Story · arXiv (via papers.cool)
SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents (arXiv (via papers.cool))
paper · Story page
Agents now choose which instruction skill to read mid-episode, but outcome-rewarded RL punishes a correct pick whenever later execution fails, a failure the authors name selector credit starvation. SkillGate routes outcome credit to execution tokens and a separate local advantage to the skill-naming tokens.
In plain words
- Researchers created SkillGate to teach action-taking artificial intelligence systems which instruction file to choose during a long task.
- Existing training can punish a correct choice when later work fails, because it grades the whole attempt together.
- SkillGate grades execution separately from the few words that name the selected instruction file.
- Separating the grades could help these systems choose useful instructions without blaming that choice for unrelated later mistakes.
Appeared in
- v0 keeps OAuth tokens out of generated code, plus SkillGate and Temporal's harness
Aug 21, 2026 · in the sections
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.