[2608.18931] Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Computer Science > Computation and Language

arXiv:2608.18931 (cs)

[Submitted on 19 Aug 2026]

Title:Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck

Authors:Davide Romano, Kanak Raj, Jerrod Parker, Daniele Giofrè<br>View a PDF of the paper titled Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck, by Davide Romano and 3 other authors

View PDF<br>HTML (experimental)

Abstract:Test-time scaling (TTS) improves language model outputs by spending additional inference compute - generating multiple candidates, searching over partial sequences, or iteratively refining drafts. These techniques yield large gains on mathematics and code, but have been developed and stress-tested almost exclusively on tasks where verification is straightforward. We conduct the first compute-normalised comparison of five TTS families across five open-ended generation benchmarks spanning medicine, law, finance, general chat, and creative writing - grounded in a unified framework that decomposes the effectiveness of each method's token budget into exploration and exploitation. The answer depends on which side of that decomposition you examine. Scaling exploration works: the best candidate in the pool improves steadily with compute across all settings. What breaks is exploitation - the step that converts a rich candidate pool into a final output. With state-of-the-art generators, reward models correlate at only $\rho_v \approx 0.12$ with true quality, rendering selection near-random regardless of budget. Tree search amplifies this failure through diversity collapse. Refinement helps on one of five benchmarks; its apparent gains elsewhere are confounded. Only synthesis across candidates (Fusion) consistently improves over single-sample baselines, yet still recovers only ~40% of available quality. The candidate pool is not the bottleneck - choosing from it is.

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

Cite as:<br>arXiv:2608.18931 [cs.CL]

(or<br>arXiv:2608.18931v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2608.18931

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Daniele Giofré [view email]<br>[v1]<br>Wed, 19 Aug 2026 13:59:53 UTC (4,865 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck, by Davide Romano and 3 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.CL

next >

new<br>recent<br>| 2026-08

Change to browse by:

cs<br>cs.AI

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?)

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