# AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration

arXiv: https://arxiv.org/abs/2602.03786 · HTML: https://mlsanity.com/paper/2602.03786/

## Key facts

- Cited by 35 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 32 of its 38 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 32)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [AFlow: Automating Agentic Workflow Generation](https://mlsanity.com/paper/2410.10762/) (2024)
- [AutoAgents: A Framework for Automatic Agent Generation](https://mlsanity.com/paper/2309.17288/) (2023)
- [Scaling Long-Horizon LLM Agent via Context-Folding](https://mlsanity.com/paper/2510.11967/) (2025)
- [OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation](https://mlsanity.com/paper/2505.23885/) (2025)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL](https://mlsanity.com/paper/2508.13167/) (2025)
- [A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?](https://mlsanity.com/paper/2408.05109/) (2024)
- [TaskCraft: Automated Generation of Agentic Tasks](https://mlsanity.com/paper/2506.10055/) (2025)
- [ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration](https://mlsanity.com/paper/2511.21689/) (2025)
- [Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training](https://mlsanity.com/paper/2508.00414/) (2025)
- [Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search](https://mlsanity.com/paper/2502.17248/) (2025)
- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [Single-agent or Multi-agent Systems? Why Not Both?](https://mlsanity.com/paper/2505.18286/) (2025)
- [OAgents: An Empirical Study of Building Effective Agents](https://mlsanity.com/paper/2506.15741/) (2025)
- [DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework](https://mlsanity.com/paper/2510.17586/) (2025)
- [THREAD: Thinking Deeper with Recursive Spawning](https://mlsanity.com/paper/2405.17402/) (2024)
- [AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning](https://mlsanity.com/paper/2511.19304/) (2025)
- [Self-Steering Language Models](https://mlsanity.com/paper/2504.07081/) (2025)

## Built on by (most cited first, 30 of 35)

- [From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents](https://mlsanity.com/paper/2603.22386/) (2026)
- [JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution](https://mlsanity.com/paper/2608.25593/) (2026)
- [InfoPO: Information-Driven Policy Optimization for User-Centric Agents](https://mlsanity.com/paper/2603.00656/) (2026)
- [Harnessing Agentic Evolution](https://mlsanity.com/paper/2605.13821/) (2026)
- [Decentralized Multi-Agent Systems with Shared Context](https://mlsanity.com/paper/2606.10662/) (2026)
- [Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures](https://mlsanity.com/paper/2607.28802/) (2026)
- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation](https://mlsanity.com/paper/2605.05007/) (2026)
- [When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning](https://mlsanity.com/paper/2605.03314/) (2026)
- [Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.29790/) (2026)
- [Can LLMs Perceive Time? An Empirical Investigation](https://mlsanity.com/paper/2604.00010/) (2026)
- [Robust Reasoning Benchmark](https://mlsanity.com/paper/2604.08571/) (2026)
- [SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research](https://mlsanity.com/paper/2606.09730/) (2026)
- [Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence](https://mlsanity.com/paper/2608.21156/) (2026)
- [Scalable Environments Drive Generalizable Agents](https://mlsanity.com/paper/2605.18181/) (2026)
- [Orchestra-o1: Omnimodal Agent Orchestration](https://mlsanity.com/paper/2606.13707/) (2026)
- [Architectural Implications of Agentic AI Workflows](https://mlsanity.com/paper/2608.04458/) (2026)
- [Retrieval-Conditioned Topology Selection with Provable Budget Conservation for Multi-Agent Code Generation](https://mlsanity.com/paper/2605.05657/) (2026)
- [SQLConductor: Search-to-Policy Learning for Step-wise Text-to-SQL Orchestration](https://mlsanity.com/paper/2606.23537/) (2026)
- [Spawn Freely, Act Sparingly: Progressive Risk Vesting for Recursive LLM-Agent Trees](https://mlsanity.com/paper/2609.01035/) (2026)
- [SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks](https://mlsanity.com/paper/2606.15872/) (2026)
- [Testing and Evaluation of Agentic AI Systems In Military Command and Control](https://mlsanity.com/paper/2608.20597/) (2026)
- [Spine-Branch Coordination for Multi-agent Computer Use](https://mlsanity.com/paper/2608.22077/) (2026)
- [AgentBetta: Verification-Driven Adaptive Configuration of an AI Nano-Agent through Selective Expansion and Verified Contraction](https://mlsanity.com/paper/2609.23512/) (2026)
- [Learning What to Activate: Combinatorial Capability Allocation for Long-Horizon Multimodal Agents](https://mlsanity.com/paper/2609.27869/) (2026)
- [RepoMAS: Solving Progressively Specified Tasks with Issue-Driven Multi-Agent Systems](https://mlsanity.com/paper/2609.32490/) (2026)
- [Trust the Brand, Lose Control: How Identity Hijacks LLM Agent Orchestration](https://mlsanity.com/paper/2609.32635/) (2026)
- [CAIRN: Dynamic Fact-Intent DAGs for Multi-Agent Exploration](https://mlsanity.com/paper/2609.32700/) (2026)
- [Visual Parallel Search: Learning to Search High-Resolution Images with Parallel Tile Inspection and Adaptive Zoom](https://mlsanity.com/paper/2609.37002/) (2026)
- [Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?](https://mlsanity.com/paper/2609.39578/) (2026)

## Abstract (arXiv)

Language agents have shown strong promise for task automation. Realizing this promise for increasingly complex, long-horizon tasks has driven the rise of a sub-agent-as-tools paradigm for multi-turn task solving. However, existing designs still lack a dynamic abstraction view of sub-agents, thereby hurting adaptability. We address this challenge with a unified, framework-agnostic agent abstraction that models any agent as a tuple Instruction, Context, Tools, Model. This tuple acts as a compositional recipe for capabilities, enabling the system to spawn specialized executors for each task on demand. Building on this abstraction, we introduce an agentic system AOrchestra, where the central orchestrator concretizes the tuple at each step: it curates task-relevant context, selects tools and models, and delegates execution via on-the-fly automatic agent creation. Such designs enable reducing human engineering efforts, and remain framework-agnostic with plug-and-play support for diverse agents as task executors. It also enables a controllable performance-cost trade-off, allowing the system to approach Pareto-efficient. Across three challenging benchmarks (GAIA, SWE-Bench, Terminal-Bench), AOrchestra achieves 16.28% relative improvement against the strongest baseline when paired with Gemini-3-Flash. The code is available at: https://github.com/FoundationAgents/AOrchestra