mlsanityData to 14 Oct 2026

Toward Super Agent System with Hybrid AI Routers

arXiv 2504.10519 ↗First posted 11 Apr 2025cs.AI cs.CL cs.LGcited by 6

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

AI Agents powered by Large Language Models are transforming the world through enormous applications. A super agent has the potential to fulfill diverse user needs, such as summarization, coding, and research, by accurately understanding user intent and leveraging the appropriate tools to solve tasks. However, to make such an agent viable for real-world deployment and accessible at scale, significant optimizations are required to ensure high efficiency and low cost. This position paper presents a design of the Super Agent System powered by the hybrid AI routers. Upon receiving a user prompt, the system first detects the intent of the user, then routes the request to specialized task agents with the necessary tools or automatically generates agentic workflows. In practice, most applications directly serve as AI assistants on edge devices such as phones and robots. As different language models vary in capability and cloud-based models often entail high computational costs, latency, and privacy concerns, we then explore the hybrid mode where the router dynamically selects between local and cloud models based on task complexity. Finally, we introduce the blueprint of an on-device super agent enhanced with cloud. With advances in multi-modality models and edge hardware, we envision that most computations can be handled locally, with cloud collaboration only as needed. Such architecture paves the way for super agents to be seamlessly integrated into everyday life in the near future.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 22 of its 33 references that are in the map. First posted on arXiv 11 Apr 2025.

Builds on

22 of 33 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Scaling Large Language Model-based Multi-Agent Collaboration11 Jun
  2. 2024Understanding the planning of LLM agents: A survey5 Feb

Other references · 20

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  3. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
  4. 2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routingcited by 372
  5. 2024RouterBench: A Benchmark for Multi-LLM Routing Systemcited by 238
  6. 2024GraphRouter: A Graph-based Router for LLM Selectionscited by 165
  7. 2025PlanGenLLMs: A Modern Survey of LLM Planning Capabilitiescited by 83
  8. 2023ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planningcited by 77
  9. 2024TensorOpera Router: A Multi-Model Router for Efficient LLM Inferencecited by 60
  10. 2023LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoningcited by 59
  11. 2024TinyAgent: Function Calling at the Edgecited by 58
  12. 2023Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomiescited by 34
8 more
  1. 2023Large Language Models for Intent-Driven Session Recommendationscited by 30
  2. 2024Intent Detection in the Age of LLMscited by 25
  3. 2024Online Cascade Learning for Efficient Inference over Streamscited by 20
  4. 2024User Intent Recognition and Satisfaction with Large Language Models: A User Study with ChatGPTcited by 19
  5. 2024Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detectioncited by 14
  6. 2025Complex LLM Planning via Automated Heuristics Discoverycited by 6
  7. 2025LANID: LLM-assisted New Intent Discoverycited by 3
  8. 2025Resource-efficient Inference with Foundation Model Programscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025A Survey on Collaborative Mechanisms Between Large and Small Language Modelscited by 14
  2. 2025ECVL-ROUTER: Scenario-Aware Routing for Vision-Language Modelscited by 4
  3. 2026PAAC: Privacy-Aware Agentic Device-Cloud Collaborationcited by 3
  4. 2025Uncertainty-Aware Collaborative System of Large and Small Models for Multimodal Sentiment Analysiscited by 1
  5. 2026BusMA: A Bus Communication Substrate for Multi-Agent Systemscited by 1
  6. 2025Intelligent Design 4.0: Paradigm Evolution Toward the Agentic AI Eracited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems
  2. 2026Infrastructure for the Agentic Web: Gap Analysis and Architecture from the Agentverse Platform
  3. 2026AgBench: Agentic AI Benchmarks for Personal AI Devices
  4. 2025SANNet: A Semantic-Aware Agentic AI Networking Framework for Multi-Agent Cross-Layer Coordination
  5. 2025Multi-agent Architecture Search via Agentic Supernet
  6. 2025AgentBay: A Hybrid Interaction Sandbox for Seamless Human-AI Intervention in Agentic Systems
  7. 2026Reimagining RAN Automation in 6G: An Agentic AI Framework with Hierarchical Online Decision Transformer ↗
  8. 2025Internet of Agents: Fundamentals, Applications, and Challenges