[2607.27283] Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Computer Science > Machine Learning

arXiv:2607.27283 (cs)

[Submitted on 29 Jul 2026]

Title:Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance

Authors:Chao Peng, Zhiheng Lyu, Peijie Dong, Hande Dong, Qiang Lin<br>View a PDF of the paper titled Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance, by Chao Peng and 4 other authors

View PDF<br>HTML (experimental)

Abstract:Long-horizon benchmarks often show that agents fail more as tasks become longer. This observation is useful for deployment, but it does not by itself explain why failure occurs. More stages create more opportunities for ordinary errors to compound; longer tasks may also contain harder individual decisions or become harder as conversation history, tool outputs, and environment changes accumulate. We use trajectory-induced degradation to mean this last possibility: earlier execution makes later work harder. When the harmful accumulation is specifically the text visible to the model, it is often called context rot. In this position paper, we argue that to claim a "long-horizon failure", benchmarks must compare actual full-task success against a baseline prediction built from short, individual stages. We call the log-ratio between this prediction and actual success the horizon residual. The comparison must use the same agent configuration and specify in advance how stages, checkpoints, information, and budgets will be chosen. The residual shows that the full rollout differs from the chosen baseline; targeted experiments are still needed to explain why.

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Software Engineering (cs.SE)

Cite as:<br>arXiv:2607.27283 [cs.LG]

(or<br>arXiv:2607.27283v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2607.27283

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Chao Peng [view email]<br>[v1]<br>Wed, 29 Jul 2026 13:57:32 UTC (1,005 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance, by Chao Peng and 4 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.LG

next >

new<br>recent<br>| 2026-07

Change to browse by:

cs<br>cs.AI<br>cs.SE

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

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<br>(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? |<br>Disable MathJax (What is MathJax?)

Major funding support from