[Submitted on 3 Jun 2026 (v1), last revised 21 Jul 2026 (this version, v2)]

View PDF HTML (experimental)

Abstract: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.

Submission history

From: Boyin Liu [view email]
[v1] Wed, 3 Jun 2026 06:02:52 UTC (11,219 KB)
[v2] Tue, 21 Jul 2026 12:35:46 UTC (2,398 KB)