# Orla: A Library for Serving LLM-Based Multi-Agent Systems

arXiv: https://arxiv.org/abs/2603.13605 · HTML: https://mlsanity.com/paper/2603.13605/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 13 Mar 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 9 of 9)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?](https://mlsanity.com/paper/2511.13646/) (2025)
- [Don't Stop Me Now: Embedding Based Scheduling for LLMs](https://mlsanity.com/paper/2410.01035/) (2024)
- [ThunderAgent: A Simple, Fast and Program-Aware Agentic Inference System](https://mlsanity.com/paper/2602.13692/) (2026)

## Built on by (most cited first, 2 of 2)

- [Serving Agentic Workflows with a Physical-Plan Compiler and Adaptive Runtime](https://mlsanity.com/paper/2607.02942/) (2026)
- [OpenClaw and Ollama in Agentic AI: Toward Fully Autonomous and Scalable AI Agent Systems](https://mlsanity.com/paper/2607.28629/) (2026)

## Abstract (arXiv)

We introduce Orla, a library for constructing and running LLM-based agentic systems. Modern agentic applications consist of workflows that combine multiple LLM inference steps, tool calls, and heterogeneous infrastructure. Today, developers typically build these systems by manually composing orchestration code with LLM serving engines and tool execution logic. Orla provides a general abstraction that separates request execution from workflow-level policy. It acts as a serving layer above existing LLM inference engines: developers define workflows composed of stages, while Orla manages how those stages are mapped, executed, and coordinated across models and backends. It provides agent-level control through three mechanisms: a stage mapper, which assigns each stage to an appropriate model and backend; a workflow orchestrator, which schedules stages and manages their resources and context; and a memory manager, which manages inference state such as the KV cache across workflow boundaries. We demonstrate Orla with a customer support workflow that exercises many of its capabilities. We evaluate Orla on two datasets, showing that stage mapping improves latency and cost compared to a single-model vLLM baseline, while workflow-level cache management reduces time-to-first-token.