Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning

An Open-Source Large-Scale Reinforcement Learning Project for Search Agents

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

A Tree Search Library with Flexible API for LLM Inference-Time Scaling

OpenClaw-RL: Train any agent simply by talking

The official repository of "A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications".

Self-referential self-improving agents that can optimize for any computable task

Research on Coding Agents

Curated academic CV templates and guidelines for PhD students, researchers, and faculty job applicants.

AI agents running research on single-GPU nanochat training automatically

LLM Chess - evaluating Large Language Models' reasoning and instruction-following abilities by simulating chess games

A collection of various llm pruning implementations, training code for GPUs & TPUs, and evaluation script.

CATArena is an engineering-level tournament evaluation platform for Large Language Model-driven code agents (LLM-driven code agents), based on an iterative competitive peer learning framework.

"AI-Trader: 100% Fully-Automated Agent-Native Trading"

Synthetic data curation for post-training and structured data extraction

Benchmark LLM reasoning capability by solving chess puzzles.

Training VLM agents with multi-turn reinforcement learning

Harsh Jhamtani*, Varun Gangal*, Eduard Hovy, Graham Neubig, Taylor Berg-Kirkpatrick. Learning to Generate Move-by-Move Commentary for Chess Games from Large-Scale Social Forum Data. ACL 2018

Open source neural network chess engine with GPU acceleration and broad hardware support.

A Text-Based Environment for Interactive Debugging

This is the official GitHub repository for our survey paper "Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models".

Fully open reproduction of DeepSeek-R1

[ICLR 2026] Learning to Reason without External Rewards

A library for generative social simulation

AI paper trading project inspired by nof1 Alpha Arena, using cctx for quotation.

Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments

Defeating the Training-Inference Mismatch via FP16

Natural Language Reinforcement Learning