mlsanityData to 7 Oct 2026

AgentJet: A Distributed Swarm Training Framework for Agentic Reinforcement Learning

arXiv 2606.04484 ↗First posted 3 Jun 2026cs.AI cs.LG cs.MAcited by 1

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

Abstract (arXiv)

Training reinforcement learning (RL) policies for large language model (LLM) agents requires optimizing multi-turn trajectories that interact with external environments. Existing training frameworks struggle with runtime failures, single-model constraints, incompatible task environments, and redundant context. We present AgentJet, a distributed swarm training framework based on a decoupled multi-node architecture. AgentJet treats the server--client topology as configurable: swarm servers host trainable models and perform optimization on GPU clusters, while detachable swarm clients execute arbitrary agents and communicate through OpenAI-compatible APIs. Reconfiguring this topology supports heterogeneous multi-model RL, mixed-task training with isolated runtimes, fault-tolerant execution, and live code iteration through hot-swappable clients. AgentJet also introduces context tracking with timeline merging, reducing actor-update time by 6.25x on AppWorld. The same detachable-client design supports an automated research system that conducts long-horizon, multi-day RL studies on large-scale clusters with limited human intervention. AgentJet is open-source and compatible with agent systems that issue standard LLM inference requests.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 39 of its 62 references that are in the map. First posted on arXiv 3 Jun 2026.

Builds on

39 of 62 references.

Closest ancestors · 7

Same direction, newest first

  1. 2026OpenClaw-RL: Train Any Agent Simply by Talking10 Mar
  2. 2026OpenTinker: Separating Concerns in Agentic Reinforcement Learning12 Jan
  3. 2025SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent20 Nov
  4. 2025Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony13 Oct
  5. 2025AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework5 Oct
  6. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Survey2 Sep
  7. 2025Agent Lightning: Train ANY AI Agents with Reinforcement Learning5 Aug

Other references · 32

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2025Qwen3 Technical Reportcited by 8,195
  7. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  8. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  9. 2024Qwen2.5 Technical Reportcited by 4,713
  10. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  11. 2023Let's Verify Step by Stepcited by 3,598
  12. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
20 more
  1. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  2. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  3. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  4. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  5. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  6. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  7. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  8. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
  9. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  10. 2023On-Policy Distillation of Language Models: Learning from Self-Generated Mistakescited by 840
  11. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
  12. 2023PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallelcited by 641
  13. 2017Ray: A Distributed Framework for Emerging AI Applicationscited by 516
  14. 2024AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agentscited by 359
  15. 2025Accelerating scientific discovery with Co-Scientistcited by 353
  16. 2025DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agentscited by 236
  17. 2025AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoningcited by 234
  18. 2017Distral: Robust Multitask Reinforcement Learningcited by 231
  19. 2024AgentScope: A Flexible yet Robust Multi-Agent Platformcited by 120
  20. 2025AgentRxiv: Towards Collaborative Autonomous Researchcited by 64

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026SRPO: Setwise Relative Policy Optimization for Multi-Agent LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning
  2. 2025AgentFly: Extensible and Scalable Reinforcement Learning for LM Agents
  3. 2025Agent-R1: A Unified and Modular Framework for Agentic Reinforcement Learning
  4. 2026Libra: Efficient Resource Management for Agentic RL Post-Training
  5. 2026ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning
  6. 2026AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs
  7. 2025Learn as Individuals, Evolve as a Team: Multi-agent LLMs Adaptation in Embodied Environments
  8. 2025AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning