Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics
- agent-rl
- agentic-ai
- llm-agents
- reinforcement-learning
132,241 visible repositories in the index
49–72 of 144 · Most stars
Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics
⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.
A modular RL library to fine-tune language models to human preferences
Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’
Scalable toolkit for efficient model reinforcement
Extract structured data and insights from documents using LLMs and decision models
An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
Information hub for our project training the largest possible historical LLMs.
WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.
An easy way to extract information from documents
Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
LLM(😽)
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
AgentEvolver: Towards Efficient Self-Evolving Agent System
Multimodal RL training framework for diffusion & omni models
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
Evaluate and improve models and agents using environments
Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀
Fine-tune LLM agents with online reinforcement learning