%PDF-1.5
%
1 0 obj
<< /Metadata 3 0 R /Names 4 0 R /OpenAction 5 0 R /Outlines 6 0 R /PageMode /UseOutlines /Pages 7 0 R /Type /Catalog >>
endobj
2 0 obj
<< /Author (Vaishnavi Shrivastava; Ahmed Awadallah; Vidhisha Balachandran; Shivam Garg; Harkirat Behl; Dimitris Papailiopoulos) /Creator (arXiv GenPDF \(tex2pdf:\)) /DOI (https://doi.org/10.48550/arXiv.2508.09726) /License (http://creativecommons.org/licenses/by/4.0/) /PTEX.Fullbanner (This is pdfTeX, Version 3.141592653-2.6-1.40.25 \(TeX Live 2023\) kpathsea version 6.3.5) /Producer (pikepdf 8.15.1) /Title (Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning) /Trapped /False /arXivID (https://arxiv.org/abs/2508.09726v1) >>
endobj
3 0 obj
<< /Subtype /XML /Type /Metadata /Length 1774 >>
stream
Sample More to Think Less: Group Filtered Policy Optimization for Concise ReasoningVaishnavi ShrivastavaAhmed AwadallahVidhisha BalachandranShivam GargHarkirat BehlDimitris Papailiopouloshttp://creativecommons.org/licenses/by/4.0/cs.CLcs.LG
endstream
endobj
4 0 obj
<< /Dests 8 0 R >>
endobj
5 0 obj
<< /D [ 9 0 R /Fit ] /S /GoTo >>
endobj
6 0 obj
<< /Count 11 /First 10 0 R /Last 11 0 R /Type /Outlines >>
endobj
7 0 obj
<< /Count 29 /Kids [ 12 0 R 13 0 R 14 0 R 15 0 R 16 0 R ] /Type /Pages >>
endobj
8 0 obj
<< /Kids [ 17 0 R 18 0 R 19 0 R 20 0 R ] /Limits [ (Doc-Start) (table.caption.8) ] >>
endobj
9 0 obj
<< /Annots [ 21 0 R ] /Contents [ 22 0 R 23 0 R 24 0 R 25 0 R ] /Group 26 0 R /MediaBox [ 0 0 612 792 ] /Parent 12 0 R /Resources 27 0 R /Type /Page >>
endobj
10 0 obj
<< /A 28 0 R /Next 29 0 R /Parent 6 0 R /Title 30 0 R >>
endobj
11 0 obj
<< /A 31 0 R /Parent 6 0 R /Prev 32 0 R /Title 33 0 R >>
endobj
12 0 obj
<< /Count 6 /Kids [ 9 0 R 34 0 R 35 0 R 36 0 R 37 0 R 38 0 R ] /Parent 7 0 R /Type /Pages >>
endobj
13 0 obj
<< /Count 6 /Kids [ 39 0 R 40 0 R 41 0 R 42 0 R 43 0 R 44 0 R ] /Parent 7 0 R /Type /Pages >>
endobj
14 0 obj
<< /Count 6 /Kids [ 45 0 R 46 0 R 47 0 R 48 0 R 49 0 R 50 0 R ] /Parent 7 0 R /Type /Pages >>
endobj
15 0 obj
<< /Count 6 /Kids [ 51 0 R 52 0 R 53 0 R 54 0 R 55 0 R 56 0 R ] /Parent 7 0 R /Type /Pages >>
endobj
16 0 obj
<< /Count 5 /Kids [ 57 0 R 58 0 R 59 0 R 60 0 R 61 0 R ] /Parent 7 0 R /Type /Pages >>
endobj
17 0 obj
<< /Kids [ 62 0 R 63 0 R 64 0 R 65 0 R 66 0 R 67 0 R ] /Limits [ (Doc-Start) (cite.wilcoxon1992individual) ] >>
endobj
18 0 obj
<< /Kids [ 68 0 R 69 0 R 70 0 R 71 0 R 72 0 R 73 0 R ] /Limits [ (cite.xiang2025just) (page.10) ] >>
endobj
19 0 obj
<< /Kids [ 74 0 R 75 0 R 76 0 R 77 0 R 78 0 R 79 0 R ] /Limits [ (page.11) (section*.25) ] >>
endobj
20 0 obj
<< /Kids [ 80 0 R 81 0 R 82 0 R ] /Limits [ (section*.27) (table.caption.8) ] >>
endobj
21 0 obj
<< /A << /S /URI /URI (https://arxiv.org/abs/2508.09726v1) >> /BS << /W 0 >> /NM (fitz-L0) /Rect [ 12 220.46002 32 571.54 ] /Subtype /Link >>
endobj
22 0 obj
<< /Length 10 /Filter /FlateDecode >>
stream
x+ |
endstream
endobj
23 0 obj
<< /Filter /FlateDecode /Length 2493 >>
stream
xڝXKs8WtmU"R%3gⲓx'hbY (ԭ}TJ > nvpss?ܰ
M"Y &/e"NoI7lDoVKeACEJ_\m9jhPȏ/;24taO2L5NԺo+}LmRilێ&7V}ۘf3gAs&ƏD\2"l3?;4v՞=MR9VO'iO3Zn3;g>@pk29H8uoLfwǐ!]r3ŕH@hȸ+IÊ&(l)V