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

Jiao Chen; Jianhua Tang; Xiaotong Yang; Zuohong Lv

cs.NIMar 31, 2026

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

Authors: Jiao Chen, Jianhua Tang, Xiaotong Yang, Zuohong Lv

Organizations: Shenzhen Smart City Technology Development Group Company, Ltd. · Shien-Ming Wu School of Intelligent Engineering, South China University of Technology · China Unicom Group Co., Ltd.

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.

Figures & tables

Fig. 1 : Agent interaction model. The agent selects tools in a closed loop until the operator intent is verified. Configuration tools mutate network state, requiring re-observation.

Fig. 2 : Overview of the 6GAgentGym framework. Left : interactive environment with 42 typed tools and Experiment Model. Center : 6G-Forge bootstraps closed-loop trajectories via iterative Self-Instruct generation with execution verification. Right : 6GAgentBench tiered evaluation (L1–L3). Below: Agentic SFT + RL training pipeline.

Fig. 3 : The 6G-Forge data synthesis pipeline. Step 1 : NS-3 traces are annotated into seed trajectories. Step 2 : A teacher LLM generates new trajectories from seed demonstrations. Step 3 : Execution against $M_{\theta}$ produces golden and error-recovery traces. Step 4 : Verified trajectories expand the seed pool; Steps 2–4 repeat for $K$ iterations.

Proprietary Models
Model	Params	Success Rate $\uparrow$ (%)			SR $\uparrow$	SPL $\uparrow$
Model	Params	L1	L2	L3	SR $\uparrow$	SPL $\uparrow$
GPT-5	–	72.4	51.3	33.8	50.2	42.7
Claude-Sonnet-4	–	68.9	46.7	28.5	45.8	38.9
Gemini-2.5-Pro	–	65.3	44.2	30.1	44.1	37.2
DeepSeek-V3	685B ∗	63.8	42.5	27.6	42.3	35.8

TABLE I : Overall Success Rate (%) on 6GAgentBench. Best in bold , second best underlined . † : our fine-tuned models.

Training Data	L1	L2	L3	SR $\uparrow$	$\Delta$
Baseline (no fine-tuning)	42.1	24.6	12.8	24.9	–
Open-loop 6G trajectories	56.2	35.4	24.1	37.0	+12.1
Closed-loop synthetic only	61.3	40.2	29.6	41.8	+4.8
+ error recovery	62.8	41.5	31.4	43.1	+1.3
+ NS-3 real data (SFT)	64.7	43.8	34.2	45.3	+2.2
+ Agentic RL	68.2	48.5	39.1	50.1	+4.8

TABLE II : Ablation on Training Data Composition (8B model). Each row adds one component;

\Delta

shows incremental gain.

Fig. 4 : Visual analysis of 6GAgentBench results. (a) Performance by difficulty tier. (b) GRPO vs. DAPO RL training on the 4B model. (c) SR vs. SPL.

Model	$M_{\theta}$ $\uparrow$	NS-3 $\uparrow$	$\Delta$ $\downarrow$	$r$ $\uparrow$
GPT-5	50.0	47.5	$-$ 2.5	0.94
Claude-Sonnet-4	45.8	43.3	$-$ 2.5	0.93
Qwen3-VL-72B	37.5	34.2	$-$ 3.3	0.91
Qwen3-VL-8B	25.0	22.5	$-$ 2.5	0.92
6GAgent-8B (SFT)	45.0	42.5	$-$ 2.5	0.93
6GAgent-8B (SFT+RL)	50.8	47.5	$-$ 3.3	0.92

TABLE III : NS-3 Grounded Validation. Success Rate (%) under Experiment Model vs. full-fidelity NS-3 replay on 120 held-out tasks.

Panel of Figure 8 — Fig. 5 : 6GAgentGym interactive visualization dashboard. (a) Six-dimensional network metrics with SLA overlays. (b) Decision point identification with type distribution. (c) Per-UAV latency heatmap revealing handover-induced spikes.

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Tool Name	Input	Output
Observation ( $\mathcal{V}_{\text{obs}}$ , 16 tools)
read_telemetry	–	TelemetryState
check_network_state	–	NetworkState
get_signal_strength	Position	SignalStrength
scan_available_gnbs	Position	GnbList
get_edge_load	–	EdgeLoad

Appendix

TABLE IV : Complete tool catalog of 6GAgentGym.

AI Agent Benchmarks

AI agent benchmarks measure how reliably autonomous systems plan, use tools, interact, and complete tasks across controlled and real-world settings.

See all 1,494 papers

From Agentic to Autogenic Network Management for AI-Native 6G and Beyond: A Standards Perspective
Jul 7, 2026Petar Djukic, Sudipta Acharya, Takai Eddine Kennouche +16G Networks Wireless Communications
Bell Labs Research, 600 March Rd, Kanata, ON K2K 2E6 · University of Ottawa, 350 Legget Drive, Kanata, ON, Canada, K2K 2W7 · Nokia Technology Standards, Nokia France, 12 rue Jean Bart Massy 91300
6G Needs Agents: Toward Agentic AI-Native Networks for Autonomous Intelligence
May 2, 2026Mohamed Amine Ferrag, Abderrahmane Lakas, Merouane Debbah6G Networks LLM Agent Orchestration
Department of Computer and Network Engineering, United Arab Emirates University, UAE · Research Institute for Digital Future, Khalifa University, UAE
NetAgentBench: A State-Centric Benchmark for Evaluating Agentic Network Configuration
Apr 3, 2026Ahmed Twabi, Yepeng Ding, Tohru KondoFinite-State Machine LLM Agent Evaluation
Informatics & Data Science, Hiroshima University, Hiroshima, Japan

Jul 7, 2026J/K move · Enter open · S save

From Agentic to Autogenic Network Management for AI-Native 6G and Beyond: A Standards Perspective

Petar Djukic, Sudipta Acharya, Takai Eddine Kennouche, Burak Kantarci

Bell Labs Research, 600 March Rd, Kanata, ON K2K 2E6 · University of Ottawa, 350 Legget Drive, Kanata, ON, Canada, K2K 2W7 · Nokia Technology Standards, Nokia France, 12 rue Jean Bart Massy 91300

6G Networks Wireless Communications Agentic AI Self-Evolving Agents

Open paper AskPDF arXiv

Standards bodies, including TM Forum, 3GPP, and ETSI, are converging on Agentic AI as the foundation for next-generation network management, where Large AI Model (LAM)-based agents autonomously interpret intent, coordinate resources, and adapt operational behaviors at runtime. However, achieving this vision at the scale and complexity of 6G networks requires management systems that can generate and evolve their own automation software during operation. We introduce Autogenic network management, a reference architecture that extends agentic capabilities with self-programming, self reflection, self-orienting, and self-architecting capabilities. The architecture supports practical staged deployment beginning with human-supervised LAM-based agents and progressing toward autonomous operation as confidence builds. We demonstrate the approach through high-priority operator scenarios drawn from TM Forum's autonomous network use cases, showing how autogenic management addresses real operational challenges. We conclude with a research roadmap outlining the technical advances needed to make autogenic network management realistic in future 6G networks.

Abstract

AI Agent Benchmarks

Explore similar work

From Agentic to Autogenic Network Management for AI-Native 6G and Beyond: A Standards Perspective

6G Needs Agents: Toward Agentic AI-Native Networks for Autonomous Intelligence

NetAgentBench: A State-Centric Benchmark for Evaluating Agentic Network Configuration