Web This site Trusted
30 result(s) for “okapi bm25 site terms com pp site github com site it apache org site doa ja site:arxiv.org” of 32 matched · 1052 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: newest result fetched 25 d ago · median age of these results 25 d · 1 of 30 carry a fetch time
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
https://arxiv.org/html/2608.02613v1
Instead, it falls on local, personal agents to effectively and safely maintain/utilize such dense person-person (PP) and person-agent (PA) interaction histories
https://arxiv.org/src/2405.20232
(T$,J I>̙i9ɹ(Yd }6%! ?= `?9 tpr Z[~=(Jqp*U[ -ߴb9 6K}ڍ'wQˀqA ˦?5 JD/^Dͤȑ{V0z~w
https://arxiv.org/src/2006.03720
ePfd,7Kd@ndE?M\{Sjn@Zh&i&!qPgu/T2ȁZ~HnUeLo:]&||zxVԼHdC hM)1ITLHѧD:x_}hpMt za" U:۷ ӘzC)z:bB uo(zq D*
https://arxiv.org/pdf/2006.02833
ŧ^așQᛀp G1'g =|@Ҋ_t_iendstream endobj 208 0 obj > stream xڍYKܶW%U* Do eǶ؎㍜, _~Weh FayWoNkU$Pi˒Biv ﻟ~>iPCy(u%L7 뇛ۿ],R8v9>$IPu^vQӘ6wL:vm5 [a7o^l[pp~3Om{T,07N
https://arxiv.org/src/2402.03300
5JYot" ~IEBF7 ObKޙ˛Дԛe_jo0_-# ԻFE#s#+ ;Swja氽wX۔2w=˗
https://arxiv.org/pdf/2303.12712v5
z$gsh)_:^XGCyrG4NǦpP%ŪB nk 5(zӸ%TQx[^Nwi o[HaWcv};F ~
https://arxiv.org/pdf/2608.02851v1
%6G"8/1tx493C`LԒ)c9S18YecܨՌ;4LCς eQ0F3pLVVһL -ѳc8zt4h(SdSLՂ5\ҳaZ*LkC|r*1)3I83Ҥ) hL1F2aYebt,qU1+(nřG.|-;tϾvcynЏ
https://arxiv.org/src/2006.02924
`ĂATT,=en{/ϣ$3=o/Z ΈS2O.9/q5SV:YtՙGYGw.̨Q:p8ZsOQ@jSjX] 2]5Bј5!SeFȇi>͌Ux%bD˂n誦5 j4k UIR=C^$ .U ̀CC>cj(tOʰ
https://arxiv.org/src/2006.01318
]æґcbnJВ5h~QSvF UJAVϫ*( 1M,#ؑE#ϩJ0GaS^ƃ- x I>0CHGC;kNt[I;E|[y( [Ihwu@;l08QN͑Bo ,/kH& ]4pt76Єjq$@+1%kS
https://arxiv.org/html/2608.03048v1
com/JetAstra/PI-Mem
Introduction
The ability to reason over long contexts is increasingly important for large language models (LLMs), supporting applications such as long-document question answering (Gemini Team 2025; Yang et al
https://arxiv.org/html/2501.13956v1
com
Abstract
We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark
https://arxiv.org/html/2407.16741v3
com/All-Hands-AI/OpenHands
Slack http://bit
https://arxiv.org/list/cs.AI/new
Extending the pattern-generation paradigm of Neural Cellular Automata (NCA), it navigates the degenerate Boolean search space to satisfy a computational task, rather than regenerating a fixed target state
https://arxiv.org/pdf/2006.00441
Ծx-#=`7FX5|YOt% dM LD7#9ܔɸ2QpH ߐʩ8r0S ʙZqjx*%ňxkuB؎})vQME+ Owʂˈ6h it;|YMe\k#kqI%h[a [}:%tKTuN M:Fk]2vNZgRUr9v%0 l:
