SkillZip compresses LLM agent skill libraries into section-level graphs with reversible, contract-preserving macros, improving task reward and retrieval while cutting context.
Cook and Lawrence B
1 Pith paper cite this work, alongside 481 external citations. Polarity classification is still indexing.
1
Pith paper citing it
481
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries
SkillZip compresses LLM agent skill libraries into section-level graphs with reversible, contract-preserving macros, improving task reward and retrieval while cutting context.