aifollow.news
Back Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · Original publication time AI score54

Amazon paper finds saved agent skills can hurt performance after environments changeMachine translation

AI introduction

The paper tested Claude Opus 4.7 and Haiku 4.5 across four settings before and after a change. On Terminal-Bench 2, a skill that had raised Opus's pass rate by 4.7 points left it 11.4 points below the no-skill baseline after the change; selectively checking and repairing conflicting content can restore a saved skill's value.

Original post · Original

The article text is unavailable in this language; an existing version is shown.

@rohanpaul_ai

New Amazon paper finds that saved agent skills can hurt once the environment changes, and checking and repairing them selectively restores their value.

Agent skills store past experience, like file paths, field names, or commands, so agents can skip work later. When an app or API changes, some of that stored detail goes stale without warning.

They tested Claude Opus 4.7 and Haiku 4.5 on 4 settings, including Terminal-Bench 2 and IRS tax forms, before and after a change. Their fix replays saved checks witho1ut model calls and repairs or rebuilds only the conflicting skill content.

On Terminal-Bench 2, a skill that had added 4.7 points for Opus cut its pass rate 11.4 points below no skill after the change. Maintenance lifted Haiku's tax-form field accuracy from 30.5% with the stale skill to 97.5%.

Check saved agent skills against the current environment before reuse, instead of waiting for tasks to fail.

Source: Rohan Paul · x.com

Research
Found an error? Send a correction