Official implementation of the NeurIPS 2025 paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"

Hierarchical Reasoning Model Official Release

[NeurIPS 2025] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains

This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.

Code and datasets for a paper: Reasoning-CV: Fine-tuning Powerful Reasoning LLMs for Knowledge-Assisted Claim Verification

Paper list for Efficient Reasoning.

[NeurIPS 2023] DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization

A PyTorch library for all things Reinforcement Learning (RL) for Combinatorial Optimization (CO)

[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution

Code for a paper accepted by NeurIPS 2024: UDC: A Unified Neural Divide-and-ConquernFramework for Large-Scale Combinatorial Optimization Problems

This is Liu Yuxuan's undergraduate graduation project at Tianjin University.

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

A Collection on Large Language Models for Optimization

[AAAI 2024] GLOP: Learning Global Partition and Local Construction for Solving Large-scale Routing Problems in Real-time

L2O/NCO codes from CIAM Group at SUSTech, Shenzhen, China

A functional Alpha Zero that plays Othello using Keras

An AI program to play Othello game. Use DQN, Double-DQN, Dueling DQN and MCTS. By Chengzhe XU and Hao XIANG