Menu
SkillsMP has collected 10 skills from Optima-CityU/LLM4AD_Next. Open a skill to review its source and details.
Showing 10 of 10 collected skills.
Organize one or more Markdown source documents into high-fidelity, editable knowledge blocks. Use when an agent must plan a semantic document reorganization, execute that plan without fixed-size chunking, or refine previously generated Markdown blocks while…
Use when a user wants to build an LLM4AD_Next task package — a runnable directory that lets the LLM4AD platform evolve an algorithm for their problem. Covers what files a task package contains, each file's contract, and how the package is run on the LLM4AD…
Evolution of Heuristics (EOH) method skill. USE WHEN the user explicitly requests EoH / Evolution of Heuristics, or wants population-level heuristic evolution with explore-exploit-merge-modify operators.
FunSearch (Program Search) method skill. USE WHEN the user explicitly requests FunSearch / Program Search, or wants search with a programs database that stores and samples from high-scoring programs.
Monte Carlo Tree Search for Automatic Heuristic Design (MCTS-AHD) method skill. USE WHEN the user explicitly requests MCTS / Monte Carlo Tree Search for heuristic design, or wants tree-structured search with UCT-based exploration-exploitation balance.
Multi-objective Evolution of Heuristics (MEoH) method skill. USE WHEN the user explicitly requests MEoH / Multi-objective EoH, or wants Pareto-based population evolution with archive for multi-objective problems.
MOEA/D (Multi-objective Evolutionary Algorithm based on Decomposition) method skill. USE WHEN the user explicitly requests MOEA/D / Decomposition-based multi-objective evolution, or wants weight-vector decomposition with neighborhood collaboration.
NSGA-II multi-objective evolutionary method skill. USE WHEN the user explicitly requests NSGA-II / Non-dominated Sorting Genetic Algorithm, or wants multi-objective optimization with non-dominated sorting and crowding distance selection.
Reflective Evolution (ReEvo) method skill. USE WHEN the user explicitly requests ReEvo / Reflective Evolution, or wants evolution with reflection mechanisms that summarize failure lessons and inject them into the next generation.
Use when a user wants to build an LLM4AD_Next task package — a runnable directory that lets the LLM4AD platform evolve an algorithm for their problem. Covers what files a task package contains, each file's contract, and how the package is run on the LLM4AD…