Research map / Large language models / Agents, code and math
NetArena: Dynamically Generated LLM Benchmarks for Network Applications
Yajie Zhou, Jiajun Ruan, Eric S. Wang, Sadjad Fouladi, Francis Y. Yan, Kevin Hsieh, Zaoxing Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| scale query set from 100-150 to 2000-5000 queries | NetArena evaluation · CP, Routing, K8s | confidence-interval overlap between agents: 85% -> 0% | Improved |
| use larger query set (5000 vs 100 queries) | GPT+ReAct vs Qwen agents · Capacity planning | CI overlap: more than 50% overlap -> none | Improved |
| use K8s:2000 instead of K8s:150 queries | GPT+ReAct · K8s | safety rate | Hurt |
| increase task complexity from Level 1 to Level 3 | GPT-4o+Few-shot · Capacity planning | correctness and safety | Hurt |
| fine-tune on single complexity level only (SFT-Level-2) (ablation) | Qwen-7B · Capacity planning Level 3 | correctness | Hurt |
| fine-tune on mixed-level data (2000 queries) instead of one level (ablation) | Qwen-7B · Capacity planning | correctness: over 0.96 across all levels | Improved |
| single-level SFT effect on safety across levels (ablation) | Qwen-7B · Capacity planning | safety rate | No clear effect |
| GRPO fine-tuning with emulator rewards | Qwen2.5-0.5B · Routing (Mininet) | valid command generation | Improved |
Closest papers by meaning
- GraphArena: Evaluating and Exploring Large Language Models on Graph Computation (ICLR 2025 · similarity 0.87)
- Dr.LLM: Dynamic Layer Routing in LLMs (ICLR 2026 · similarity 0.86)
- AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks (NeurIPS 2025 · similarity 0.86)
- Evaluating Test-Time Scaling of General LLM Agents (NeurIPS 2026 · similarity 0.86)
- Benchmarking Agentic Workflow Generation (ICLR 2025 · similarity 0.86)
- DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
