Story · arXiv
ERPBench: A State-Grounded Evaluation Paradigm for Computer-Use Agents in Enterprise Software (arXiv)
paper · Story page
Screenshot-only agents scored against a live ERP system's database
Appeared in
- Split an MCP injection across two channels and resistant models leak at 100%
Sep 18, 2026 · quick links
Subscribe
Get the brief in your inbox
Pick daily, weekly, or both. Nothing is gated either way: every issue is on the site and in the feeds.
- Weekdays at 8:45am IST, one lead story and 6 to 9 items.
- Sundays, an argued synthesis rather than a recap.
- One click to leave, and quiet days say so in the subject line.