#
deter3
Follow
Lists (3)
Starred repositories
这是一个自动收集各大平台热点新闻（更关注 AI热点）、RSS订阅源以及特定Twitter Feed，进行处理、去重、总结，并通过多种渠道推送热点摘要的工具。该项目完全由Cursor和Trae接力编写
OpenPipe ART (Agent Reinforcement Trainer): train LLM agents
CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
A Text-to-SQL Agent with Self-Refinement, Format Restriction, and Column Exploration
Exploring Applications of GRPO
Agno is a lightweight library for building Agents with memory, knowledge, tools and reasoning.
A playground for code experiments, snippets, and small-scale projects in one organized repository.
Code repo for CLERC: A Legal Precedent Dataset for Case Retrieval and Retrieval-Augmented Analysis Generation (NAACL 2025)
Generalist and Lightweight Model for Text Classification
This repository contains a pipeline for fine-tuning Large Language Models (LLMs) for Text-to-SQL conversion using General Reward Proximal Optimization (GRPO).
A fast, local, and secure approach for training LLMs for coding tasks using GRPO with WebAssembly and interpreter feedback.
Official Repo for Open-Reasoner-Zero
Mentis: A powerful multi-agent orchestration framework built on LangGraph.
Code and implementations for the paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.
A live stream development of RL tunning for LLM agents
Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks
A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. All in a modern, AI-native editor.
Repository for the demo and paper: ReasonGraph: Visualisation of Reasoning Paths
Demo of knowledge graph creation and Graph RAG with BAML and Kuzu
Dataset of Python Codes for Reinforcement Learning
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