Configuration

Configuration File Structure

SkyDiscover uses YAML files to configure all aspects of the discovery process:

config.yaml

# General settings
max_iterations: 100
checkpoint_interval: 10
log_level: "INFO"

# LLM configuration
llm:
  models:
    - name: "gpt-5"
      weight: 1.0
  temperature: 0.7
  max_tokens: 32000

# Search algorithm
search:
  type: "adaevolve"
  num_context_programs: 4
  database:
    population_size: 20
    num_islands: 2

# Prompt configuration
prompt:
  system_message: "You are an expert to help find the best solution."

# Evaluator configuration
evaluator:
  timeout: 360
  cascade_evaluation: true

General Settings

int

default:"100"

Maximum number of discovery iterations

int

default:"10"

Save checkpoint every N iterations

string

default:"INFO"

Logging level: DEBUG, INFO, WARNING, ERROR, CRITICAL

string

default:"null"

Custom directory for log files (default: output_dir/logs)

string

default:"python"

Target language: python for code, text for prompts

string

default:".py"

File extension for generated programs (.py, .txt, .cpp, etc.)

bool

default:"true"

Generate diffs instead of full programs (faster, more focused)

int

default:"60000"

Maximum characters in generated solutions

int

default:"1"

Number of iterations to run concurrently (1 = sequential)

LLM Configuration

Basic Model Setup

llm:
  models:
    - name: "gpt-5"
      weight: 1.0
  
  api_base: "https://api.openai.com/v1"
  temperature: 0.7
  top_p: 0.95
  max_tokens: 32000
  timeout: 600
  retries: 3
  retry_delay: 5

Multiple Models

SkyDiscover samples from multiple models based on weights:

llm:
  models:
    - name: "gpt-5"
      weight: 0.5
    - name: "gemini/gemini-3-pro"
      weight: 0.3
    - name: "claude-3-7-sonnet"
      weight: 0.2
  
  temperature: 0.7
  max_tokens: 32000

Per-Model Configuration

llm:
  models:
    - name: "gpt-5"
      weight: 0.7
      temperature: 0.8
      max_tokens: 40000
    - name: "gemini/gemini-3-pro"
      weight: 0.3
      temperature: 0.6
      max_tokens: 30000
      api_key: ${GEMINI_API_KEY}  # Model-specific key
  
  # Defaults for models without explicit values
  temperature: 0.7
  max_tokens: 32000

Evaluator and Guide Models

llm:
  # Main models for solution generation
  models:
    - name: "gpt-5"
      weight: 1.0
  
  # Models for LLM-as-judge evaluation
  evaluator_models:
    - name: "gpt-4o-mini"
      weight: 1.0
  
  # Models for high-level strategy (paradigm breakthrough)
  guide_models:
    - name: "o1"
      reasoning_effort: "high"
      weight: 1.0

If evaluator_models or guide_models are not specified, they default to the same models as the main models list.

LLM Parameters

string

default:"https://api.openai.com/v1"

Base URL for API requests

string

default:"null"

API key (defaults to environment variable)

float

default:"0.7"

Sampling temperature (0.0 = deterministic, 2.0 = very random)

float

default:"0.95"

Nucleus sampling threshold

int

default:"32000"

Maximum tokens per generation

int

default:"600"

Request timeout in seconds

int

default:"3"

Number of retry attempts on failure

int

default:"5"

Seconds to wait between retries

string

default:"null"

Reasoning effort for o1/o3 models: low, medium, high

Search Configuration

Top-K (Simple)

search:
  type: "topk"
  num_context_programs: 4
  database:
    db_path: "database.db"
    log_prompts: true

AdaEvolve (Adaptive Multi-Island)

search:
  type: "adaevolve"
  num_context_programs: 4
  database:
    # Population
    population_size: 20
    num_islands: 2
    
    # Adaptive intensity
    decay: 0.9
    intensity_min: 0.15
    intensity_max: 0.5
    use_adaptive_search: true
    
    # Island selection
    use_ucb_selection: true
    
    # Migration
    use_migration: true
    migration_interval: 15
    migration_count: 5
    
    # Archive
    use_unified_archive: true
    fitness_weight: 1.0
    novelty_weight: 0.0
    diversity_strategy: "code"  # "code", "metric", or "hybrid"
    
    # Dynamic islands
    use_dynamic_islands: true
    max_islands: 5
    spawn_productivity_threshold: 0.015
    spawn_cooldown_iterations: 30
    
    # Paradigm breakthrough
    use_paradigm_breakthrough: true
    paradigm_window_size: 10
    paradigm_improvement_threshold: 0.12
    paradigm_max_uses: 2
    paradigm_num_to_generate: 3

