NishiSearch

Web This site Trusted

30 result(s) for “okapi bm25 site hotchips pp site github com site text os dev site rate builder tls site:arxiv.org” of 37 matched · 910 ms

Scope: Nishi’s own index (our crawl + Common Crawl) — not the whole live web. Some sites block all automated crawlers (anti-bot walls), so their pages may be absent here even though we never filter lawful content.

Freshness: no result on this page carries a fetch time yet (indexed before the fetch epoch was stored beside the doc)

The query asks the model to recall the topic of an earlier conversation about Tesla; the gold answer is anchored in one specific session about Pooja’s dig site
from the top result below

Report GitHub Issue

https://arxiv.org/html/2608.02613v1
1K text-only ego-observed tokens/agent/day)

Artificial Intelligence

https://arxiv.org/list/cs.AI/new
Skip to main content System maintenance August 4th and 5th Learn more × Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Artificial Intelligence New submissions Cross-lists Replacements See recent

Report GitHub Issue

https://arxiv.org/html/2608.03048v1
com/JetAstra/PI-Mem Introduction The ability to reason over long contexts is increasingly important for large language models (LLMs), supporting applications such as long-document question answering (Gemini Team 2025; Yang et al

1 Introduction

https://arxiv.org/html/2407.16741v3
com/All-Hands-AI/OpenHands Slack http://bit

Computation and Language

https://arxiv.org/list/cs.CL/new
1K text-only ego-observed tokens/agent/day)

%PDF-1.7 % 1 0 obj > stream x}Mo0 H =΃ 8(

https://arxiv.org/pdf/2608.04008
6>Ȍ6=RBmLLXƇM_|VNe]V[Rª{‚5X68$T`="03[R/u C*JsI)u8WqMI|WG0hZ5+ާl* pair 3z } Bx׏J ߣۡjy ŃE"eSPL0}O;ﮍk;_E滳6")sr\#UxtQ 2~'wgrxW]pp*c )>VNbQW'Z]

%PDF-1.5 % 2 0 obj > stream xmTˎ0+$$0  a#A%

https://arxiv.org/pdf/2407.02402
߯jD岻fc;Z̫MfG} q]/ޭmޯo⣩0Z^x]fkn{E+{*ʧypg6;5PVpH8$hmڢ*߄zR:")󨺠3qXysO'H)-"}[˺s 3 4{pYdrK+ a }ѫW{ Fvm7344AGc

w_z߯x;ã'x|p ãGsJĊ(2w[

https://arxiv.org/src/2006.02230
VJU7cϘ3D$^I 27O=`׆tJaFX H3uloSlBd7bisK`&

%PDF-1.5 % 1 0 obj > endobj 2 0 obj > endobj 3 0 obj > stream Large

https://arxiv.org/pdf/2407.00225
*kG endstream endobj 19 0 obj > stream x f endstream endobj 20 0 obj > stream xE 1 Diă 7* IIADŽsu C+Ѥ NfWsc[‡ep6WWшL) Fh͆J*CGVǴM=& endstream endobj 21 0 obj > endobj 22 0 obj > /Pattern 62 0 R /ProcSet [ /PDF /Text ] >>

G%_\nɑ޿ ! Heg}pt6gd\CA^〻˓Uu

https://arxiv.org/src/2005.14165
B-jLFt\w"z_s7)ӯdcq94HB{D /}4Bpe82YGZ k/|oSxɚiP2Wb' >sۮ鵹^;-㎡u,%j=/l&`)BCy@Hw>pGdG;Y|)/c]}d QogJ

Pt^| o?px8:Fߓ)IĊ,2wStN}

https://arxiv.org/src/2006.02085
$ 7+4W "wLjun1"q ff׶01Zh/WIc-QhbI$#5DlUQJ@C$Xji5}T$cOsǠ7@` Vzjis "a'2ZӹY6(ԚzȲa(]ۊ

rj;srY9靟OO߰ޟ4'}Ʊڅ'o1d{l

https://arxiv.org/src/2608.03883
lއxG&JWXԴ&[v @V[uԇF7vz%N`pP \>$kb {K/05 U0[|ʋXcc S-bQEAE

%PDF-1.7 % 1 0 obj > stream xZYS9~_ݘ0*tUĄ#pc0c6Mz

https://arxiv.org/pdf/2608.03118
Zz|PG-T*1P8Yvk-'Nğ`PM$&] L'|*p7k7mE7nry09U=PP#'#ބv2Z$t;Ʀlr5

%PDF-1.5 % 91 0 obj > stream xڭ[YƑ~ׯG#) 6h$Hv4P݄h

https://arxiv.org/pdf/2006.01402
_8b/UYyWѻyn̳/?4oIܼvF7ina>M){WlY}]~pPdSvD?f[۸/,3OM% >N9.t ^hsuY}ǛVZ+*5ڰ2b.mZ6M{@|Pܠ;Y>i?

