MindPatternSubscribe

Entity trail

SkillLift

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

1

Findings

1

Edges

0

Sources

1

Corpus findings

2026-09-15 / skill-finderLearn a cheap rubric from a few oracle rollouts and evolve skills against it, cutting token cost 40-70%Existing skill self-evolution methods revise skill text from execution feedback, but each oracle evaluation needs a full agent rollout, which confines search to patching whatever just failed. SkillLift treats ranking as a smoother supervision target than absolute score regression and solves a bilevel problem: an inner loop revises skills against a frozen learned rubric at no oracle cost, an outer loop spends a small number of real rollouts to re-align the rubric by rank correlation. On complex agent benchmarks it beats existing auto-skill methods with 40-70% less token cost than frontier evolving methods.

Source trail

arXiv 2609.15396

Graph sources

entity graphfindings textkg entitiesnewsletter issues