mlsanityData to 14 Oct 2026

Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation

arXiv 2605.05007 ↗First posted 6 May 2026cs.AIcited by 6

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

Abstract (arXiv)

Large language model (LLM) multi-agent systems typically rely on rigid orchestration, committing either to flat per-query routing or to hand-engineered task decomposition, so decomposition depth, worker choice, and inference budget are not jointly optimized under one objective. We introduce Uno-Orchestra, a unified orchestration policy that selectively decomposes a task and dispatches each subtask to an admissible (model, primitive) pair, with both decisions learned together from curated RL trajectories grounded in real worker interactions. Against 22 baselines on a 13-benchmark suite spanning math, code, knowledge, long-context, and agentic tool-use, Uno-Orchestra reaches 77.0% macro pass@1, roughly 16% above the strongest workflow baseline, at roughly an order of magnitude lower per-query cost, advancing the accuracy-efficiency frontier of selective delegation.

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 61 of its 78 references that are in the map. First posted on arXiv 6 May 2026.

Builds on

61 of 78 references.

Closest ancestors · 10

Same direction, newest first

  1. 2026Explainable Model Routing for Agentic Workflows4 Apr
  2. 2026WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning4 Feb
  3. 2026AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration3 Feb
  4. 2026Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning7 Jan
  5. 2026EvoRoute: Experience-Driven Self-Routing LLM Agent Systems6 Jan
  6. 2025A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems10 Aug
  7. 2025Multi-Agent Collaboration via Evolving Orchestration26 May
  8. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review28 Apr
  9. 2025Survey on Evaluation of LLM-based Agents20 Mar
  10. 2025MasRouter: Learning to Route LLMs for Multi-Agent Systems16 Feb

Other references · 51

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  6. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  8. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  9. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  10. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  11. 2023Let's Verify Step by Stepcited by 3,789
  12. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
38 more
  1. 2021Program Synthesis with Large Language Modelscited by 3,637
  2. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  3. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  5. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,883
  6. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  7. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  8. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  9. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  10. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  11. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,301
  12. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  13. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  14. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  15. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 903
  16. 2017Crowdsourcing Multiple Choice Science Questionscited by 765
  17. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  18. 2026Kimi K2.5: Visual Agentic Intelligencecited by 501
  19. 2025Group-in-Group Policy Optimization for LLM Agent Trainingcited by 497
  20. 2022FOLIO: Natural Language Reasoning with First-Order Logiccited by 235
  21. 2024ToolACE: Winning the Points of LLM Function Callingcited by 216
  22. 2021QuALITY: Question Answering with Long Input Texts, Yes!cited by 208
  23. 2023TACO: Topics in Algorithmic COde generation datasetcited by 160
  24. 2023AutoMix: Automatically Mixing Language Modelscited by 125
  25. 2024RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Modelscited by 88
  26. 2025Tree Search for LLM Agent Reinforcement Learningcited by 79
  27. 2025Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learningcited by 72
  28. 2025ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestrationcited by 47
  29. 2026LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routingcited by 38
  30. 2025TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Modelscited by 31
  31. 2025ICL-Router: In-Context Learned Model Representations for LLM Routingcited by 28
  32. 2024THREAD: Thinking Deeper with Recursive Spawningcited by 25
  33. 2026SkillOrchestra: Learning to Route Agents via Skill Transfercited by 23
  34. 2026The Orchestration of Multi-Agent Systems: Architectures, Protocols, and Enterprise Adoptioncited by 15
  35. 2025Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Routercited by 13
  36. 2026Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarioscited by 10
  37. 2026Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selectioncited by 4
  38. 2026How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learningcited by 3

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Mint-Agent: Introducing Finance-Native Agentic Foundation Modelscited by 0
  2. 2026Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimizationcited by 0
  3. 2026Decoupled Multi-Agent Orchestrationcited by 0
  4. 2026Proactive Agentic Orchestrationcited by 0
  5. 2026TurnCost: Turns, Not Observations: Cache-Aware Loop Engineering for Coding Agentscited by 0
  6. 2026Degrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026AdaptOrch: Task-Adaptive Multi-Agent Orchestration in the Era of LLM Performance Convergence
  2. 2026Orchestra-o1: Omnimodal Agent Orchestration
  3. 2026Small Model as Master Orchestrator: Learning Unified Agent-Tool Orchestration with Parallel Subtask Decomposition
  4. 2026OrchSLM: Probing the Dynamics of Small Language Model Orchestration
  5. 2026Learning What to Retain: Gated-Memory Routing for Efficient Collaboration in Multi-Agent LLM Systems
  6. 2026A Formal Hierarchical Architecture for Agentic Orchestration with Stack-Based Execution and Lazy Discovery
  7. 2026Persistent LLM Orchestration of Heterogeneous Robot Teams via Partial Delegation to Multi-Agent Protocols
  8. 2026Orchestrating Intelligence: Confidence-Aware Routing for Efficient Multi-Agent Collaboration across Multi-Scale Models