# Alto: Orchestrating Distributed Compound AI Systems with Nested Ancestry

arXiv: https://arxiv.org/abs/2403.04311 · HTML: https://mlsanity.com/paper/2403.04311/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 52 references that are in the map.
- First posted on arXiv 7 Mar 2024.

## Builds on (most cited first, 17 of 17)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Ray: A Distributed Framework for Emerging AI Applications](https://mlsanity.com/paper/1712.05889/) (2017)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios](https://mlsanity.com/paper/2307.13528/) (2023)
- [Multi-Stage Document Ranking with BERT](https://mlsanity.com/paper/1910.14424/) (2019)
- [Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models](https://mlsanity.com/paper/2402.14207/) (2024)
- [Complex Claim Verification with Evidence Retrieved in the Wild](https://mlsanity.com/paper/2305.11859/) (2023)
- [BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents](https://mlsanity.com/paper/2308.05960/) (2023)
- [WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia](https://mlsanity.com/paper/2305.14292/) (2023)
- [InferCept: Efficient Intercept Support for Augmented Large Language Model Inference](https://mlsanity.com/paper/2402.01869/) (2024)

## Built on by (most cited first, 7 of 7)

- [StructuredRAG: JSON Response Formatting with Large Language Models](https://mlsanity.com/paper/2408.11061/) (2024)
- [Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms](https://mlsanity.com/paper/2508.18298/) (2025)
- [TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval](https://mlsanity.com/paper/2502.20969/) (2025)
- [Flow State: Humans Enabling AI Systems to Program Themselves](https://mlsanity.com/paper/2504.03771/) (2025)
- [Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulation](https://mlsanity.com/paper/2606.01725/) (2026)
- [The Architecture of Trust: A Framework for AI-Augmented Real Estate Valuation in the Era of Structured Data](https://mlsanity.com/paper/2508.02765/) (2025)
- [DynBranch: Speculative Subgraph Reuse for Dynamic Agentic LLM Serving](https://mlsanity.com/paper/2609.31047/) (2026)

## Abstract (arXiv)

Compound AI applications chain together subcomponents such as generative language models, document retrievers, and embedding models. Applying traditional systems optimizations such as parallelism and pipelining in compound AI systems is difficult because each component has different constraints in terms of the granularity and type of data that it ingests. New data is often generated during intermediate computations, and text streams may be split into smaller, independent fragments (such as documents to sentences) which may then be re-aggregated at later parts of the computation. Due to this complexity, existing systems to serve compound AI queries do not fully take advantage of parallelism and pipelining opportunities. We present Alto, a framework that automatically optimizes execution of compound AI queries through streaming and parallelism. Bento introduces a new abstraction called nested ancestry, a metadata hierarchy that allows the system to correctly track partial outputs and aggregate data across the heterogeneous constraints of the components of compound AI applications. This metadata is automatically inferred from the programming model, allowing developers to express complex dataflow patterns without needing to reason manually about the details of routing and aggregation. Implementations of four applications in Alto outperform or match implementations in LangGraph, a popular existing AI programming framework. Alto implementations match or improve latency by between 10-30%.