Your private AI assistant on your phone: simple, safe, and ready anytime. 你手机里的私人 AI 助手：简单、安全，随时可用。

Code for our paper "Balanced Meta Learning and Diverse Sampling for Lifelong Task-Oriented Dialogue Systems" (AAAI2023).

"A Survey on Agent-as-a-Judge"

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

A collection of AI Agents papers (Updated biweekly)

(ACL2025 Findings) Official code for the paper "STeCa: Step-level Trajectory Calibration for LLM Agent Learning"

Official code for paper "SPA-RL: Reinforcing LLM Agent via Stepwise Progress Attribution"

[EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs

ChatReviewer: 使用ChatGPT分析论文优缺点，提出改进建议

Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

A Unified Library for Parameter-Efficient and Modular Transfer Learning

DSTC8 Track 1 Task 1 End-to-End Multi-Domain Dialog Challenge Result: