Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mohammadi, Bardia, Potamitis, Nearchos, Klein, Lars, Arora, Akhil, Bindschaedler, Laurent
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910272734625792
author Mohammadi, Bardia
Potamitis, Nearchos
Klein, Lars
Arora, Akhil
Bindschaedler, Laurent
author_facet Mohammadi, Bardia
Potamitis, Nearchos
Klein, Lars
Arora, Akhil
Bindschaedler, Laurent
contents LLM agents execute multi-step workflows that mutate external state through tools. Common orchestrators treat tool return as the settlement trigger, so faults, speculation, and concurrent agents can leave partial effects, losing-branch residue, stale writes, or irreversible sends. Correct settlement needs two facts that retries, checkpoint replay, locks, and compensation each conflate: which effects must settle together, and when earlier conflicting work is exhausted. Atomix makes this split explicit with progress-aware transactions. The runtime records reads and effects during execution, seals a transaction when its footprint is complete, and commits only after per-resource frontiers show that no earlier conflicting work can still arrive. Commit is final settlement: Atomix releases bufferable effects, accepts reversible external effects as final, and lets irreversible effects leave the gate. Abort suppresses unreleased effects and compensates externalized reversible effects where possible. On representative agent workloads, this composition improves clean recovery under injected faults, isolates contending and speculative work, and prevents correctly classified irreversible actions from leaking; microbenchmarks show microsecond-scale wrapper overhead relative to tool latency.
format Preprint
id arxiv_https___arxiv_org_abs_2602_14849
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows
Mohammadi, Bardia
Potamitis, Nearchos
Klein, Lars
Arora, Akhil
Bindschaedler, Laurent
Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Multiagent Systems
LLM agents execute multi-step workflows that mutate external state through tools. Common orchestrators treat tool return as the settlement trigger, so faults, speculation, and concurrent agents can leave partial effects, losing-branch residue, stale writes, or irreversible sends. Correct settlement needs two facts that retries, checkpoint replay, locks, and compensation each conflate: which effects must settle together, and when earlier conflicting work is exhausted. Atomix makes this split explicit with progress-aware transactions. The runtime records reads and effects during execution, seals a transaction when its footprint is complete, and commits only after per-resource frontiers show that no earlier conflicting work can still arrive. Commit is final settlement: Atomix releases bufferable effects, accepts reversible external effects as final, and lets irreversible effects leave the gate. Abort suppresses unreleased effects and compensates externalized reversible effects where possible. On representative agent workloads, this composition improves clean recovery under injected faults, isolates contending and speculative work, and prevents correctly classified irreversible actions from leaking; microbenchmarks show microsecond-scale wrapper overhead relative to tool latency.
title Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows
topic Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Multiagent Systems
url https://arxiv.org/abs/2602.14849