AdaEvolve Parameters Explained

Adaptive Intensity:

decay: EMA weight (0.9 = slow adaptation)
intensity_min: Min search intensity (exploitation)
intensity_max: Max search intensity (exploration)

Migration:

Every migration_interval iterations, top migration_count programs migrate to neighboring islands

Diversity Strategy:

code: Edit distance between solutions
metric: Euclidean distance in metric space
hybrid: Weighted combination

Paradigm Breakthrough:

Triggered when improvement rate drops below threshold
Generates high-level strategy ideas to escape local optima

Beam Search

search:
  type: "beam_search"
  num_context_programs: 4
  database:
    beam_width: 5
    beam_selection_strategy: "diversity_weighted"
    beam_diversity_weight: 0.3
    beam_temperature: 1.0
    beam_depth_penalty: 0.0

Best-of-N

search:
  type: "best_of_n"
  num_context_programs: 4
  database:
    best_of_n: 5

EvoX (Co-Evolution)

search:
  type: "evox"
  num_context_programs: 4
  database:
    database_file_path: null  # Uses default search strategy
    evaluation_file: null     # Uses default evaluator
    config_path: null         # Uses default config
    auto_generate_variation_operators: true

OpenEvolve Native (MAP-Elites)

search:
  type: "openevolve_native"
  num_context_programs: 4
  database:
    num_islands: 5
    population_size: 40
    archive_size: 100
    exploration_ratio: 0.2
    exploitation_ratio: 0.7
    elite_selection_ratio: 0.1
    feature_dimensions: ["complexity", "diversity"]
    feature_bins: 10
    migration_interval: 10
    migration_rate: 0.1

GEPA Native

search:
  type: "gepa_native"
  num_context_programs: 4
  database:
    population_size: 40
    candidate_selection_strategy: "epsilon_greedy"  # "best", "pareto"
    epsilon: 0.1
    acceptance_gating: true
    use_merge: true
    merge_after_stagnation: 15

Prompt Configuration

System Message

prompt:
  system_message: |
    You are an expert mathematician specializing in circle packing.
    
    Your task is to improve a function that arranges N circles in a unit
    square to maximize the sum of their radii.
    
    Key insights:
    - Hexagonal patterns achieve densest packing
    - Edge effects make square containers harder
    - Consider layered/shell arrangements

External File

prompt:
  system_message: "system_prompt.txt"  # Load from file

Template Selection

prompt:
  template: "default"      # "default" or "evox"
  template_dir: null       # Custom template directory
  system_message: "system_message"
  evaluator_system_message: "evaluator_system_message"  # For LLM judge

Simplification Suggestion

prompt:
  suggest_simplification_after_chars: 500  # Suggest simplifying if solution > 500 chars

Evaluator Configuration

evaluator:
  timeout: 360              # Evaluation timeout (seconds)
  max_retries: 3            # Retry on failure
  
  # Cascade evaluation
  cascade_evaluation: true
  cascade_thresholds: [0.3, 0.6]
  
  # LLM-as-a-judge
  llm_as_judge: false

int

default:"360"

Maximum seconds for evaluation

int

default:"3"

Retry failed evaluations N times

bool

default:"true"

Enable multi-stage evaluation (requires evaluate_stage1() and evaluate_stage2() in evaluator)

array

default:"[0.3, 0.6]"

Score thresholds for cascade stages

bool

default:"false"

Enable LLM judge for qualitative feedback

Agentic Configuration

Enable codebase-aware solution generation:

agentic:
  enabled: false
  codebase_root: null  # Auto-detected from initial_program location
  
  # Agent loop limits
  max_steps: 5
  per_step_timeout: 60.0
  overall_timeout: 300.0
  
  # Context management
  max_context_chars: 400000
  max_file_chars: 50000
  max_search_results: 50
  max_files_read: 20
  
  # Regex safety
  regex_timeout: 2.0
  max_regex_length: 200
  
  # Repo map
  repo_map_max_depth: 4
  
  # File access
  allowed_extensions:
    - ".py"
    - ".txt"
    - ".md"
    - ".json"
    - ".yaml"
  excluded_dirs:
    - ".git"
    - "__pycache__"
    - "node_modules"
    - ".venv"

Monitor Configuration

Enable live dashboard:

monitor:
  enabled: true
  host: "127.0.0.1"
  port: 8765
  max_solution_length: 10000
  
  # AI summary settings
  summary_model: "gpt-5-mini"
  summary_api_key: null  # Defaults to OPENAI_API_KEY
  summary_api_base: "https://api.openai.com/v1"
  summary_top_k: 3       # Summarize top-K programs
  summary_interval: 0    # Auto-generate every N programs (0 = manual only)

See the Monitoring guide for details.

