arXiv2
Search
Dark
/ Date
/ Name
Aa
W
/ Date
/ Name
"au:"Ivan Bercovich"" — arXiv2 Search
Showing 1–2 of 2 results
/ Date
/ Name
Apr 19, 2026
Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories
Jan 17, 2026
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces