> ## Documentation Index > Fetch the complete documentation index at: https://mintlify.com/skydiscover-ai/skydiscover/llms.txt > Use this file to discover all available pages before exploring further. # AdaEvolve > Multi-island adaptive search with UCB-based island selection and paradigm breakthroughs ## Overview AdaEvolve is an adaptive evolutionary search algorithm that dynamically adjusts its optimization behavior based on observed progress. It uses a multi-island architecture where each island evolves independently, with migration between islands and adaptive exploration/exploitation control. Read the full AdaEvolve paper on ArXiv ## Key Features Multiple parallel populations evolve simultaneously with periodic migration of top solutions Dynamically adjusts exploration vs exploitation based on improvement signals Upper Confidence Bound algorithm selects which island to evolve next Generates high-level strategy shifts when globally stuck ## How It Works ### Adaptive Search Intensity AdaEvolve tracks improvement history per island using two key metrics: * **Improvement Signal (δ)**: Normalized magnitude of fitness improvement * **Accumulated Signal (G)**: Decayed sum of squared improvements The search intensity for each island is calculated based on its accumulated improvement signal, determining the balance between exploration (trying diverse approaches) and exploitation (refining known good solutions). ### Island-Based Evolution The algorithm maintains multiple independent populations (islands) that evolve in parallel: 1. **Round-robin selection**: Islands take turns evolving using UCB-based selection 2. **Migration**: Top solutions periodically migrate between islands 3. **Independent adaptation**: Each island has its own search intensity ### Paradigm Breakthroughs When progress stagnates globally across all islands, AdaEvolve can generate "paradigm breakthroughs" - high-level strategic ideas that represent fundamentally different approaches to the problem. ## Configuration ### Basic Usage ```bash theme={null} skydiscover-run initial_program.py evaluator.py \ --search adaevolve \ --iterations 100 ``` ### Configuration File ```yaml theme={null} search: type: adaevolve database: # Island configuration num_islands: 5 population_size: 40 # Adaptive search use_adaptive_search: true gamma_decay: 0.95 # Decay factor for accumulated improvement # Migration settings migration_interval: 10 # Iterations between migrations migration_rate: 0.1 # Fraction of population to migrate # Paradigm breakthroughs use_paradigm_breakthrough: true paradigm_stagnation_threshold: 20 paradigm_num_to_generate: 3 # Error handling enable_error_retry: true max_error_retries: 2 ``` ## Configuration Options Number of independent populations to maintain Maximum number of programs per island Enable adaptive exploration/exploitation control Decay factor for accumulated improvement signal (0-1) Number of iterations between island migrations Fraction of top programs to migrate between islands Enable paradigm breakthrough generation when stuck Iterations without improvement before triggering paradigm generation Number of paradigm ideas to generate per breakthrough ## When to Use AdaEvolve * Complex optimization problems with multiple local optima * Problems where both exploration and exploitation are important * Long discovery runs (100+ iterations) where adaptation can help * Problems requiring diverse solution approaches * Very short discovery runs (\< 20 iterations) * Problems with clear single optimal approach * When simplicity is prioritized over performance ## Performance Across \~200 optimization benchmarks, AdaEvolve achieves: * **Frontier-CS**: \~34% median score improvement over OpenEvolve, GEPA, and ShinkaEvolve * **Math + Systems**: Matches or exceeds AlphaEvolve and human SOTA on 6/6 systems and 6/8 math tasks * **Real-world impact**: 41% lower cross-cloud transfer cost, 14% better GPU load balance ## Example: Circle Packing ```bash theme={null} # Run AdaEvolve on the circle packing benchmark uv run skydiscover-run \ benchmarks/math/circle_packing/initial_program.py \ benchmarks/math/circle_packing/evaluator.py \ --config benchmarks/math/circle_packing/config.yaml \ --search adaevolve \ --iterations 100 ``` ## Advanced Features ### Sibling Context AdaEvolve provides the LLM with information about previous mutations of the same parent ("siblings"), helping it learn from recent attempts. ### Mode-Aware Prompting The prompt automatically adapts based on whether the current mode is: * **Exploration**: Encourages diverse, creative approaches * **Exploitation**: Encourages refinement and optimization ### Comprehensive Logging AdaEvolve logs detailed statistics to a JSON file including: * Search intensity per island * Improvement signals * Island populations and best scores * UCB selection scores Access via `adaevolve_iteration_stats_*.jsonl` in the output directory. ## Related Algorithms * [EvoX](/algorithms/evox) - Co-evolves the search strategy itself * [Top-K](/algorithms/topk) - Simpler top-K selection without adaptation * [OpenEvolve Native](/algorithms/openevolve-native) - MAP-Elites with island architecture