Sari la conținut

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

perspectiva aiqbenchCercetare AI

analiza aiqbench

This research proposes a timestamp theory and decision ledger framework to address the latency between an LLM's initial decision and its eventual execution in dynamic environments. By factorizing accuracy into routing capabilities and temporal judgment, the study demonstrates how up-to-date evidence can be systematically delivered to affected decisions before their revision deadlines across models ranging from 8B to frontier scale.
Surse care acoperăarXiv, Effective Altruism Forum, Viakoo, LessWrong
Ce este aceastaLectura unui model asupra articolului și a acoperirii conexe, scrisă pentru aiqbench. Nu sunt cuvintele publicației.

Fresh at Decision, Stale at Action: Routing New Information to LLM Decisions Already Made

arXiv3 min de cititArticolul și perspectiva sunt în engleză.

arXiv:2610.18126v1 Announce Type: new Abstract: Freshness shapes an LLM decision at the moment it is made; the action it commits to is latent, carried out later, in a changing world. We therefore introduce a timestamp theory of decision validity and a decision ledger that realises it. Six timestamps define a decision; a freshness ceiling bounds what up-to-date evidence guarantees at action time, placing the remaining risk in information published afterwards. Accuracy then factorises into two capabilities: routing, which delivers that information to affected decisions before their revision deadlines, and temporal judgment, which reads it for the time of action. The ledger is persistent state holding each decision's times, evidence and background knowledge, indexed by watch conditions written at decision time. Controlled decision streams with exact labels confirm four predictions across five LLMs, from 8B to frontier scale: freshness alone yields exactly the accuracy the ceiling predicts; models act on decisive news once it arrives, so accuracy follows routing; the ledger's index sets what routing reaches, and watch conditions reach indirect dependencies at low exposure; and the remaining errors concern when a change takes effect. Freshness makes a decision right when it is made; routing and temporal judgment keep it right when it is carried out.

Abstract:Freshness shapes an LLM decision at the moment it is made; the action it commits to is latent, carried out later, in a changing world. We therefore introduce a timestamp theory of decision validity and a decision ledger that realises it. Six timestamps define a decision; a freshness ceiling bounds what up-to-date evidence guarantees at action time, placing the remaining risk in information published afterwards. Accuracy then factorises into two capabilities: routing, which delivers that information to affected decisions before their revision deadlines, and temporal judgment, which reads it for the time of action. The ledger is persistent state holding each decision's times, evidence and background knowledge, indexed by watch conditions written at decision time. Controlled decision streams with exact labels confirm four predictions across five LLMs, from 8B to frontier scale: freshness alone yields exactly the accuracy the ceiling predicts; models act on decisive news once it arrives, so accuracy follows routing; the ledger's index sets what routing reaches, and watch conditions reach indirect dependencies at low exposure; and the remaining errors concern when a change takes effect. Freshness makes a decision right when it is made; routing and temporal judgment keep it right when it is carried out.

Artificial Intelligence (cs.AI); Computer Science and Game Theory (cs.GT); Information Retrieval (cs.IR); Multiagent Systems (cs.MA)

I.2.7; I.2.11; I.2.3; I.2.4; H.3.3

arXiv:2610.18126 [cs.AI]

(or arXiv:2610.18126v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2610.18126 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Text integral sub licența deschisă a publicației · 311 cuvinte

Subiecte conexe