NishiSearch

Web This site Trusted

30 result(s) for “okapi bm25 site terms com pp site github com site led would site www exe fr site:arxiv.org” of 38 matched · 1017 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
We evaluate five open-weight readers with Vanilla context, BM25-RAG, Oracle retrieval, Memobase, and MemSearch as memory backends

%PDF-1.7 % 1 0 obj > stream xXKs7 W"dF4IS'^Ȗ*

https://arxiv.org/pdf/2608.02817
R7cRpJ } \v>pfv)Z+ȊPP%:3vⱂT3̙IjS L*Wo5#F5Ͻ `Ř,ϔ5SY V 3T4Vq ^6d菷q^EЭZ6#;mx_

w_z߯x;ã'x|p ãGsJĊ(2w[

https://arxiv.org/src/2006.02230
2+45(@;KQ&5HS+DD~:Q7X0]""n@h|P_a&%Bqr^݊'|V}W4 nGo>h(F?)SxCƗz^G_A +|CHurX$=ҜnR ߵ-TSZ^a } /_SS`]2f|m0Ui@S75Ј4

Zzc\msFguT$#oYo'sξ홮x Yb3

https://arxiv.org/src/2211.10435v1
HIķR&8ק_e]&K{n>{'~O޹s;O&'>Q>$Q.tzӺ}W;8Y]+s ߿߽~OǓO#qSoʺ|L C3fzf-|ȶ jZ|17vDٝ59@"0l3b0GYs 3 Wt ->

w{r_CpMԶ >ϱm۶m۶m۶m۶mߪ议;+2w3%`ll`

https://arxiv.org/src/2006.01128
hLkol 'VV=kdgcfc``becf`zYYE.Nvv{"ae"_YbŧǷ3憢65s6gd`E'jalO'jml"lbdgl hb`徹-݆{WH_ lы>$1NRS$|E Dǫ`ݨǴE(M5nWAEQ16Xfqm

rrjw\S?   ! fI{,D^^B 5@ $Jl

https://arxiv.org/src/2608.04008
4H"%`H $̉Sϼg^o5Grrk^{G}+B5/Gz_q%riJU8VvlEFaaQ?:)666¢#~qoy%p:|p򷨰Gbm8gȉ#'d`H芨#q낤ewyqBqu

%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}Qn0+Ǝ_ BR>NC,)$1}

https://arxiv.org/pdf/2607.27070v1
IRGsro>tJ~~z|AOρ{U+(>[c;JA[/0Ҁg^9xӁwVo9ѳICÁ`xG]򩾥WW6W'vѴ>/+ڀmƷޝE{11E-Lw6 ܿ]_qеDuykG $AbpPЍkZ_E8JVkj&}0*V: HH

n^}ٰ1FQ9nJU. M=$ssw#;qDĖ"K v

https://arxiv.org/src/2006.01318
ɵn"ubȮ/ fR ҃&Ҥ$ zq ĭI3zmtu`jWWV r ռ i%{(:ej/~$jz"a+#8櫈6cCR˔QM4PK$tU8 CO*A(Ihv-"Af

%PDF-1.7 % 1 0 obj > stream xZr6}߯ࣵXJV7dɊ$n做%

https://arxiv.org/pdf/2608.00426
gHÑ|v A**Gn>hఄ$OJ:#$]rd KeѵL!"p 8 H&+) ,)KAY++\Jt 0D `IwGHm4=pW&Z D>60!DJ W!HB K~OR"U y@4(RRRTm@O'h2C#AhC !TCp=5

drj[Fo=EqlDuWq'@H3FD$)KAy}}9UHj

https://arxiv.org/src/2608.04003
8vK0\If'Gz4Yd&҅ $×U[-Ǯqo{$*N /+$\5l]5Fa͉2w|: *Uڹ2t*~ =0oW-BH-VI*0+]F~Q'{ZCLqo0TCBW"[] [M}W̳(aˍr)ɀ0(Tۗ")A ]Hȳvt `OZrٴN4ɢ=4Q@OW}oLdFҎ ;Ou@gA3x[Ÿ06ΠuFR_&K~