4^h?Gsz:S;:d|2ǣOÓOR%['

https://arxiv.org/src/2006.00508
6t[Þ9{ʞ{Wwb {ޱ #;X/ŭIf30q6g d]3,dE=YRvVl>H:OAibvĆlĎ٘Sv ;!"H )5Naxzj8џ74y jHx:_yf!~Noi2VoZ

%PDF-1.3 % 3 0 obj > stream x\[oƑ~_hPG;Xލ=Il

https://arxiv.org/pdf/2608.02666
'd$ WU)]Wu}~1JД&Y{S.i臿Exiy=U%]REYy[tE.zK]::(.Yy9_b޾\_odGva-KF){:^>^ou_^GmϟooޤS9TQNR2)ۢ\[NUtE:dM&UYb-@u%

%PDF-1.7 % 1 0 obj > stream x\[s۶~?t7ٳg'idI'

https://arxiv.org/pdf/2608.02935
0rFBLS^C#)^ku7qy dZ1% rF>2tK0(OB{յ;7]  GJӽpM Gpp-dR-|qd

%PDF-1.7 % 1 0 obj > stream x\rFr}WQ`IihʫRZ

https://arxiv.org/pdf/2608.03411
6applМe~-y2Gi&pf3KjGKe ,"&:w|ҶP"rfr\xqF=/ܖn*>]zJX-w_0}0(B5&2

1 Introduction

https://arxiv.org/html/2501.13956v1
com Abstract We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark

%PDF-1.7 % 1 0 obj > stream xMO@.$M1ZZ6

https://arxiv.org/pdf/2608.02942
+e,L}Ëuh{ǀHJ'>N>NA-z*ky nx ZZ{I3qF_z MJӠPp

%PDF-1.7 % 1 0 obj > stream xWMo7Wę'Hiд>(`I

https://arxiv.org/pdf/2310.19147
%;Cr. ^̛B)VE?cPN9kW@WQQ`/ fc(,g'r ='HVG/#("FdZ^Rd1*NIA',q:4E09,`[_:ިe,MtN+_KܐfDd(gO+?6g{='$D ࢌ َA,A&K%

Distributed Instruments for Planetary Surface Science: Scientific

https://arxiv.org/html/2407.01757v1
Opportunities and Technology Feasibility 1 Introduction 1.1 What is a distributed instrument? 1.1.1 Distributed Instruments and Sensor Networks 1.1.2 Distributed Instruments and Swarms 1.2 Contribution and Organization 2 State of the Art

%PDF-1.5 % 92 0 obj > stream xuTMo0 W6]n]P4S׃f+0Y

https://arxiv.org/pdf/2006.02602
^b⇷E(8A⚞X@D6hg7u[ -0L*:h$V pP/O퓩-~ɉMI5&Bd]$ԣv9d̾i@͝j0pX  "Ihg> stream xuvܸ_;ܚQ323~o4ADE

%PDF-1.7 % 1 0 obj > stream x}MO09|$M{Ux0bBW

https://arxiv.org/pdf/2608.01651v1
(1-Lc4OO2 `g$AA $3AfzxC  ANx4ƍov> endobj 10 0 obj > stream x[YSʺ}Bݕ-'IUNU0$@HBr>[ml˱Zn @Uq}% y s/!2ƽsk jaQ,dLKy0mU G]J_ΆKlFڡ

$][msFgZlWH);N[YRlDr;XD(=

https://arxiv.org/src/1911.06462
IەTݩT L XԷGzşs?=_?zp`hÇ_!9JWH+}ӟil2UY%ҹ_'xSI[(Qt*э\_Si:Dgo2*GQIw++^/ά7MWMջDLd&+\̖:ybVee 5ç٫-A#e^h 0y2

%PDF-1.5 % 106 0 obj > stream xڍ[K WU* G󡽍a

https://arxiv.org/pdf/2407.02510
JXH'>4EQM/j4~z}7O_}jv. ;i(Sq9C>Tmm ~.3Tеx(=)g;>7K}&4秿Ӑʼn|C[ռ? te^W+ $@GP&lmQvZz8%e^cŔ~O0N7uyZn Vz) "M!

trj; tU3rYd:t'1A$I~]N:e?

https://arxiv.org/src/2608.04009
-SV5S)I @ّH5g+_f/n dP = nX :(+osYeO+Lf[+Gyk9,4&H4KBBCp%\٬k8

%PDF-1.5 % 61 0 obj > /Filter /FlateDecode /Height 437 /Length 65550

https://arxiv.org/pdf/2006.04122
/Width 614 >> stream x XkǏ=D!D6"ZT$E%BEgQ)tJ{hU(J+!V) D~s)Ie_5ͼP( jBP(D& BPiӦAP( E# ȄBP(hDP( BP("BP(D& %%X B~; ߿[^

%PDF-1.7 % 1 0 obj > stream x[is۸~?Nޔ bRuV%v8N

https://arxiv.org/pdf/2608.02615
vsEqٱe%;rηب:ȫ ٘86爬`QlaNٲZD$٦:>4 9wd@o=v˾'6ݡ-A"cږ&-uұS]¶#r/ӎL9]i; '4ˡ uz6 i)[tC_'عvLۖO__97lU;{Oc1oS;9Ll3+^mhmBwֿcՌ:{]n'=n)"g(~l&Ճ>WL=͊/Km8z~

[2608.03883] DS@GT-ARC at eRisk 2026 Task 3: Sparse, Semantic, and LLM

https://arxiv.org/abs/2608.03883
Our systems combine sparse BM25 retrieval, evidence-aware rescoring for self-referential symptom reports, embedding-based reranking, query-prototype expansion, and LLM-based reranking