When LLM Agents Meet Reinforcement Learning
Section: Base Framework · Tsinghua University (THUDM)
Entry
Appears in 6 awesome lists
Zhipu AI / Tsinghua's (THUDM) RL scaling framework — the production trainer behind the GLM series from GLM-4.5 to GLM-5.3-Flash; connects Megatron training with SGLang rollout through a unified train–rollout–buffer architecture (parameters sync, router-based generation, prompt/verifier management)…
Section: Base Framework · Tsinghua University (THUDM)
Section: Agentic RL
Section: Training and Fine-tuning · an LLM post-training framework for RL Scaling
Section: 7. Training & Fine-tuning Ecosystem · LLM post-training framework for RL Scaling from THUDM. Supports SFT and RL training with multi-turn compilation feedback, powering projects like TritonForge for automated GPU kernel generation. Apache 2.0 licensed.
Section: Industry Strength Reinforcement Learning · slime is an LLM post-training framework for RL Scaling.
Section: Agent Training (RL Post-Training) · Zhipu AI / Tsinghua's (THUDM) RL scaling framework — the production trainer behind the GLM series from GLM-4.5 to GLM-5.3-Flash; connects Megatron training with SGLang rollout through a unified train–rollout–buffer architecture (parameters sync, router-based generation, prompt/verifier management)…
Hugging Face's post-training library — the reference implementation of GRPO (the algorithm DeepSeek popularized) and the most-used single-GPU-to-cluster starting point for RL post-training; 75+ trainers across SFT / DPO / KTO / PPO / ORPO / CPO and more, with vLLM generation, PEFT/LoRA, and AMD…
The Ray+vLLM pioneer of open RLHF/RL post-training — the first framework built around a fully decoupled Ray-based distributed architecture (vLLM generation + DeepSpeed ZeRO/FSDP training, placement-colocated hybrid engine with sleep-mode weight sharing between actor/critic/reward/reference); PPO /…
Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.
NVIDIA's scalable RL post-training library (successor to NeMo Aligner, re-architected with the NeMo Framework) — the megatron-core-backed option in the open stack: GRPO / GSPO / DAPO / PPO / DPO / SFT(+LoRA) / on-policy distillation / GDPO with training via PyTorch DTensor (FSDP2) or Megatron Core…
Prime Intellect's fully asynchronous RL framework — "agentic RL training at scale" (the INTELLECT-3 report) — built to train 1T+ parameter MoE models on 1,000+ GPUs through three abstractions: a lightweight CPU Orchestrator (dataflow/scheduling), an FSDP2 Trainer, and vLLM inference as…
The most widely adopted open-source RL post-training framework for LLMs (ByteDance Seed; HybridFlow architecture, EuroSys 2025) — a flexible single-controller/dataflow abstraction that hybrid-orchestrates rollout generation (vLLM/SGLang) and training (FSDP/Megatron) in one program; PPO / GRPO /…
a Python library for using and training embedding and reranker models for applications like retrieval augmented generation, semantic search, and more
Microsoft Research's harnessed agentic RL trainer — v1.0 (~3,500 LOC, arXiv 2608.17528) trains agents inside their real production harnesses instead of reimplementing them within the trainer: an OpenAI-compatible API Gateway proxy records prompts/responses/logprobs of any agent (LangGraph, OpenAI…