GROOM: Gated Refresh of Organizational Memory — BeConfident Labs<br>(a)  trigger sequence(b)  maintenance opsAgent sessionLauncherGROOM agentwiki/checks: enabled?last run ≥ 24 h ago?skill activationreturns in spawn · detachedread all pagespage contentsedits · one opappend journal entrytconversation proceeds, never blockedlintFix the form.Never touch the meaning.pruneCut what repeats.Leave fewer lines behind.expandIngest what changed.Touch at most 3–6 files.researchAdmit new papers.Demand citations first.one op per cycle, chosen by config

Figure 1 · One consultation, end to end (interactive). A read activates the skill; the launcher checks its gates and returns in under 100 ms while a detached GROOM agent reads the corpus, applies one operation, and journals the run. The conversation never blocks. The panel on the right names the four maintenance operations.The full technical preprint, with the complete evaluation, is available as a PDF.Read the full preprint (PDF) →<br>AUTHORS<br>Gui Dávid<br>Author contributions statement below.

AFFILIATIONS<br>Head of AI at BeConfident

PUBLISHED<br>June 18, 2026

Code & benchmark harness ↗Technical paper →Companion survey →<br>An LLM agent is only as current as the text it reads. Production agents ground their answers in curated corpora: engineering wikis, runbooks, style guides, the documents behind retrieval-augmented generation[1]. We version the model and update it on a schedule. The corpus sits still, and the world moves past it. GROOM keeps the corpus current by turning each consultation into the trigger to maintain it. Every edit it makes passes a checkpoint before it counts, so the maintenance runs on its own.<br>Knowledge rot<br>Start with a concrete failure. An agent reads your team’s wiki before it answers a question. Six weeks ago someone wrote that the staging database lives at db-staging-1. Last week the team moved staging to db-staging-3 and left the page alone. The agent reads the page and answers db-staging-1, with full confidence.<br>The model did nothing wrong. It read the source it was told to trust and reported what the source said. No exception fired. No log line turned red. The agent gave a confident wrong answer because the page behind it was old.<br>We call this knowledge rot : a corpus describes a world that has moved on, and the agents reading it inherit the error. A page written in March documents an API that shipped a breaking change in May. An agent reads it in June and repeats the mistake in whatever it builds. The failure stays invisible until something downstream breaks.<br>Context engineering[2] manages the window, the tokens that reach the model at inference time. GROOM manages the source those tokens come from. Keep the source fresh and the agent stays right; let it rot and the agent inherits the error and states it with the same confidence.<br>Most of the tools we build for knowledge bases handle two jobs: writing pages and finding them. Authoring, search, embeddings, retrieval. Keeping pages current after they are written gets far less attention. GROOM is built for that third job.<br>Why the usual fixes miss<br>Three reflexive answers come up first. Each one fixes something real and leaves the rot in place.<br>Re-index it. Rebuild the embeddings, add a reranker, tune retrieval. This makes a stale fact easier to find. It does not make the fact true. A faster retriever surfaces the wrong page sooner. Retrieval freshness and content freshness are separate axes, and correctness lives on the second one.<br>Run a nightly job over everything. A cron that rechecks every page spends most of its budget on pages no agent reads, lags reality by up to a day, and asks a model to operate over the whole corpus in one unbounded pass. That pass is the unsupervised, hard-to-review operation you want to avoid. Grow the corpus and the cost grows with the shelf, not with what agents use.<br>Have a person review it. This is where most teams land, and it does not scale. It also inverts the priority: the pages that rot are the ones no one opens, which are the ones a review pass keeps skipping.<br>All three treat maintenance as a separate chore, scheduled and paid for on its own, cut off from the moments an agent uses the knowledge. GROOM joins the two.<br>The idea: reading the corpus maintains it<br>The pattern comes from web caching. HTTP has a directive called stale-while-revalidate[3]. When a cached response is past its freshness window, the cache serves the stale copy at once and fetches a fresh one in the background, so the next request gets the update. The reader never waits. The cache stays useful because agents keep reading it.<br>GROOM applies that pattern to knowledge. A consultation is the trigger to check whether the page needs maintenance. The agent that reads it never waits: the check returns in tens of milliseconds, and any real work runs in a separate process the reader never sees. The corpus gets maintained as a side effect of being read.<br>This gives GROOM a property a nightly job cannot have: maintenance...