OpenLoopX · LLM4AD Next

From problem description to runnable evolutionary algorithm search — in one command.
LLM-driven automated algorithm design with evolutionary optimization

Website · Quickstart · Docs · Wiki

English | 中文

---

⭐ Star us on GitHub to earn 10$ bonus tokens for the Online Website!

---

🔥 News

• 🧮 [2026.09][New Dataset]: The AlphaEvolve Mathematics Benchmark Suite adds 11 independently runnable mathematical optimization cases, case-local evaluators, evolved implementations, and reusable experience artifacts.
• 🏝️ [2026.09][New Search Method]: Diverse Island GA is now available, assigning a continuous spectrum of exploitation, correction, and independent-exploration behaviors across any number of islands while coordinating migration and memory use.
• 🎯 [2026.08][New Feature]: Algorithm Design Skills — Modular skill definitions (EoH, FunSearch, ReEvo, MEoH, MOEA/D) that enable coding agents to autonomously design algorithms. See Algorithm Design Skills.
• 🔬 [2026.07][New Feature]: Search methods migrated — EoH, MEoH, ReEvo, and MCTS-AHD are now available as standalone orchestrators. See Search Methods.
• 🧠 [2026.07][New Feature]: MindMemOS-backed long-term memory is now available, with global, project, and task memory scopes plus configurable Chat and Embedding model bindings. See the Memory Guide.
• 🚀 [2026.07][New Release]: LLM4AD_Next Online Trial is now available at https://llm4ad-next.cn/ — try the full problem-to-algorithm workflow directly in your browser with no local setup.
• ✨ [2026.07][New Feature]: Introducing an interactive problem-to-project workflow that turns natural-language problem descriptions into runnable evolutionary algorithm search projects.
• 🐳 [2026.07][New Feature]: Versioned Docker Hub deployment images are now aligned with GitHub Release tags for reproducible local deployment.

🚀 Why LLM4AD_Next?

Traditionally, using Large Language Models for Automated Algorithm Design (LLM4AD) required a tedious, multi-step configuration pipeline. LLM4AD_Next destroys this entry barrier.

With LLM4AD_Next, after creating your directory, all of these painful steps are fully automated through an interactive conversational terminal. Just run:

uv run llm4ad chat

Our built-in AI-powered consultant will interview you, instantly understand your requirements, and automatically generate a ready-to-run pipeline (evaluator, algorithm skeleton, configuration, and debugger) so you can leap straight into producing Useful Algorithms.

🎯 Key Features Overview

• 🧠 LLM-Powered Design & 🧬 Evolutionary Optimization combined to automatically evolve top-performing code.
• 💬 Interactive Configuration (llm4ad chat) — Your conversational AI consultant that generates the entire runnable app framework.
• 🔍 Evolve-Block Advisor & Recommender — Point LLM4AD_Next at any repository, and it will scan, score, and recommend exactly which blocks of code are most promising to evolve to hit your goals.

Search Methods (Automatic Heuristic Design)

Migration status of the Automatic Heuristic Design (AHD) search methods from the original LLM4AD platform.

Method	Status	Skill	Method	Status	Skill
IslandGA	✅ Available	⏳ Pending	FunSearch	⏳ Pending	🧩 Available
Diverse Island GA	✅ Available	⏳ Pending	HillClimb	⏳ Pending	⏳ Pending
MEoH	✅ Available	🧩 Available	LHNS	⏳ Pending	⏳ Pending
DyCA	✅ Available	⏳ Pending	LLaMEA	⏳ Pending	⏳ Pending
EoH	✅ Available	🧩 Available	MLES	⏳ Pending	⏳ Pending
ReEvo	✅ Available	🧩 Available	MOEA/D	⏳ Pending	🧩 Available
MCTS-AHD	✅ Available	🧩 Available	NSGA-II	⏳ Pending	🧩 Available
			PartEvo	⏳ Pending	⏳ Pending
			RandSample	⏳ Pending	⏳ Pending

Using the migrated methods

Set evolution.type in your config and run llm4ad run <config.yaml>. See examples/config/config.complete.yaml for full examples.

evolution:
  type: "eoh"  # options include "diverse_island_ga", "island_ga", "eoh", "meoh", "reevo", "mcts_ahd", "dyca"

Algorithm Design Skills

Modular skill definitions that enable coding agents to autonomously design algorithms. Give a coding agent this prompt:

I want you to design a [PROBLEM] solver using the [SKILL] method.

Skill: https://github.com/Optima-CityU/LLM4AD_Next/blob/develop/skills/algo-design/[SKILL]/SKILL.md
Task: /path/to/your/task/

Read the skill, read the task package, run [N] generations, give me the best algorithm.

See use_example for a complete TSP + EoH example.

