iterative-refinement

Open-source implementation of AlphaEvolve

OpenAlpha_Evolve is an open-source Python framework inspired by the groundbreaking research on autonomous coding agents like DeepMind's AlphaEvolve.

Official Implementation for "ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement" (ICCV 2021) https://arxiv.org/abs/2104.02699

LoongFlow is an expert-grade Agent framework for Loop Engineering. Through a Plan-Execute-Summary loop and structured experiential memory, it enables AI to continuously think, execute, reflect, and evolve across complex software engineering, mathematical, and machine learning tasks.

Lightweight Event-based Optical Flow Estimation via Iterative Deblurring

Probabilistic Downscaling of Climate Variables Using Denoising Diffusion Probabilistic Models

Installable Codex skill for long-running autonomous coding refinement loops with validation and resumable state

Mulitprecision Arrays

Self-Refine iterative critique-and-refinement loop evaluating constraint adherence and applying structured revisions

Self-Refine iterative critique-and-refinement loop evaluating constraint adherence and applying structured revisions

Enable Codex to run objective-first autonomous loops with mandatory review and optional verification for long-running task completion

For our AAAI25 paper LATTE: Improving Latex Recognition for Tables and Formulae with Iterative Refinement by Nan Jiang, Shanchao Liang, Chengxiao Wang, Jiannan Wang, and Lin Tan

Core part of HPL-AI implementation based on HPL-2.3. For the complete version of our HPL-AI benchmark, please go to the following site.

Minimizing Cost and Risk Using Bayesian Estimation and Gaussian Process Regression

AI-powered business analyst agent with multi-agent collaboration workflow for iterative project specification refinement

CodeOpt: A framework for optimizing code performance using Two-Stage Sampling, Few-Shot Learning, and Iterative Self-Reflection with support for Genetic Algorithm Inspired Chain-of-Thought (GA-COT).

AI quality method for validating LLM output against predefined criteria. Includes a builder-critic workflow, evidence checks, cost limits and stopping conditions.

Cost-aware multi-agent LLM framework with quality gates. Simple questions: 1 call. Code tasks: writer+reviewer loop.

Code for student-code guided test case generation for CS Education.

Post-it technique et prompt-template prêt à l'emploi pour le Loop Engineering : boucle Producteur / Contrôleur Qualité en session unique avec un LLM (ChatGPT, Claude...). Document Markdown unique à copier-coller comme prompt système, avec plafond d'itérations, points de contrôle humains et critères de qualité mesurables, propres à la tâche.