^]7 ڟ tow$lLr0Ig]SSUNp

https://arxiv.org/src/2006.01598
IKֿlƮE)Q_~oFK)?忇?moO瘓vd~ÿyg^E}7~~?/˯~?篜?޼髿t1p?>w  w߽?

c;^y٘ҏgG|~?z~ϓFD9zfd_໯

https://arxiv.org/src/2006.02055
3BȤ/;?$eR B&OȤ2B&埐OȤ2AFMz?_u5%D2?Hw/t!w~?Kf_ozP ?0{d,TNuoMjFg}#+ $;" s!誓 >ƃ^[zA ho¤UQ؀ދ+(TlXoZ

Pt^| o?px8:Fߓ)IĊ,2wStN}

https://arxiv.org/src/2006.02085
r٥]+ZWǧ'-tf|| ޻zmE{:o=Wl.o;0?SƑb EP yojz0H'OJ Dv]+i@ WOÏeV^1AggNnυO| îdΒ`$rC

Z:0f\r8nٙ9kNvn\l'?b+dL'1I0$(KѮD

https://arxiv.org/src/2402.03300
٭JUh4 '~-g7|_{^N^ ?y&iJW>/>P8a&e++FWrAwK8'JW"ɠ`'|%-[Ԉ^A)giz6aogYl'dȓ-ҠkXzb MK];VFĂO545kTy

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

https://arxiv.org/pdf/2508.16279
AgentScope 1.0: A Developer-Centric Framework for Building Agentic ApplicationsDawei GaoZitao LiYuexiang XieWeirui KuangLiuyi YaoBingchen QianZhijian MaYue CuiHaohao LuoShen LiLu YiYi YuShiqi HeZhiling LuoWenmeng ZhouZhicheng ZhangXuguang

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/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

1 Introduction

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

Report GitHub Issue

https://arxiv.org/html/2607.22511v2
The source code, formal library, and run records are available at https://github

%PDF-1.7 % 1 0 obj > stream xo@ﯘws IDlD{XV

https://arxiv.org/pdf/2608.03014
o*6erfR0 80b`m pqMpFqAp7F`qqw$:4`Dq-ˏSW x"Q FP{ˎ@qӢ~=MuĿۭQ}p,XHpCfS[ nmȋs8C(q8'Y]T{g[ bCl

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

%PDF-1.5 % 7 0 obj > stream xP(endstream endobj 9 0 obj >

https://arxiv.org/pdf/2407.17789
ȇ)d`$gៀAHP; s=1PhpPe0f(h,@F%;

%PDF-1.5 % 157 0 obj > stream xڍ[[F~-LQU\y=w;

https://arxiv.org/pdf/2006.00064
0@~' QCT*CPskj_ppej

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

https://arxiv.org/pdf/2002.02145
߯jD岻fc;Z̫MfG} q]/ޭmޯo⣩0Z^x]fkn{E+{*ʧypg6;5PVpH8$hmڢ*߄zR:")󨺠3qXysO'H)-"}[˺s 3 4{pYdrK+ a }ѫW{ Fvm7344AGc

%PDF-1.5 % 7 0 obj > stream xP(endstream endobj 9 0 obj >

https://arxiv.org/pdf/2407.00215
stream xP(endstream endobj 11 0 obj > stream xP(endstream endobj 17 0 obj > stream xP(endstream endobj 20 0 obj > stream xP(endstream endobj 23 0 obj > stream xP(endstream endobj

Computation and Language

https://arxiv.org/list/cs.CL/new
We evaluate five open-weight readers with Vanilla context, BM25-RAG, Oracle retrieval, Memobase, and MemSearch as memory backends

[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

[2104.08663] BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of

https://arxiv.org/abs/2104.08663
Our results show BM25 is a robust baseline and re-ranking and late-interaction-based models on average achieve the best zero-shot performances, however, at high computational costs

[2608.03860] SciRet: A Compute-Aware Empirical Study of Retrieval and

https://arxiv.org/abs/2608.03860
The pipeline combines sentence-window chunking, BM25, BGE-M3 dense retrieval, reciprocal rank fusion, optional cross-encoder reranking, and grounded answer generation