Web This site Trusted
30 result(s) for “okapi bm25 site hotchips pp site github com site text org de site 511 org site:arxiv.org” of 68 matched · 950 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 24 d ago · median age of these results 24 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
1K text-only ego-observed tokens/agent/day)
https://arxiv.org/pdf/2407.00125
3/ Trapped Text internal Indication if the document has been modified to include trapping information XMP Media Management Schema xmpMM http://ns
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/pdf/2407.00225
*kG endstream endobj 19 0 obj > stream x f endstream endobj 20 0 obj > stream xE 1 Diă 7* IIADsu C+Ѥ NfWsc[ep6WWшL) Fh͆J*CG VǴM=& endstream endobj 21 0 obj > endobj 22 0 obj > /Pattern 62 0 R /ProcSet [ /PDF /Text ] >>
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/html/2608.03233v1
org perpetual non-exclusive license
arXiv:2608
https://arxiv.org/pdf/2508.11152
3/ Trapped Text internal Indication if the document has been modified to include trapping information XMP Media Management Schema xmpMM http://ns
https://arxiv.org/pdf/2608.02851v1
b CP/SkWa CpؕaXl9L_g4Ʋ t zgfkde}BlѕuA&TNUJ*ԺRJՕ3V s P /]x^F
https://arxiv.org/pdf/2508.02691
WǴM=} s(> endstream endobj 24 0 obj > endobj 25 0 obj > /ProcSet [ /PDF /Text ] >> endobj 26 0 obj > endobj 27 0 obj > endobj 28 0 obj > endobj 29 0 obj endobj 30 0 obj > endobj 31 0 obj > endobj 32 0 obj > endobj 33 0 obj > endobj 34 0 obj > endobj 35 0 obj > endobj 36 0 obj > endobj 37 0 obj > endobj 38 0 obj >
https://arxiv.org/pdf/2508.07408
1>,ԂӯGX[ vo)(0 endstream endobj 28 0 obj > /Pattern 66 0 R /ProcSet [ /PDF /Text ] >> endobj 29 0 obj > endobj 30 0 obj > endobj 31 0 obj > endobj 32 0 obj > endobj 33 0 obj > endobj 34 0 obj > endobj 35 0 obj > endobj 36 0 obj > endobj 37 0 obj > endobj 38 0 obj > endobj 39 0 obj > endobj 40 0
https://arxiv.org/pdf/2608.03095
֒W[Gta!q$| I P`$ : ^, k*̾(J[EN_a]߯lE1_0wlõ8p vz3lwQGYcCtߧI'%O |{ @DYo肋`%E\ z\A@ݼOҡu;>ϾVl`WI|gˋuW֒sbc " $SdβaY
https://arxiv.org/html/2501.13956v1
com
Abstract
We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark
https://arxiv.org/html/2608.03077v1
org perpetual non-exclusive license
arXiv:2608
https://arxiv.org/pdf/1911.06462
&kCixu(;xDe lZd
https://arxiv.org/pdf/2309.08431
тppJCyS N*ɸkg
https://arxiv.org/pdf/2608.03437
obj > endobj 5 0 obj /Dest 2814 0 R>> endobj 6 0 obj > endobj 7 0 obj > endobj 8 0 obj > endobj 9 0 obj > endobj 10 0 obj > endobj 11 0 obj > endobj 12 0 obj > endobj 13 0 obj > endobj 14 0 obj > endobj 15 0 obj > endobj 16 0 obj > endobj
https://arxiv.org/html/2407.16741v3
com/All-Hands-AI/OpenHands
Slack http://bit
https://arxiv.org/list/cs.CL/new
1K text-only ego-observed tokens/agent/day)
https://arxiv.org/pdf/2006.15704
(Stm"Y*s D- FՈKQ|p#UA8ԧ:vדS| AmEܖD BVDuQ> /Font > /ProcSet [ /PDF /Text ] >> >> stream xVKo0 W iI@Q`u: A;6Qh)qf`Yȏ~x
https://arxiv.org/pdf/2006.02759
37&p VPx+@2;8tEjL~IEaGU:SAƑO|T*8 D1XD[v DE]Sx7[V =-a}>x#7Ki~+ ;W P e- smo+xE~W8
https://arxiv.org/pdf/1802.07228
0000016651 00000 n 0000016817 00000 n 0000018950 00000 n 0000019067 00000 n 0000019192 00000 n 0000019395 00000 n 0000019510 00000 n 0000020692 00000 n 0000020873 00000 n 0000021345 00000 n 0000021891 00000 n 0000022501 00000 n 0000022626
https://arxiv.org/pdf/2101.00190
/XObject > >> >> stream x+TT(T0 B K33 3Tp> stream xw$U/aIWTDE3Q aq9g]̺ݼauװ-9vx| S'= @ @ @ @ @ @ @ @
https://arxiv.org/pdf/2508.04671
485 ] /Info 411 0 R /Root 187 0 R /Size 670 /Prev 2921183 /ID [] >> stream xcbdg`b`8 $;A. H0 > X`$$,@ P)$A@{A ayY@* $xM@ D(201* (1J cr]0 -Qb% 0T endstream endobj 187 0 obj >
https://arxiv.org/pdf/2608.02935
0 rFBLS^C#)^ku7qy dZ1% rF>2tK0(OB{յ;7] GJӽpM Gpp-dR-|qd
https://arxiv.org/pdf/2510.03215
Pp~NG\cqF*XȻI\%〫~h`kx6p3 g2(5Co(dr/ъӓ_눟k P}Ca @B
https://arxiv.org/pdf/2608.03063
ٔ@:^( 1t0xa2X̤6,aJ(2B#bZ 93Co4Xbb5KUĸ2F8$QV f#"R^ExWeU-5CHD P ;%2a xRU$Wqʤ B|u/ ' . 442N98QLI@G]# 2 8*"4TS9>+
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
We leverage a careful selection of 18 publicly available datasets from diverse text retrieval tasks and domains and evaluate 10 state-of-the-art retrieval systems including lexical, sparse, dense, late-interaction and re-ranking architectures on the BEIR benchmark
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/pdf/2407.02509
z`2 ,;7ڊm ʲê&DE rV;|5" "