skydiscover 0.1.0

A Flexible Framework for AI-Driven Scientific and Algorithmic Discovery

   

  SkyDiscover

A Flexible Framework for AI-Driven Scientific and Algorithmic Discovery

       

SkyDiscover is a modular framework for AI-driven scientific and algorithmic discovery, providing a unified interface for running and comparing algorithms across 200+ optimization tasks. It follows the same high-level evolutionary loop as prior systems like AlphaEvolve, but exposes each stage as a reusable, extensible component:

1. Context Builder. Assembles prompts from the problem spec, prior solutions, and human feedback.
2. Solution Generator. Produces candidates via LLM calls, with optional tool use (e.g., reading codebases).
3. Evaluator. Scores candidates and logs metadata back into the solution database.
4. Solution Selector. Maintains the solution database and picks priors for the next iteration (Top-K, MAP-Elites, adaptive evolutionary methods, etc.).

Come and build easily with SkyDiscover!

🚧 This project is under active development. APIs and interfaces may change.

---

🏆 Benchmarks & Performance

We implement two adaptive evolutionary algorithms (AdaEvolve and EvoX), achieving:

• Best open-source performance — ~34% median score improvement on 172 Frontier-CS problems over OpenEvolve, GEPA, and ShinkaEvolve
• Matching or exceeding AlphaEvolve and human SOTA — on 8 math and 6 systems optimization tasks
• Real-world discoveries — 41% lower cross-cloud transfer cost, 14% better GPU load balance for MoE serving, 29% lower KV-cache pressure via GPU model placement

200+ tasks across math, systems, and algorithms

	Benchmark	Domain	Tasks	Description
🔢	math/	Math	14	Circle packing, Erdos problems, geometric optimization
🖥️	ADRS/	Systems	6	Cloud scheduling, load balancing, MoE expert placement
⚡	gpu_mode/	Systems	3	GPU kernel optimization
🧩	frontier-cs-eval/	Algorithms	172	Frontier-CS competitive programming
🧠	arc_benchmark/	Reasoning	—	ARC-AGI visual reasoning
💻	ale_bench/	Algorithms	—	Algorithmic programming contests
💬	prompt_optimization/	NLP	1	HotPotQA prompt evolution

See Dependency extras for install commands per benchmark.

🚀 Quick Start

Prerequisites: Python >= 3.10, uv

# Install
uv sync
export OPENAI_API_KEY="<your-key>"

# Try the circle packing benchmark
uv sync --extra math
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

# Or run on your own problem
uv run skydiscover-run initial_program.py evaluator.py \
  --search evox \
  --model gpt-5 \
  --iterations 100

Or use the Python API:

from skydiscover import run_discovery

result = run_discovery(
    initial_program="initial_program.py",
    evaluator="evaluator.py",
    search="evox",   # or "adaevolve"
    model="gpt-5",
    iterations=100,
)
print(result.best_score, result.best_solution)

✏️ The Two Files You Write

Scoring Function

Your evaluator is a Python file with an evaluate(program_path) function. It returns a dict with metrics and optional artifacts:

def evaluate(program_path):
    score = run_and_grade(program_path)
    return {
        "combined_score": score,       # primary optimization target (maximized)
        "artifacts": {                 # optional — stored with the solution for future context
            "feedback": "Off by one in the loop boundary",
        },
    }

• combined_score drives evolution. If omitted, SkyDiscover averages all numeric values in the dict.
• artifacts is optional — entries are injected into the next LLM prompt as context.

Starting Solution

Your initial program marks the region to mutate with EVOLVE-BLOCK markers. Everything outside is left untouched.

# EVOLVE-BLOCK-START
def solve(input_data):
    return input_data  # baseline — SkyDiscover will improve this
# EVOLVE-BLOCK-END

If no markers are present, the entire file is treated as mutatable.

🧬 Pick an Algorithm

Algorithm	Flag	Description
⭐ AdaEvolve	--search adaevolve	Multi-island adaptive search with UCB, migration, and paradigm breakthroughs
🧠 EvoX	--search evox	Self-evolving paradigm that co-adapts solution generation and experience management
📊 Top-K	--search topk	Simple baseline — keeps the top-K solutions
🔍 Beam Search	--search beam_search	Breadth-first expansion of a beam of top solutions
🎲 Best-of-N	--search best_of_n	Generates N variants per iteration, keeps the best

External backends

Note: The external extra is only supported when installing via uv. It will not work with pip install skydiscover[external] because it pulls packages directly from Git. If you are using pip, install the backends manually (see each project's repo).

