr 66 days ago \| hide \| past \| pdf \| 209 comments
2.	Teaching agents to predict and pre-execute their next tool call (arxiv.org)
	6 points by rotariuvladimir 66 days ago \| hide \| past \| pdf \| discuss
3.	Detecting CSAM Text-to-Image LoRAs from Weights (arxiv.org)
	6 points by sbulaev 66 days ago \| hide \| past \| pdf \| discuss
4.	Visual prompt engineering for video models (arxiv.org)
	4 points by root-parent 66 days ago \| hide \| past \| pdf \| discuss
5.	Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation (arxiv.org)
	4 points by tcp_handshaker 66 days ago \| hide \| past \| pdf \| discuss
6.	Every Time I Hire a Linguist, Inference Costs Go Down (arxiv.org)
	3 points by cwbuilds 66 days ago \| hide \| past \| pdf \| discuss
7.	Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation (arxiv.org)
	3 points by root-parent 66 days ago \| hide \| past \| pdf \| discuss
8.	Adaptive Agentic Attacks on LLM Vulnerability Detectors via Adversarial Comments (arxiv.org)
	3 points by tcp_handshaker 66 days ago \| hide \| past \| pdf \| discuss
9.	ProofCouncil: An LLM Agent for Solving Open Mathematical Problems (arxiv.org)
	3 points by frozenseven 66 days ago \| hide \| past \| pdf \| 1 comment
10.	Mapping CVEs to Mitre ATT&CK Techniques (arxiv.org)
	3 points by adulau 66 days ago \| hide \| past \| pdf \| 1 comment
11.	Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model (arxiv.org)
	3 points by sbulaev 66 days ago \| hide \| past \| pdf \| discuss
12.	CryptanalysisBench: Can LLMs Do Cryptanalysis? (arxiv.org)
	1 point by zdw 66 days ago \| hide \| past \| pdf \| discuss