[Submitted on 22 Sep 2026]
Title:TomasuLLM: Out-of-Order Speculative Execution for LLM Agents
View a PDF of the paper titled TomasuLLM: Out-of-Order Speculative Execution for LLM Agents, by Jiangnan Yu and 8 other authors
View PDF HTML (experimental)
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.
Subjects:
Computation and Language (cs.CL); Operating Systems (cs.OS); Software Engineering (cs.SE)
Cite as: arXiv:2609.38201 [cs.CL]
(or arXiv:2609.38201v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.38201
arXiv-issued DOI via DataCite
Submission history
From: Jiangnan Yu [view email] [v1] Tue, 22 Sep 2026 03:41:35 UTC (3,755 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled TomasuLLM: Out-of-Order Speculative Execution for LLM Agents, by Jiangnan Yu and 8 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-09
Change to browse by:
cs cs.OS cs.SE
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)