(Netflix 2025) Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning

VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications

Open source code for Paper: Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions

Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification

The official repo of "WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents"

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

MiroMind Research Agent: Fully Open-Source Deep Research Agent with Reproducible State-of-the-Art Performance on FutureX, GAIA, HLE, BrowserComp and xBench.

[IEEE Intelligent Systems] Awesome-Graph-augmented-LLM-Agent (GLA)

The official code of ARPO & AEPO

Democratizing Reinforcement Learning for LLMs

A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.

TreeRL: LLM Reinforcement Learning with On-Policy Tree Search in ACL'25

[NeurIPS'25] Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

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"

[arXiv 2025] Materials Generation in the Era of Artificial Intelligence: A Comprehensive Survey

Code, Data and Model for Paper "Learning from Peers in Reasoning Models"

ZeroSearch: Incentivize the Search Capability of LLMs without Searching

[ICML 2025] Official implementation for paper "A Comprehensive Analysis on LLM-based Node Classification Algorithms"

A Sober Look at Language Model Reasoning

✨ Official code for our paper: "Uncertainty-o: One Model-agnostic Framework for Unveiling Epistemic Uncertainty in Large Multimodal Models".

Open replication of DeepSeek R1 for text-to-graph extraction.

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.