Install with uv sync --extra external, then use the corresponding flag:

Backend	Flag	Source
OpenEvolve	--search openevolve	codelion/openevolve
GEPA	--search gepa	gepa-ai/gepa
ShinkaEvolve	--search shinkaevolve	SakanaAI/ShinkaEvolve (manual install)

ShinkaEvolve manual install

git clone --depth 1 https://github.com/SakanaAI/ShinkaEvolve.git external_repos/ShinkaEvolve
uv pip install -e external_repos/ShinkaEvolve

SkyDiscover shows a helpful error if you try to use a backend that isn't installed.

⚙️ Configuration

Pass a YAML config with -c. See configs/ for full annotated templates.

max_iterations: 100
llm:
  models: [{ name: "gemini/gemini-3-pro-preview", weight: 1.0 }]
search:
  type: "adaevolve"                  # or "evox", "topk", "beam_search", "best_of_n"
prompt:
  system_message: |
    You are an expert at optimizing algorithms.

API keys (OPENAI_API_KEY, GEMINI_API_KEY, etc.) are resolved from environment variables automatically.

📊 Live Monitor & Human Feedback

Add monitor: { enabled: true } to your config. The dashboard URL prints at run start — scatter plot of all programs, code diffs, metrics, and AI summaries. A Human Feedback panel lets you steer evolution in real time. Replay a completed run:

uv run skydiscover-viewer /path/to/checkpoints/checkpoint_100

📖 Reference

CLI flags

uv run skydiscover-run INITIAL_PROGRAM EVALUATOR [options]

Flag	Description
-c, --config FILE	Config YAML
-i, --iterations N	Number of iterations
-m, --model MODEL	LLM model (overrides config)
-s, --search TYPE	Search algorithm
-o, --output DIR	Output directory
--api-base URL	Override LLM API endpoint
--checkpoint DIR	Resume from checkpoint
--codebase DIR	Agentic mode (LLM can read your files)
-l, --log-level LEVEL	DEBUG, INFO, WARNING, or ERROR

Python API — discover_solution()

from skydiscover import discover_solution

result = discover_solution(
    initial_solution="def solve(x): return x",
    evaluator=lambda path: {"combined_score": run_tests(path)},
    iterations=50,
    search="evox",
)

Model providers

Any LiteLLM-compatible model works using provider/model format:

--model gpt-5                                               # OpenAI (default)
--model gemini/gemini-3-pro-preview                          # Gemini
--model anthropic/claude-sonnet-4-20250514                   # Anthropic
--model ollama/llama3 --api-base http://localhost:11434/v1   # Local (Ollama, vLLM, etc.)

Multi-model pools with weighted sampling are supported in config:

llm:
  models:
    - name: "gpt-5-mini"
      weight: 0.7
    - name: "gemini/gemini-2.0-flash"
      weight: 0.3

Benchmark dependency extras

uv sync                              # Base install
uv sync --extra math                 # Math benchmarks (SciPy, JAX, PyWavelets, …)
uv sync --extra adrs                 # ADRS systems benchmarks
uv sync --extra frontier-cs          # Frontier-CS benchmark tooling
uv sync --extra external             # OpenEvolve / GEPA / ShinkaEvolve backends (uv only, not available via pip)
uv sync --extra prompt-optimization  # HotPotQA prompt optimization

Combine extras as needed: uv sync --extra external --extra math

If a benchmark ships its own requirements.txt, also run: uv pip install -r path/to/requirements.txt

---

🔗 Related Work

SkyDiscover is inspired by AlphaEvolve, Google DeepMind's evolutionary coding agent, and OpenEvolve, an open-source reimplementation of the AlphaEvolve framework.

✍️ Citation

@misc{skydiscover2025,
  title={SkyDiscover: A Flexible Framework for AI-Driven Scientific and Algorithmic Discovery},
  author={Liu, Shu and Cemri, Mert and Agarwal, Shubham and Krentsel, Alexander and Naren, Ashwin and Mang, Qiuyang and Li, Zhifei and Gupta, Akshat and Maheswaran, Monishwaran and Cheng, Audrey and Pan, Melissa and Boneh, Ethan and Ramchandran, Kannan and Sen, Koushik and Dimakis, Alexandros G. and Zaharia, Matei and Stoica, Ion},
  year={2025},
}