# Substrate-Portable Execution for Production LLM Workflows

arXiv: https://arxiv.org/abs/2609.06128 · HTML: https://mlsanity.com/paper/2609.06128/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 29 references that are in the map.
- First posted on arXiv 5 Sep 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, 10 of 10)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://mlsanity.com/paper/2406.11939/) (2024)
- [Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges](https://mlsanity.com/paper/2406.12624/) (2024)
- [PreAct: Prediction Enhances Agent's Planning Ability](https://mlsanity.com/paper/2402.11534/) (2024)

## Abstract (arXiv)

Production LLM agents execute tool-calling loops, retrieval chains, and compositional workflows in multiple modes, yet execution semantics are often coupled to one runtime. We encountered this portability problem in Rufus, a conversational AI assistant with a large tool catalog that serves millions of Amazon customers. Rufus supports real-time serving, asynchronous background tasks, and high-volume batch workloads such as evaluation and content pregeneration. Each mode has distinct service-level objectives and typically uses a separate runtime. Reusing streaming orchestration makes asynchronous and batch workloads blocking and prevents use of batch inference APIs, which offer a 50 percent discount at published prices. We present a binding-adaptive agent execution platform that separates workflow definition from execution substrate. Developers define a workflow once as a typed dataflow graph. The platform compiles the graph to in-process streaming for real-time serving, durable AWS SWF orchestration for asynchronous execution, or distributed Apache Flink stream processing for batch inference. No workflow code changes are required. LLM inference is represented as a suspendable graph node whose behavior depends on the substrate: streaming delivery online, durable retry asynchronously, and batched submission offline. We validated dozens of production agent configurations across five orchestration patterns: single-inference RAG, iterative ReAct, compositional PreAct, conditional routing, and multi-agent deep research. Across all three bindings, we found no detectable difference in output quality. Batch execution reduced per-query inference cost in line with published batch API pricing while operating alongside the streaming path at production scale.