Stars
τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
[ICML 2026] RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments
(ICML'25 Outstanding) CollabLLM: From Passive Responders to Active Collaborators
Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks
Training Proactive and Personalized LLM Agents
Source code for the collaborative reasoner research project at Meta FAIR.
[ICLR 2026] ParallelBench: Understanding the Tradeoffs of Parallel Decoding in Diffusion LLMs
Post-training with Tinker
Korea Investment & Securities Open API Github
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured mem…
Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
[COLM 2025] Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
A research prototype of a human-centered web agent
NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
Official implementation of Sparsified State-Space Models are Efficient Highway Networks (TMLR 2025).
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
A high-throughput and memory-efficient inference and serving engine for LLMs
Official Repo for Open-Reasoner-Zero
A hackable, simple, and reseach-friendly GRPO Training Framework with high speed weight synchronization in a multinode environment.
Fully open reproduction of DeepSeek-R1
A simple screen parsing tool towards pure vision based GUI agent
Pretraining and inference code for a large-scale depth-recurrent language model
Minimal reproduction of DeepSeek R1-Zero