Web This site Trusted
30 result(s) for “okapi bm25 site www eyespy cy site so tech com site:arxiv.org” of 235 matched · 879 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)
1 Search
Zep implements three search functions: cosine semantic similarity search (φcos)subscript𝜑cos(\varphi_{\text{cos}})( italic_φ start_POSTSUBSCRIPT cos end_POSTSUBSCRIPT ), Okapi BM25 full-text search (φbm25)subscript𝜑bm25(\varphi_{\text{bm25}})( italic_φ start_POSTSUBSCRIPT bm25 end_POSTSUBSCRIPT )
from the top result below
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
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
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
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
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
https://arxiv.org/pdf/2006.02318
3/ pdfx PDF/X Schema external URL to an online version or preprint AuthoritativeDomain Text http://www
https://arxiv.org/pdf/2608.03883
3/ pdfx PDF/X Schema external URL to an online version or preprint AuthoritativeDomain Text http://www
https://arxiv.org/pdf/2407.00345
+; j m (ȣ;%^BEkOHxwE Dg,]WQmP κcy:0YdCoB`Yt˨sH O$##Д0Id)o 9HLDznMܗ "UZiOMgF :8 LZA lXN$C g
https://arxiv.org/pdf/2608.00151
R59Dɂ6, βYW*e"ڐRlF k l+|Z-[~Zзad}X\>]8nV HIКb7Eb8d%lV)Pf e Z6z ^wcoMzi& ^ $aZ nοYP$ joV5nYç@
https://arxiv.org/src/2205.11916v1
*HF]p\xNHX}|;{7.#DD dQ W= x oxԾm9Nv l l50_&Afpi(ik?}")e= ~ 35GHBFJa4OFJMhE!ob]L|,ږ' c+X.e""N vaqL4g E}ֶ f{oA0zJ*
https://arxiv.org/pdf/2109.12196
:;" `EXՁgS ` NsOĀ8hUC*Hn4%A*kKM tTȱŌASao* RN_E%'QFMolOJoOQ>UF$80
https://arxiv.org/src/2006.02318
Ux ݍ|t̹}Q OpXRWh\ YQI $_QqN:VpN&WU 9Nb;@0ЙcSot
https://arxiv.org/pdf/2104.00446
0p|xwA mb[Ŵ6ς5dVضbCwj_3O'dsSouApSRDJiACj Oo)LXP-hQ_QV
https://arxiv.org/pdf/2608.02764
RD"$U4\ ox_ݕ_BJSB6&so)=lv/|kI=0&RS
https://arxiv.org/src/2205.11916v3
&#rG"soV۱OBcvkz8-y_;r)>HuqSdm5-
https://arxiv.org/src/2006.01048
;Ӝ~]w "nz*]{CyG]+];+ _
https://arxiv.org/src/2608.03994
{Uulr8$IxYfgo ?={G 5s7BeV*q( >w/MW+ L'Z%؛Dri!dQ |3If:*dV $46p.iV,%L4!J?rvRg)ak{ORA^dˢf,e Y"}G:g>])9kf
https://arxiv.org/src/2211.10435
Com4 Ž(MW"_x ;;Bu85'UN;h&H0ԐP/^/3 KO`GC/ +ӄ3jGIt, ;]"}3ъ_w˓s&s]b%#-Ic:9Pb(RGl+̏GGK~XA/(ׅd CbBUCG8tY[|A]['ꍤQ[SSMl`/Jn'퉪 |;x V|߶;~0\h[z)G> ~X
https://arxiv.org/src/2006.02759
u4W sO__~ 1:zA 3zʗy8ȍaIeE*%(_A_ V|4v`Nf X$K[~%l{{+jFfiddB'y }jL7Fu֮y~6 g{ݟazy
https://arxiv.org/pdf/2608.02758
@۬MXT` )iI}= go)p 9I" "PZ AJBE&BZ@ae00)SV( )+ g H 0Jx cYfq;{~7zy:Zgޝi{c,c% Л*Ӂ`VNWwL/fW 2}(^tu0}efY ]3Co+iY/ڙg=nr\p֘EBp
https://arxiv.org/pdf/2608.03118
2$lx sofcNO"Փ$I" gNf$Po6~wWwiҒ^F "q;ۄ+O :aƼg&VfZG
https://arxiv.org/pdf/2303.12712v5
{-M1p^4hzإԻn5v{ R ']L4`G~w-e7pu):2SoO -9t2j ^0UlYOx }G0V60`;iL& 1 I}[Jn/ g o2,qPHËqoEgũcB:EraE J[xԆ6 k~#n s$Ƣ|dy
https://arxiv.org/pdf/2005.14165
{괙֭ƭ[ux~ t Y;i;w~~ \^^puWWW^__ ggg{/_;- 5S;wzrrAR
https://arxiv.org/pdf/2006.00342
` GGGP 8P4r w TVyzvw ܀' 0ar͛7iذԔ*P |MSO=%
https://arxiv.org/pdf/2402.03300
߯jD岻fc;Z̫MfG} q]/ޭmޯo⣩0Z^x]fkn{E+{*ʧypg6;5PVpH8$hmڢ*߄zR:")3qXysO'H)-"}[˺s 3 4{pYdrK+ a }ѫW{ Fvm7344AGc
https://arxiv.org/src/2303.12712
֜ h7XI @{=KL*1cSXBSj+6(Ja' 3:[e8# ozbJ§WLqcy\3r8Ȇ4J L2N$Brd9 >CPf6-k;N:
https://arxiv.org/pdf/2006.04122
/Width 614 >> stream x XkǏ=D!D6"ZT$E%BEgQ)tJ{hU(J+!V) D~s)Ie_5ͼ P( j BP(D& BP iӦAP( E# ȄBP(hDP( BP("BP(D& %%X B~; ߿[^
https://arxiv.org/pdf/2508.04671
6| mc }wU+%}OMx Mn~F2+OY&sOWw' 2NOBe/g
https://arxiv.org/pdf/2508.11152
com three Proceedings of ACM Conference (Conference'17) book 1 1 9 9 Tianjiao ZhaoJingrao LyuStokes JonesHarrison GarberStefano PasqualiDhagash Mehtahttp://arxiv
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