A more scalable version of FILO.

Code for the differentiable feasibility pump

Complexity Scaling Laws for Neural Models using Combinatorial Optimization (NeurIPS 2025)

State-of-the-art LLM-designed heuristics for Vehicle Routing Problems

code for paper "DRoC: Elevating Large Language Models for Complex Vehicle Routing via Decomposed Retrieval of Constraints"

code for paper "Large Language Models as End-to-end Combinatorial Optimization Solvers"

IPM-LSTM: A Learning-Based Interior Point Method for Solving Nonlinear Programs

Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization

RouteOpt

程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).

Official PyTorch implementation for "Large Language Diffusion Models"

Genetic programming using LLMs

GPU accelerated decision optimization

Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.

[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers

Open-source implementation of AlphaEvolve

ML4CO-Bench-101: Benchmark Machine Learning for Classic Combinatorial Problems on Graphs.

[AAAI 2026] TrajEvo: Designing Trajectory Prediction Heuristics via LLM-driven Evolution

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Neural Destruction Search for Vehicle Routing Problems

[ICLR 2025 - Workshop AgenticAI Oral] Large Language Models powered Neural Solvers for Generalized Vehicle Routing Problems

Neur2SP: Neural Two-Stage Stochastic Programming

[AAAI 2026] Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization

NVIDIA cuOpt examples for decision optimization

Learning-to-Optimize for Mixed-Integer Non-Linear Programming

[NeurIPS 2025 DiffCoALG WS] Neural Combinatorial Optimization for Real-World Routing

[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat

[ICLR 2025] Graph Assisted Offline-Online Deep Reinforcement Learning (GOODRL) for Dynamic Workflow Scheduling (DWS)

Code for [ICML2025]``Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design``.

A Python toolkit for Machine Learning (ML) practices for Combinatorial Optimization (CO).