LLM Digest
Subscribe

AI Storyline

3 items · 2 sources · 3 days

View as JSON

Operational story trace

Skill Evolution

Latest change

ScienceCUA (Nov 2) builds skills from software manuals and web pages and refines them from execution feedback for scientific computer-use agents.

Earlier contextThe story so far

EvoSkill v2 (Oct 19) evolves agent skills, meaning instructions, without touching the model or harness. A Oct 26 paper extended this to coding agents with hierarchical skills.

editor-curated · source-linked

Arc

Oct 19Nov 2 · now
LAUNCH · Oct 19
EvoSkill v2: a three-agent system that edits skills
1 source · show source ▾
CODING · Oct 26
Hierarchical skills separate reusable experience from repo-specific context
1 source · show source ▾
NOW · Nov 2
ScienceCUA builds skills from manuals and evolves them by execution
1 source · show source ▾

What to watch — open questions

  • Do evolved skills hold up on tasks and repositories outside their training benchmark?
  • Does skill evolution beat hand-written skills on a shared benchmark?
How this thread was built
editor wrote the arc · 3 beats

Storylines are threaded mechanically from the feed: stories that share a distinctive anchor across multiple days and sources. Each item links to its original source. The evidence trace, current state, and open questions are written by the editor routine and refreshed whenever a new beat lands.