mlsanityData to 7 Oct 2026

EvoRoute: Experience-Driven Self-Routing LLM Agent Systems

arXiv 2601.02695 ↗First posted 6 Jan 2026cs.CL cs.MAcited by 13

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

Abstract (arXiv)

Complex agentic AI systems, powered by a coordinated ensemble of Large Language Models (LLMs), tool and memory modules, have demonstrated remarkable capabilities on intricate, multi-turn tasks. However, this success is shadowed by prohibitive economic costs and severe latency, exposing a critical, yet underexplored, trade-off. We formalize this challenge as the Agent System Trilemma: the inherent tension among achieving state-of-the-art performance, minimizing monetary cost, and ensuring rapid task completion. To dismantle this trilemma, we introduce EvoRoute, a self-evolving model routing paradigm that transcends static, pre-defined model assignments. Leveraging an ever-expanding knowledge base of prior experience, EvoRoute dynamically selects Pareto-optimal LLM backbones at each step, balancing accuracy, efficiency, and resource use, while continually refining its own selection policy through environment feedback. Experiments on challenging agentic benchmarks such as GAIA and BrowseComp+ demonstrate that EvoRoute, when integrated into off-the-shelf agentic systems, not only sustains or enhances system performance but also reduces execution cost by up to 80% and latency by over 70%.

Key facts. Cited by 13 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 41 of its 69 references that are in the map. First posted on arXiv 6 Jan 2026.

Builds on

41 of 69 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025TaskCraft: Automated Generation of Agentic Tasks11 Jun
  2. 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation29 May
  3. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks12 Mar
  4. 2025Multi-agent Architecture Search via Agentic Supernet6 Feb
  5. 2024Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks7 Nov
  6. 2024Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents13 Aug
  7. 2024StreamBench: Towards Benchmarking Continuous Improvement of Language Agents13 Jun
  8. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey17 Apr
  9. 2023AutoAgents: A Framework for Automatic Agent Generation29 Sep
  10. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 31

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  4. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  5. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  6. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,151
  7. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  8. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 633
  9. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 616
  10. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 550
  11. 2022DS-1000: A Natural and Reliable Benchmark for Data Science Code Generationcited by 442
  12. 2024MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineeringcited by 429
19 more
  1. 2017A Tutorial on Thompson Samplingcited by 420
  2. 2023Self-collaboration Code Generation via ChatGPTcited by 255
  3. 2025BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agentcited by 183
  4. 2024GraphRouter: A Graph-based Router for LLM Selectionscited by 154
  5. 2024Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Makingcited by 142
  6. 2024Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agentscited by 91
  7. 2022DDXPlus: A New Dataset For Automatic Medical Diagnosiscited by 87
  8. 2025Universal Model Routing for Efficient LLM Inferencecited by 80
  9. 2023Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorldcited by 65
  10. 2025BEST-Route: Adaptive LLM Routing with Test-Time Optimal Computecited by 63
  11. 2025ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoningcited by 57
  12. 2025FlowReasoner: Reinforcing Query-Level Meta-Agentscited by 56
  13. 2023Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worldscited by 45
  14. 2024Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routingcited by 43
  15. 2025Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Trainingcited by 42
  16. 2025The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giantscited by 37
  17. 2025Optimizing Model Selection for Compound AI Systemscited by 34
  18. 2025Capability Instruction Tuning: A New Paradigm for Dynamic LLM Routingcited by 25
  19. 2025Towards Resource-Efficient Compound AI Systemscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 13.

13 papers.

Sort:

By area:

  1. 2026Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agentscited by 7
  2. 2026MonoScale: Scaling Multi-Agent System with Monotonic Improvementcited by 5
  3. 2026GenRouter: Unified Workflow Routing for Agentic Image Generationcited by 4
  4. 2026On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflowscited by 3
  5. 2026The Scaling Laws of Skills in LLM Agent Systemscited by 3
  6. 2026Uno-Orchestra: Parsimonious Agent Routing via Selective Delegationcited by 2
  7. 2026Task- and Session-Level Model Routing: A Common-Interface Hybrid Evaluation of Four Open-Source Routers Across Four Benchmarkscited by 2
  8. 2026The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Projectcited by 1
  9. 2026TACIT-Switch: Cost-Aware Model Escalation for LLM Agents from Censored Supervisioncited by 1
  10. 2026SwarmBench: Can Large Language Models Act as Agent Swarm Orchestrators?cited by 1
  11. 2026CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agentscited by 0
  12. 2026Learning What to Activate: Combinatorial Capability Allocation for Long-Horizon Multimodal Agentscited by 0
1 more
  1. 2026What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Runtime Burden Allocation for Structured LLM Routing in Agentic Expert Systems: A Full-Factorial Cross-Backend Methodology
  2. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
  3. 2026RSI-Router: Evolving Subtask-Level LLM Routing and Skills for Cost-Efficient Agents
  4. 2026Reward-Driven LLM Agent Workflows: Synthesizing POMDP Routing and Self-Correction for Autonomous Decision-Making
  5. 2026From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents
  6. 2026EASy: Towards Efficient LLM-Based Agentic System
  7. 2026EvoMAS: Evolutionary Generation of Multi-Agent Systems
  8. 2026Agentic Routing: The Harness-Native Data Flywheel