https://arxiv.org/pdf/1911.06462
yĻhR2aOЗkIH[jaҁgܤ U_P:x,F \{7q fldl|Co \M 4_ \0жHbՌ|* l( \wjnָ]9H[ٰWG7d:B(\vaXvXxVTCT Alm4Tg ~ʦ@لZiEG12ɨxWKl5:V%sk fR$BG@";lJݽ;/vԮ d0]⥚j;f{vZY"9͞cl)>w܁;
https://arxiv.org/pdf/2608.01651v1
`C BhgiیtV; ۳ѝ)(ZK7bA;E^]|sQ endstream endobj 316 0 obj > stream xmTn@Cx ^"#&W)R CfqTcfޛ|{NۻItճ;urnn: ];pvA= ]u7Ŧm;J۹v'k^Sn_ܯI
https://arxiv.org/pdf/2510.03215
Pp~NG\cqF*XȻI\%〫~h`kx6p3 g2(5Co(dr/ъӓ_눟k P}Ca @B
https://arxiv.org/pdf/2608.02976
}Ҥ婳g{4)4 V},H2֫Z B aa4ۮ_n5z dItϢ~ 7h*H0(hU6:͠;7+ v[:cHv1HT@j (*l}P3sPH"jb#l&
https://arxiv.org/pdf/2608.03437
obj > endobj 5 0 obj /Dest 2814 0 R>> endobj 6 0 obj > endobj 7 0 obj > endobj 8 0 obj > endobj 9 0 obj > endobj 10 0 obj > endobj 11 0 obj > endobj 12 0 obj > endobj 13 0 obj > endobj 14 0 obj > endobj 15 0 obj > endobj 16 0 obj > endobj
https://arxiv.org/pdf/2608.02615
B>,TGbPq> stream x[ێ7}W1 "0`;kH dmM[#D#i%9lOҨ'^ &dUX*u0B H/#$t"hƠ:*a ja֣>Za giŌg>Xʓ,VEh6RNs*w 0'*ZƐ 6 L2 o
https://arxiv.org/pdf/2608.03086
1>Ϗ&_ގhJa_lIhF]05JF(md` -*Pb4Wr~>8:|zׇuA%5ϵ ^jnTY4 eS*nls(nwwwNlۈ X,lbۍtZ0Y%k%nkݝIý ]k[Kפ]jx uJ}80]p>_@bY`DZǨbTN:Y
https://arxiv.org/pdf/2507.17609
כּfK#XRE>(Rcx%M%*T%+FY*EUWJWBT%VV0BWWJצ2,`fr>(pV8s $!X`$oQWLAb O Q0 (Wi@s%o`T\+j%+d%V Y%GH >bW~" հ (KIו5` vt
https://arxiv.org/list/cs.CL/new
With the interaction history, it co-generates ground truth over six recall, reasoning, and trustworthiness evaluation dimensions
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
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
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
https://arxiv.org/list/cs.IR/recent
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
Information Retrieval
Authors and titles for recent submissions
Wed, 5 Aug 2026
https://arxiv.org/list/cs.IR/new
To handle it, KGD assigns them to separate parameter sets: a refreshable encoder owns behavioral knowledge, while a task learner reads contextualized encoder states through read-only cross-attention and writes task-specific geometry through Anchored Calibration Residual (ACR) orthogonal to the pretrained embedding
https://arxiv.org/pdf/2006.00064
-8dmӣ :ypat}إIt +^a 6 8 =\ S+֓Y5Kvz# esşP^%oD=xjIE"b Xlu c/UqhwD~
https://arxiv.org/pdf/2604.05327v4
[5ݭ/@Qjz8 ~ 4L2/b\P3Lx,F1ǔYJ@rO(ұc \-OډBi`VSszm Tı>B}ו]GϗtXwݹnn *WπprV{9K.m OM/ 2мUm[0oNzEPtU/:67nWW] 0xu