AgentJet: A Flexible Swarm Training Framework for Agentic Reinforcement Learning
Summary
AgentJet is a distributed swarm training framework for LLM agent reinforcement learning that decouples agent rollouts from model optimization, enabling heterogeneous multi-agent RL, multi-task training, fault tolerance, and live code iteration with 1.5-10x training speedup. It also introduces an automated research system capable of autonomously conducting multi-day RL studies on large-scale clusters.
View Cached Full Text
Cached at: 06/05/26, 02:07 AM
# AgentJet: A Flexible Swarm Training Framework for Agentic Reinforcement Learning Source: [https://arxiv.org/abs/2606.04484](https://arxiv.org/abs/2606.04484) [View PDF](https://arxiv.org/pdf/2606.04484) > Abstract:We present AgentJet, a distributed swarm training framework for large language model \(LLM\) agent reinforcement learning\. Unlike centralized frameworks that tightly couple agent rollouts with model optimization, AgentJet adopts a decoupled multi\-node architecture in which swarm server nodes host trainable models and run optimization on GPU clusters, whereas swarm client nodes execute arbitrary agents on arbitrary devices\. This design provides capabilities that are difficult to support in centralized frameworks: \(1\) heterogeneous multi\-model reinforcement learning, enabling the training of heterogeneous multi\-agent teams with multiple LLM as brains; \(2\) multi\-task cocktail training with isolated agent runtimes; \(3\) fault\-tolerant execution that prevents external environment failures from interrupting the training process; and \(4\) live code iteration, which allows agents to be edited during training by replacing swarm client nodes\. To support efficient RL in multi\-model, multi\-turn, and multi\-agent settings, AgentJet introduces a context tracking module with timeline merging, which consolidates redundant context and achieves a 1\.5\-10x training speedup\. Finally, AgentJet introduces an automated research system that takes a research topic as input and autonomously conducts long\-horizon, multi\-day RL studies on large\-scale clusters\. By leveraging the swarm architecture, this system reproduces key exploratory workflows of RL researchers without human intervention during execution\. ## Submission history From: Boyin Liu \[[view email](https://arxiv.org/show-email/1e712628/2606.04484)\] **\[v1\]**Wed, 3 Jun 2026 06:02:52 UTC \(11,219 KB\)
Similar Articles
EASy: Towards Efficient LLM-Based Agentic System
The paper proposes EASy, a trainable agentic framework that uses reinforcement learning to jointly optimize task performance and computational efficiency, introducing a milestone-plan-act workflow, dependency-aware execution graphs, and tree-structured rollout for training.
@_akhaliq: LiteResearcher A Scalable Agentic RL Training Framework for Deep Research Agent
LiteResearcher is a scalable reinforcement learning training framework designed for deep research agents.
Agent Lightning: Train ANY AI Agents with Reinforcement Learning
Agent Lightning introduces a flexible reinforcement learning framework for training large language models in AI agents, achieving decoupling between agent execution and training to handle complex interactions.
@h100envy: This paper completely changed how I think about a swarm of agents: Describe an agent as a graph -> Nodes are operations…
A paper presents a framework where LLM agents are represented as computational graphs with nodes as operations and edges as information flow, enabling automatic optimization of both node prompts and edge connectivity via RL, turning scattered agent swarms into a single optimizable graph.
MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning
MetaAgent-X introduces an end-to-end reinforcement learning framework that jointly optimizes the design and execution of automatic multi-agent systems, overcoming the frozen-executor ceiling and achieving up to 21.7% gains over existing baselines.