Skip to content

ERRAND: Budgeted Maintenance of Agent Memory

Sep 2026 · 2 citations · 80 references
Computer Science

TL;DR

This work introduces ERRAND, which treats revalidation as a priced errand, which clears every non-oracle policy on the preregistered calibers, primary in every setting and conditional at every binding budget, leading eager revalidation by 10.0pp at the base cap.

Abstract

Deployed agents run on handed-over knowledge: a frozen policy consults a briefing of consolidated items written before the stream begins. The world then moves while the store stands still: paths close, flags change, price bands move; every item was true at handover, and the failure is staleness, not ignorance. We introduce ERRAND, which treats revalidation as a priced errand: a recheck competes with the task it protects for the same scarce actions, funded only when the value per action of resolving a doubt clears a running wage. The errand index is single-peaked, vanishing at both ends of belief, so certainty in either direction costs nothing; free en-route receipts maintain on-path knowledge, and repair writes a version, never a deletion. Under equal action budgets in two drifting tool-use worlds, ERRAND clears every non-oracle policy on the preregistered calibers, primary in every setting and conditional at every binding budget, leading eager revalidation by 10.0pp at the base cap. Restraint wins: given no cap, ERRAND stops on its own, spending 11.0% of steps, while uncapped eager revalidation spends 70.7% and still finishes 4.5pp behind capped ERRAND. The margin sits where the briefing's coverage is thinnest, the shadow price of long-tail knowledge: a small budget, well priced, beats a bigger store that never rechecks.

View source

Similar papers

#artificial intelligence Preprint Sep 2026

FinalityBench: An Effect-Level Benchmark for Agent Decisions Under Delayed and Conflicting Financial Finality

A merchant's payment processor, ledger, ERP and bank feed are updated by messages that get delayed, duplicated, dropped and reordered, so for minutes at a time the four hold contradictory beliefs about the same order. An agent resolving the exception must decide whether to ship goods, re-submit a capture, refund or wai...

Abhishek B. Sharma · 2 citations
Sep 2026

TRACE: Governing Memory Validity in Evolving Multi-Agent Systems

TRACE is presented, a training-free layer that treats re-entry as an eligibility decision rather than a storage or retrieval operation, reconciling a departure checkpoint against absence-period updates, resolving explicit and implicit invalidation, and releasing a bounded Return View only when it covers the returning r...

Wen-Jun Xiong, Shengtao Zhang, Shangding Gu et al. · 0 citations
Preprint Aug 2026

The Compaction Cliff in Long-Running AI Agent Memory

Knowledge Triage, a framework that classifies each line of an agent's knowledge base by type and routes each type through its own retention policy, is addressed, and AgentArtifactCorpus, the classifier, and the reference implementation are released.

S. Zerhoudi, Jelena Mitrović, M. Granitzer · 2 citations
#artificial intelligence Preprint Aug 2026

Invalidation Contracts for Cross-Episode Agent Memory

LLM agents that cache recovery suggestions from API errors can skip re-derivation in later episodes, spending fewer tokens and fewer model calls on constraints they have already learned. Server-side data drift turns those cached fixes into silent failures, and the usual remedy, re-deriving on every episode, gives the s...

Michael Wu, A. Canedo · 1 citation

StateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents

A novel and scalable framework that rewrites a coding agent's context as the repository changes rather than as the context grows, and can achieve a higher resolve rate in all experiments spanned by six coding agents and three edit-heavy benchmarks with little computational overhead.

Zi-Yang Yu, Liang Zhao, Bo-Wen Zhu et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.