mlsanityData to 7 Oct 2026

ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web

arXiv 2601.08276 ↗First posted 13 Jan 2026cs.AIcited by 7

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

Abstract (arXiv)

With the rise of the Agent Web and Model Context Protocol (MCP), the agent ecosystem is evolving into an open collaborative network, exponentially increasing accessible tools. However, current architectures face severe scalability and generality bottlenecks. To address this, we propose ACE-Router, a pipeline for training history-aware routers to empower precise navigation in large-scale ecosystems. By leveraging a dependency-rich candidate Graph to synthesize multi-turn trajectories, we effectively train routers with dynamic context understanding to create the plug-and-play Light Routing Agent. Experiments on the real-world benchmarks MCP-Universe and MCP-Mark demonstrate superior performance. Notably, ACE-Router exhibits critical properties for the future Agent Web: it not only generalizes to multi-agent collaboration with minimal adaptation but also maintains exceptional robustness against noise and scales effectively to massive candidate spaces. These findings provide a strong empirical foundation for universal orchestration in open-ended ecosystems.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 25 of its 44 references that are in the map. First posted on arXiv 13 Jan 2026.

Builds on

25 of 44 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems10 Aug
  2. 2025SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents4 Aug
  3. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMs10 Jan

Other references · 22

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  3. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  4. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  5. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  6. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
  7. 2024ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilitiescited by 272
  8. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 129
  9. 2023ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Searchcited by 103
  10. 2023T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Stepcited by 91
  11. 2025MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Serverscited by 89
  12. 2024ToolNet: Connecting Large Language Models with Massive Tools via Tool Graphcited by 59
10 more
  1. 2025MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Modelscited by 48
  2. 2025LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?cited by 47
  3. 2025Agentic Web: Weaving the Next Web with AI Agentscited by 43
  4. 2025ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agentscited by 36
  5. 2025MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmarkcited by 30
  6. 2025MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Toolscited by 30
  7. 2024ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesiscited by 27
  8. 2025Build the web for agents, not agents for the webcited by 17
  9. 2025Octopus: Agentic Multimodal Reasoning with Six-Capability Orchestrationcited by 8
  10. 2025GRAIL:Learning to Interact with Large Knowledge Graphs for Retrieval Augmented Reasoningcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Trainingcited by 23
  2. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  3. 2026What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agentscited by 2
  4. 2026Learning What to Activate: Combinatorial Capability Allocation for Long-Horizon Multimodal Agentscited by 0
  5. 2026Learning Multimodal Embeddings with Evidence-Aligned Readoutcited by 0
  6. 2026What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agentscited by 0
  7. 2026AutoGUIWorld: Image Generators as Visual World Models for GUI Agentcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026CASTER: Breaking the Cost-Performance Barrier in Multi-Agent Orchestration via Context-Aware Strategy for Task Efficient Routing
  2. 2026HM-ROUTER: Joint Model and Harness Routing for Agentic Systems
  3. 2026AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents
  4. 2025WebRouter: Query-specific Router via Variational Information Bottleneck for Cost-sensitive Web Agent
  5. 2025Optimal-Agent-Selection: State-Aware Routing Framework for Efficient Multi-Agent Collaboration
  6. 2025MasRouter: Learning to Route LLMs for Multi-Agent Systems
  7. 2026GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs
  8. 2026Agent-as-a-Router: Agentic Model Routing for Coding Tasks