SkillZip Pro: Execution-Aware Dynamic Compression of Progressively Loaded Skills for Self-Evolving Agents
This work introduces \method, an evaluation-free compressor for complete, progressively loaded skill bundles, which leaves the agent harness unchanged and emits an ordinary directory and preserves routing, so every required file and directly callable entry remains reachable after rewriting.
Xiaofan Bai, Chao Liu, Hong-Qiang Lin et al.
· 0 citations