Math 2.0

Resources / preprint

Curating Always-Loaded Context for LLM Agents: A Capacitated Assortment Model with Censored Feedback MF0H78XZXC

URIm2://res/MF0H78XZXC
Kindpreprint
CreatorsZexuan Liu, Yuning Yang, Tiancheng Zhao
Date2026-10-07
Subjectsarxiv cs.AI, arxiv cs.LG, arxiv math.OC
Scopeborder

Expressions

e1: version, preprint

Date2026-10-07
IdsarXiv 2610.11007

Items in this resource

The mentions of the inventory that name this resource. Each name links to the card of its inventory row.

ItemKindWhereSource
Load bound on optimastatementproposition A.5arxiv
Single deletionstatementlemma A.6arxiv
ETC-$m$ under an edit cap, full formstatementtheorem C.12arxiv
Accretion is unboundedly suboptimalstatementcorollary 1arxiv
76BHGENCV8statementtheoremarxiv
The edit-cap term is unavoidablestatementtheorem 3arxiv
File size bound under bounded-average compliancestatementproposition A.3arxiv
False inclusionstatementlemma C.8arxiv
ETC-$m$ under an edit capstatementtheorem 2arxiv
Binomial tailstatementlemma C.7arxiv
Tuned explorationstatementcorollary C.13arxiv
Batch errorsstatementlemma C.10arxiv
File size boundstatementproposition 1arxiv
What censored transcripts identifystatementtheorem C.5arxiv
Deleting on non-compliance is value-blindstatementproposition 3arxiv
Plug-in stabilitystatementlemma C.11arxiv
Without dilution, accretion is optimalstatementproposition 2arxiv
K7F7ZV0BNXstatementtheoremarxiv
Optimal files lie inside the accretion closurestatementproposition A.2arxiv
File size bound, full versionstatementproposition A.1arxiv
M77VE5NF0Cstatementtheoremarxiv
N0CD9ZZY10exampleexamplearxiv
Delaystatementlemma C.9arxiv
NETGJZSVBTstatementlemma A.4arxiv
Sharpened size boundstatementproposition A.7arxiv
Magnitudes are necessarystatementproposition C.6arxiv
A cap insures against an underestimated token pricestatementcorollary A.9arxiv
How many sightings before adding an instructionstatementtheorem 1arxiv
Envelope boundstatementlemma A.8arxiv

Catalogue records