[2607.28576] Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Computer Science > Computation and Language

arXiv:2607.28576 (cs)

[Submitted on 30 Jul 2026]

Title:Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B

Authors:Iliya Mirzaei<br>View a PDF of the paper titled Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B, by Iliya Mirzaei

View PDF

Abstract:Methods that make a language model plan, criticise and rewrite its own answer, reflect on mistakes, pick the best of several attempts, or debate with copies of itself nearly all make it generate far more text than a single chain of thought. Because generating more text raises accuracy by itself, a gain over one chain of thought does not show the method's idea is what helped. Wang et al. (2024) reported that a simple baseline, sampling the same question repeatedly and keeping the most common answer, often wins once budgets are comparable, but gave point estimates with no confidence intervals or significance tests.

We rerun that comparison as a designed experiment: seven methods, open models of 1.5B, 3B and 7B parameters, two mathematics benchmarks, 150 questions each. We count every generated token, including those spent on critiques, reflections, debate turns and checking, and compare each method against repeated sampling at its own measured cost. All 36 comparisons are paired by question, with bootstrap intervals and multiplicity correction.

No method is reliably better than repeated sampling at equal cost anywhere. Ten are reliably worse, all of them methods where the model inspects its own output, and all 18 self-inspection comparisons are negative. The two kinds of self-inspection part company as models grow. Choosing stops hurting: taking Best-of-N's eight samples and just counting the most common answer beats letting the model pick by 8.0 and 11.3 points at 1.5B, but only 2.0 and 1.3 at 7B, no longer distinguishable from zero. Rewriting does not recover: Self-Refine and a forced Reflexion stay 3.6 to 10.1 points below baseline at 7B.

Reflexion as published never triggered its own retry on the smallest model. It judged itself correct every time and silently became a single chain of thought. We release code, prompts, all generations, and our verification scripts.

Subjects:

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

Cite as:<br>arXiv:2607.28576 [cs.CL]

(or<br>arXiv:2607.28576v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2607.28576

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Iliya Mirzaei [view email]<br>[v1]<br>Thu, 30 Jul 2026 17:38:23 UTC (37 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B, by Iliya Mirzaei<br>View PDF<br>TeX Source

view license

Current browse context:

cs.CL

next >

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

Change to browse by:

cs<br>cs.AI<br>cs.LG

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...