Web This site Trusted
30 result(s) for “okapi bm25 site www eyespy cy site www maxikit com site bank data com site www site:arxiv.org” of 236 matched · 570 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
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/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/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
IR)
LLM-based agents are increasingly being deployed for data-related tasks, including data sense-making, exploration, and retrieval
https://arxiv.org/list/cs.IR/new
Code and data are available at this https URL
https://arxiv.org/abs/2608.03883
Because no annotated training data were released for this first edition of the task, we relied on zero-shot experimentation, manual validation, and unsupervised or weakly guided retrieval pipelines
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/html/2407.16741v3
com/All-Hands-AI/OpenHands
Slack http://bit
https://arxiv.org/list/cs.CY/current
Supplementary methods, coding manual, and data workbook included as ancillary files
Subjects: Computers and Society (cs
https://arxiv.org/abs/2510.01395
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy
https://arxiv.org/abs/2607.29380
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy
https://arxiv.org/abs/1411.2842
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy
https://arxiv.org/src/2006.02318
] f\QnL#"x,g M )2@|sD}_ &2Ej\l 5GW0 ozƃe,nܘcY
https://arxiv.org/list/cs.SI/new
We test our data on five real-world and one synthetically simulated dataset using both engineered and automatically generated features
https://arxiv.org/src/2006.03178
jVY ; kEaޱGɴ;JjbLњ:G zfCy =͞P
https://arxiv.org/list/econ.GN/recent
Monash Business School, Monash University, (4) Department of International Development, London School of Economics and Political Science, (5) Social Data Science and AI Lab, LMU Munich)
Comments: 171 pages, 42 figures, and 76 tables, including appendices
Subjects: General Economics (econ
https://arxiv.org/pdf/2608.02833
KZ Ms^7\NaϹ}\vh=ǫ fCyTLz4o ^zY~@u} 7زc|| JZ+q5wW+ {r:=ai+tYqy Wpxތ|+ZrZq=Wpx+Ȼ_Mv-t Ln*_u:}%v,]qɶ3PWJ_wCoWpy~
https://arxiv.org/pdf/2609.03103
U=d dY *˖ gYʤ%x(י천K MdWG{N g)\#t8JI )q *)_5 'GAF yb@~gfO/_ѸDZl^,S^1(n,0jo' qnEPU, ytq;|))sU2m 8QҐ젬VdUݗCy,ONwy%s6)o)KJ D~n
https://arxiv.org/pdf/2607.26327v3
zcYF-k &XK M^jqXJ ^Z0k lvTJ >K6hz2*免Pu_w/'O uUvqpaR
https://arxiv.org/pdf/2407.02402
߯jD岻fc;Z̫MfG} q]/ޭmޯo⣩0Z^x]fkn{E+{*ʧypg6;5PVpH8$hmڢ*߄zR:")3qXysO'H)-"}[˺s 3 4{pYdrK+ a }ѫW{ Fvm7344AGc
https://arxiv.org/pdf/2407.00345
+; j m (ȣ;%^BEkOHxwE Dg,]WQmP κcy:0YdCoB`Yt˨sH O$##Д0Id)o 9HLDznMܗ "UZiOMgF :8 LZA lXN$C g
https://arxiv.org/src/2002.02145
SiGnf YA9Ki©qdXDE9Yv GMVz%VfSR9KdڝH aO8Sy%!(k7 OJC>d k$~,H8PK@-J&ˁ~p=Cm>EuR)̟-'_;o?Rsymr/
https://arxiv.org/html/2608.02966v1
Data Efficient LLM Benchmarking
Compression of MCQ Benchmarks
https://arxiv.org/pdf/2608.02609
,6 JtLʒ 5&(B1@ !H"P(g(A G(E,N .H?0E);H)\9X0\CSp & _ l$O" )\$R|R7 QlpNSDlF (A,G~oJh4l,N7݇ dF 'a8LZC1E ޚ/$:x a
https://arxiv.org/pdf/2608.01366
f-__RHrK6&9{I}5(PF XHerʃU^#QiϠ4 ?F"V{**=:اwT)c2X6RfT2l F1Ǡ`D6FRDe8) ˌ٩"c7hR}fDØ;0h1&%(4!打phept )"Wp-+Uň&UM
https://arxiv.org/pdf/2104.00446
vA5PCaۗ}/>-_q'RUϮr`,Y;.Y%>.YQ0d>͉[jpSӋay1RgtrTptC+jZ9DL SqR3Ml@dP }Сە۩d549:6 ּ MtT0Ǯەܦ Z5 A eRfX L}cVũj3۩c ꢛ
https://arxiv.org/pdf/2508.02686
^NHy^ N/Lh2^ 2Lݙ2 :qZlcY ;=S^;O