---
format: "aidr-story-markdown/v1"
id: "d55a4c113a242b65cda2a026b7a806bb10a8d15dae601e09fac6038edf835ee6"
canonical_url: "https://aidr.today/d55a4c11?lang=en"
title: "TomasuLLM: Out-of-Order Speculative Execution for LLM Agents"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-01T04:00:00.000Z"
category: "Research"
topics: ["agent"]
source_urls: ["https://arxiv.org/abs/2609.38201"]
summary: "arXiv:2609.38201v1 Announce Type: new Abstract: Long-running tools can dominate coding-agent latency: compilers, test suites, and repository commands take seconds to minutes while the agent idles. This observation stall presents the same tension that drove out-of-order processors -- asequential interface hides work that can be predicted and started early, but a speculative result may become visible only after it and every earlier step have been validated. We present TomasuLLM, a runtime that executes agent tool calls out of trajectory order while preserving task-execution correctness. It drafts future actions, runs them in isolated copy-on-write sandboxes, traces their dependencies and effects, and commits results in trajectory order only after validation against committed state. Across three benchmarks spanning sub-second to minutes-long tool calls, TomasuLLM improves the reported benchmark means and scales with tool latency: 1.31x on 100 SWE-bench Verified tasks, 1.35x on 28 Terminal-Bench 2.0 tasks, and 1.27x matched progress on 18 SWE-Marathon sessions. Across 4,010 audited commit-validation records, it produces zero false accepts."
---

# TomasuLLM: Out\-of\-Order Speculative Execution for LLM Agents

> [Open the canonical story](<https://aidr.today/d55a4c11?lang=en>)

**Published:** 2026-10-01T04:00:00.000Z
**Category:** Research
**Topics:** agent

## Summary

arXiv:2609\.38201v1 Announce Type: new Abstract: Long\-running tools can dominate coding\-agent latency: compilers, test suites, and repository commands take seconds to minutes while the agent idles\. This observation stall presents the same tension that drove out\-of\-order processors \-\- asequential interface hides work that can be predicted and started early, but a speculative result may become visible only after it and every earlier step have been validated\. We present TomasuLLM, a runtime that executes agent tool calls out of trajectory order while preserving task\-execution correctness\. It drafts future actions, runs them in isolated copy\-on\-write sandboxes, traces their dependencies and effects, and commits results in trajectory order only after validation against committed state\. Across three benchmarks spanning sub\-second to minutes\-long tool calls, TomasuLLM improves the reported benchmark means and scales with tool latency: 1\.31x on 100 SWE\-bench Verified tasks, 1\.35x on 28 Terminal\-Bench 2\.0 tasks, and 1\.27x matched progress on 18 SWE\-Marathon sessions\. Across 4,010 audited commit\-validation records, it produces zero false accepts\.

## Sources

- [Story source](<https://arxiv.org/abs/2609.38201>)