[Submitted on 6 Sep 2026]
Title:Prompt Breadth and Rollout Refresh Interact in On-Policy Distillation
View a PDF of the paper titled Prompt Breadth and Rollout Refresh Interact in On-Policy Distillation, by Lingxiang Hu and 4 other authors
View PDF HTML (experimental)
Abstract:How many prompts does on-policy distillation (OPD) need, and how does the answer depend on the student policies that generate its training responses? We study these two controls jointly: prompt breadth and rollout refresh. A 3x3 mathematical-reasoning experiment fixes 14,080 trajectories and 110 optimizer updates while varying the prompt bank and the number of response-generating policy snapshots. With ten snapshots, eight prompts reach 24.09% average accuracy, close to 24.51% for 14,080 distinct prompts. With responses frozen at the initial policy, however, increasing breadth lowers accuracy from 21.16% to 19.05%; under per-update refresh, it raises accuracy from 23.61% to 25.57%. The resulting interaction is 4.07 percentage points, with a 95% question-paired interval of [2.00, 6.28]. Matched comparisons under two teachers reveal a second reversal: the periodic models have higher short-budget accuracy and answer completion, but frozen-response models overtake in average accuracy at a 32K output limit, using 1.7-1.8x as many response tokens. These results show that prompt efficiency in OPD can depend on both refresh and inference budget.
Comments: 21 pages, 7 figures, 11 tables
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
ACM classes: I.2.6; I.2.7
Cite as: arXiv:2609.25048 [cs.CL]
(or arXiv:2609.25048v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.25048
arXiv-issued DOI via DataCite
Submission history
From: Lingxiang Hu [view email] [v1] Sun, 6 Sep 2026 06:54:24 UTC (225 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Prompt Breadth and Rollout Refresh Interact in On-Policy Distillation, by Lingxiang Hu and 4 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.AI
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?)