Toolsslug: terminal-bench-2

Terminal-Bench 2

Benchmark evaluating agents on real command-line tasks in terminal environments.

Curated Intelligence

1 items · Page 1/1
Rohan Paul (@rohanpaul_ai)T2·Agents
74 pts
Amazon Study Finds Stale Agent Skills Hurt After Environment Changes

A new Amazon paper finds that saved agent skills such as file paths, field names and commands silently go stale after app or API changes, hurting performance. On Terminal-Bench 2, a skill that had added 4.7 points for Opus cut pass rate 11.4 points below no-skill after the change; their selective check-and-repair approach lifted Haiku's tax-form field accuracy from 30.5% to 97.5%.