Lists (4)
Stars
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
💻 A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Kortix – build, manage and train AI Agents.
The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment
A Python example project showcasing the capabilities of **DeepSeek-V3.2** models combining "Thinking Mode" (Reasoning) with **Tool Calling**.
Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/
Scaling Agentic Environments Automatically.
AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。
An early research stage expert-parallel load balancer for MoE models based on linear programming.
Kimi K2 Thinking Agentic Search Unofficial Implementation
A Collection of Papers about Memory for Language Agents
Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.
Code repository for "RL Grokking Recipe: How RL Unlocks and Transfers New Algorithms in LLMs""
An Open-Source Large-Scale Reinforcement Learning Project for Search Agents
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning
MiniMax-M2, a model built for Max coding & agentic workflows.
Code for "APTBench: Benchmarking Agentic Potential of Base LLMs During Pre-Training"
🛠️ DeepAgent: A General Reasoning Agent with Scalable Toolsets
主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题