Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.
An open-source AlphaEvolve-style evolutionary algorithm discovery engine. LLM-driven mutation operator inside an island-model evolutionary loop.
Multi-language algorithms & data structures solving engine: Java, C++ and Rust tiers with a Python reference, cross-language benchmarks, and a local synthesizer that rediscovers algorithms (Kadane, buy-and-sell, jump game) from examples.
A benchmark and execution harness for evaluating AI-driven research and optimization systems on real GitHub repositories
A research repo into differentiable algorithm search for 3x3 matmul
Codex Skill and platform-neutral research CLI for reproducible, auditable OpenEvolve algorithm discovery with holdouts, ablations, budgets, and novelty audits.
ADC-bench: A benchmark for algorithm discovery, transfer, and certification in AI coding agents.
Autonomous neuro-symbolic research agent synthesizing, verifying, and sandboxing algorithms with FunSearch, CEGIS (Z3), Lean 4 proofs, and Wasmtime JIT
To associate your repository with the algorithm-discovery topic, visit your repo's landing page and select "manage topics."