The authors represented when skills apply, how they execute, and how they compose as a unified graph.
Attribution-guided skill graphs improve targeted repairs for frozen language models
SkillAA traces execution failures to specific graph objects, edits only the implicated structure, and validates changes before committing them.
Top University
Ziqiao Shang · Ling-Yue Ge · Lan-Zhe Guo
National Key Laboratory for Novel Software Technology · Nanjing University
Research Digest··2 min read
Thread:Skill Selection for Agents
Shang, Ge, and Guo introduce SkillAA, a framework that improves external procedural skills without updating a language model’s parameters.
Why this paper
From Nanjing University and National Key Laboratory for Novel Software Technology · Part of Skill Selection for Agents, now 14 papers
In one line
GraphSkillAA uses attribution-guided updates and two-level validation to optimize skill graphs, outperforming existing methods.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§