Human Feedback Configuration

human_feedback_enabled: true
human_feedback_file: "human_feedback.md"
human_feedback_mode: "append"  # "append" or "replace"

Write feedback in Markdown:

human_feedback.md

# Iteration 15

The packing is too dense in the center. Try spreading circles more evenly.

# Iteration 22

Good improvement! Now focus on optimizing corner utilization.

Environment Variable Expansion

Use ${VAR} syntax to reference environment variables:

llm:
  api_key: ${OPENAI_API_KEY}
  models:
    - name: "gemini/gemini-3-pro"
      api_key: ${GEMINI_API_KEY}

Example Configurations

max_iterations: 100
checkpoint_interval: 10
log_level: "INFO"

llm:
  models:
    - name: "gpt-5"
      weight: 1.0
  temperature: 0.7
  max_tokens: 32000

search:
  type: "topk"
  num_context_programs: 4

prompt:
  system_message: "You are an expert to help find the best solution."

evaluator:
  timeout: 360
  cascade_evaluation: false

diff_based_generation: true

max_iterations: 100
log_level: "INFO"

llm:
  models:
    - name: "gpt-5"
      weight: 1.0
  temperature: 0.7
  max_tokens: 32000

search:
  type: "adaevolve"
  num_context_programs: 4
  database:
    population_size: 20
    num_islands: 2
    use_adaptive_search: true
    use_paradigm_breakthrough: true

prompt:
  system_message: "system_prompt.txt"

evaluator:
  timeout: 360
  cascade_evaluation: true
  cascade_thresholds: [0.3, 0.6]

max_iterations: 200

llm:
  models:
    - name: "gpt-5"
      weight: 0.5
      temperature: 0.8
    - name: "gemini/gemini-3-pro"
      weight: 0.3
    - name: "claude-3-7-sonnet"
      weight: 0.2
  max_tokens: 32000

search:
  type: "beam_search"
  database:
    beam_width: 8

max_iterations: 50

llm:
  models:
    - name: "gpt-5"
      weight: 1.0
  evaluator_models:
    - name: "gpt-4o-mini"
      weight: 1.0

prompt:
  evaluator_system_message: |
    You are a code quality judge. Return JSON with scores 0.0-1.0:
    {"readability": 0.8, "correctness": 0.9, "efficiency": 0.7}

evaluator:
  llm_as_judge: true

Next Steps

Model Providers

Set up different LLM providers

Writing Evaluators

Create effective scoring functions

Monitoring

Enable the live dashboard

Benchmarks

See real configuration examples

Get Started

Core Concepts

Guides

Examples

Extending

Configuration File Structure

General Settings

LLM Configuration

Basic Model Setup

Multiple Models

Per-Model Configuration

Evaluator and Guide Models

LLM Parameters

Search Configuration

Top-K (Simple)

AdaEvolve (Adaptive Multi-Island)

Beam Search

Best-of-N

EvoX (Co-Evolution)

OpenEvolve Native (MAP-Elites)

GEPA Native

Prompt Configuration

System Message

External File

Template Selection

Simplification Suggestion

Evaluator Configuration

Agentic Configuration

Monitor Configuration

Human Feedback Configuration

Environment Variable Expansion

Example Configurations

Next Steps

Model Providers

Writing Evaluators

Monitoring

Benchmarks

​Configuration File Structure

​General Settings

​LLM Configuration

​Basic Model Setup

​Multiple Models

​Per-Model Configuration

​Evaluator and Guide Models

​LLM Parameters

​Search Configuration

​Top-K (Simple)

​AdaEvolve (Adaptive Multi-Island)

​Beam Search

​Best-of-N

​EvoX (Co-Evolution)

​OpenEvolve Native (MAP-Elites)

​GEPA Native

​Prompt Configuration

​System Message

​External File

​Template Selection

​Simplification Suggestion

​Evaluator Configuration

​Agentic Configuration

​Monitor Configuration

​Human Feedback Configuration

​Environment Variable Expansion

​Example Configurations

​Next Steps

Model Providers

Writing Evaluators

Monitoring

Benchmarks

Configuration File Structure

General Settings

LLM Configuration

Basic Model Setup

Multiple Models

Per-Model Configuration

Evaluator and Guide Models

LLM Parameters

Search Configuration

Top-K (Simple)

AdaEvolve (Adaptive Multi-Island)

Beam Search

Best-of-N

EvoX (Co-Evolution)

OpenEvolve Native (MAP-Elites)

GEPA Native

Prompt Configuration

System Message

External File

Template Selection

Simplification Suggestion

Evaluator Configuration

Agentic Configuration

Monitor Configuration

Human Feedback Configuration

Environment Variable Expansion

Example Configurations

Next Steps