Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows
Bardia Mohammadi, Nearchos Potamitis, Lars Klein, Akhil Arora, Laurent Bindschaedler

TL;DR
Atomix is a runtime system that ensures safe, reliable execution of external tool calls by providing transactional semantics, tracking progress, and enabling safe retries and compensation during failures or contention.
Contribution
It introduces a novel progress-aware transactional framework for LLM agent tool use, improving reliability and isolation in external system interactions.
Findings
Transactional retry increases task success rates.
Frontier-gated commit enhances isolation under contention.
Bufferable effects can be delayed for safety.
Abstract
LLM agents increasingly act on external systems, yet tool effects are immediate. Under failures, speculation, or contention, losing branches can leak unintended side effects with no safe rollback. We introduce Atomix, a runtime that provides progress-aware transactional semantics for agent tool calls. Atomix tags each call with an epoch, tracks per-resource frontiers, and commits only when progress predicates indicate safety; bufferable effects can be delayed, while externalized effects are tracked and compensated on abort. Across real workloads with fault injection, transactional retry improves task success, while frontier-gated commit strengthens isolation under speculation and contention.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMulti-Agent Systems and Negotiation · Distributed systems and fault tolerance · Mobile Agent-Based Network Management
