MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization

ArXi:2605.19330v1 Announce Type: new LLM agents organize behavior through skills - structured natural-language specifications governing how an agent reasons, retrieves, and responds. Unlike monolithic prompts, skills are multi-field artifacts subject to hard platform constraints: description fields are truncated for routing, instruction bodies are compacted via progressive disclosure, and co-resident skills compete for limited context windows.