6GAgentGym: Tool Use, Data Synthesis, and Agentic Learning for Network Management

TL;DR

This paper introduces 6GAgentGym, an interactive environment with tools and models enabling autonomous, closed-loop network management for 6G, demonstrating near GPT-5 performance on a new benchmark.

Contribution

The paper presents 6GAgentGym and associated methods for training autonomous agents capable of closed-loop network management in 6G environments.

Findings

8B open-source model achieves GPT-5 success rate on 6GAgentBench.

Closed-loop training improves agent performance on long-horizon tasks.

Experiment Model calibrated on NS-3 data supports environment interaction.

Abstract

Autonomous 6G network management requires agents that can execute tools, observe the resulting state changes, and adapt their decisions accordingly. Existing benchmarks based on static questions or scripted episode replay, however, do not support such closed-loop interaction, limiting agents to passive evaluation without the ability to learn from environmental feedback. This paper presents 6GAgentGym to provide closed-loop capability. The framework provides an interactive environment with 42 typed tools whose effect classification distinguishes read-only observation from state-mutating configuration, backed by a learned Experiment Model calibrated on NS-3 simulation data. 6G-Forge bootstraps closed-loop training trajectories from NS-3 seeds via iterative Self-Instruct generation with execution verification against the Experiment Model. Supervised fine-tuning on the resulting corpus followed by reinforcement learning with online closed-loop interaction enables an 8B open-source model to achieve comparable overall success rate to GPT-5 on the accompanying 6GAgentBench, with stronger performance on long-horizon tasks. Together, these components provide a viable path toward autonomous, closed-loop network management.