Skip to content
AI News HubLIVE
Original source2 min read

DeltaHarness: Self-Evolving Harnesses for Resource-Adaptive Tool Execution

Summary

DeltaHarness is an execution-guided policy-search method that adapts agent harnesses from cold-start measurements, using a QHI loop to update runtime dispatch and revise plans, significantly reducing latency in tasks like video editing.

SourcearXiv Machine LearningAuthor: Lecheng Yan, Jianze Lin, Xicheng Han, Xiantao Xu, Wenxi Li, Chenyang Lyu
DeltaHarness: Self-Evolving Harnesses for Resource-Adaptive Tool Execution
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 16 Nov 2026]

Title:DeltaHarness: Self-Evolving Harnesses for Resource-Adaptive Tool Execution

View a PDF of the paper titled DeltaHarness: Self-Evolving Harnesses for Resource-Adaptive Tool Execution, by Lecheng Yan and 5 other authors

View PDF HTML (experimental)

Abstract:Tool-using agents rely on execution harnesses to organize and schedule tool operations. The same task and resource description can conceal runtime conditions that reverse the latency ordering of valid execution plans. Resolving this uncertainty requires firsthand execution in the target setting. We introduce DeltaHarness, an execution-guided policy-search method that adapts agent harnesses from cold-start measurements. Its QHI loop uses the observed response to update runtime dispatch, revise physical plans, and select experiments for later proposals. An independent confirmation panel controls policy replacement. With fixed dispatch, a revised materialization policy reduces complete-delivery latency by 30.0% on one video-editing task across three fresh pairs. On held-out tasks, the evolved policies reduce latency by 8.2% relative to the best fixed plan in one seed and by 4.6% relative to the initial proposal in another.

Comments: preprint

Subjects:

Machine Learning (cs.LG); Performance (cs.PF)

Cite as: arXiv:2611.21688 [cs.LG]

(or arXiv:2611.21688v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2611.21688

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Lecheng Yan [view email] [v1] Mon, 16 Nov 2026 06:17:34 UTC (652 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled DeltaHarness: Self-Evolving Harnesses for Resource-Adaptive Tool Execution, by Lecheng Yan and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.LG

new | recent | 2026-11

Change to browse by:

cs cs.PF

References & Citations

SciX

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?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

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?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Introduces DeltaHarness, an execution-guided policy-search method that adapts agent harnesses from cold-start measurements.
  • The QHI loop uses observed responses to update runtime dispatch, revise physical plans, and select experiments.
  • A revised materialization policy reduces complete-delivery latency by 30.0% on a video-editing task.
  • On held-out tasks, evolved policies reduce latency by 8.2% relative to the best fixed plan and by 4.6% relative to the initial proposal.

Highlights and analysis are generated automatically and may contain errors. Check the original source.