🏆 Featured Cases

AlphaEvolve Mathematics Benchmark

Case (↑ Max · ↓ Min)	LLM4AD Next	Published Results	Artifacts
26 circles in a unit square ↑	2.6359830833 Δ +1.21e-7	AlphaEvolve 2.6358627564 LoongFlow 2.6359829625	Code · Experience · Result
21 circles in a perimeter-four rectangle ↑	2.3658323757 Δ +1.46e-7	AlphaEvolve 2.3658321334 LoongFlow 2.3658322295	Code · Experience · Result
11 unit hexagons in a regular hexagon ↓	3.9246884168 Δ +0.00421844	AlphaEvolve 3.930092 LoongFlow 3.9289068555	Code · Experience · Result
16-point maximum/minimum distance ratio ↓	12.8892299077 Δ +1.36e-5	AlphaEvolve 12.8892661120 LoongFlow 12.8892435472	Code · Experience · Result
Uncertainty inequality ↓	0.352099104419 Δ +2.68e-12	AlphaEvolve 0.352099104423 LoongFlow 0.352099104422	Code · Experience · Result
Second autocorrelation inequality ↑	0.9053043553 Δ +0.00260225	AlphaEvolve 0.8962799442 LoongFlow 0.9027021077	Code · Experience · Result
First autocorrelation inequality ↓	1.5074598117 Δ -0.00216584	AlphaEvolve 1.5052939684 LoongFlow 1.5095273149	Code · Experience · Result
Minimum overlap ↓	0.3809250447 Δ -1.13e-5	AlphaEvolve 0.380924 LoongFlow 0.3809137564	Code · Experience · Result
Heilbronn problem in an equilateral triangle ↑	0.0365298881928 Δ -1.69e-9	AlphaEvolve 0.0365298898800 LoongFlow 0.0365298898793	Code · Experience · Result

Quick Start

Try Online	Watch Instruction	Read Docs
Run LLM4AD_Next in your browser. No installation or API key required.	Watch the introduction before installing or configuring a local environment.	Use the documentation path map for setup, configuration, examples, and Web UI deployment.

Instruction Video

Run LLM4AD Next

Option A: Online Demo (No Installation Required)

Use the online demo from Quick Start, or open it directly: Launch Online Demo.

No setup, no API key needed — just open the link and start designing algorithms.

Option B: Local Installation

Requires Python 3.12+ (pinned in .python-version) and uv (recommended) or pip. A plain uv sync sets up everything, including the chatv2 AI build agent, out of the box.

# Clone the repository
git clone https://github.com/Optima-CityU/LLM4AD_Next.git
cd LLM4AD_Next

# Install dependencies
uv sync

# Configure your LLM provider (see Global Settings section below)
# Or set environment variables directly:
export LLM_BASE_URL="https://api.openai.com/v1"
export LLM_API_KEY="your-api-key"
export LLM_MODEL="gpt-4o"

# Option 1: Interactive configuration (recommended for new users)
llm4ad chat

# Option 2: Run with an existing config file
llm4ad run examples/applications/tsp_benchmark_python/config.yaml

For optional dependency groups (infra, providers, eval, dev, docs, all) and uv installation, see the Installation Guide.

Global Settings

Create ~/.llm4ad/settings.yaml to configure shared providers across all projects:

providers:
  - name: default
    type: openai
    api_key: ${OPENAI_API_KEY}
    model: gpt-4o
  - name: anthropic
    type: anthropic
    api_key: ${ANTHROPIC_API_KEY}
    model: claude-sonnet-4-20250514

Task configs then only need the provider name — credentials and model are resolved from global settings automatically.

For CLI commands, the interactive chat workflow, the Evolve-Block Advisor / Recommender, and the Python API, see the Documentation.

Documentation

• Documentation Home
• Quick Start Guide
• Configuration Guide
• Writing Evaluators

Local Development

# Serve documentation with live reload
mkdocs serve

# Build static documentation
mkdocs build

Project Structure

LLM4AD/
├── src/llm4ad/          # Main source code
│   ├── config/           # Configuration schemas and global settings
│   ├── consultant/       # Interactive configuration wizard
│   ├── builder/          # Task builder (analyzer, creator, validator, writer)
│   ├── advisor/          # Evolve-block advisor and recommender
│   ├── provider/         # LLM provider implementations
│   ├── planner/          # Algorithm planning layer
│   ├── coder/            # Code generation layer
│   ├── evaluator/        # Evaluation layer
│   ├── orchestrator/     # Workflow orchestration
│   ├── infra/            # Infrastructure (Ray, monitoring)
│   └── utils/            # Utilities
├── examples/             # Example configurations and applications
├── tests/                # Test suite
└── docs/                 # Documentation

Contributing

Contributions are welcome! Please read our Contributing Guide for details.

# Set up development environment
uv sync --extra all

# Run tests
pytest

# Format code
black src/ tests/
ruff check src/ tests/ --fix

License

This project is licensed under the BSD 3-Clause License - see the LICENSE file for details.

Acknowledgements

The AutoResearch module is based on / adapted from AutoResearchClaw (MIT License). Its original copyright and license notice are retained in THIRD_PARTY_LICENSES.md.

Support

• Documentation
• Discussions
• Issue Tracker

Join the Community

Scan the QR code with WeChat to join the LLM4AD_Next community group.