# Web

The fact you need often shares no words with the question. It shares a name with a fact that does.

Pilot results · d/rksci research · Published 2026-10-08 · Tags: Agent Memory, Retrieval, MemoryAgentBench, LongMemEval, Engram, Entities, Multi-hop

Can one hop through a shared name find the updated fact?

Multi-hop questions need a chain of facts, and only the first link looks like the question. A graph of shared entities is the usual answer, and the published systems that use one are among the best on this benchmark.

## 1. Idea

Experiment 4 of 10 in the Engram series. [← Ring](/engram/ring) · [Engram overview](/engram) · [Bloodhound →](/engram/bloodhound)

Ask “what is the country of citizenship of the spouse of the author of Book A?” and the best match by wording is the fact about Book A. The fact that answers the question is about Person C and Country D, and shares no words with the question at all. Web follows the names: Book A leads to Person B, Person B to Person C, Person C to Country D.

**Web · one hop.** A hit names its entities; an index of entities leads to every other fact that mentions one, and those are merged with the hits and re-scored.

One hop reaches the second link only. A three-link chain needs a second pass, which is not added until the single hop has been measured.

## 2. Where it came from

The archived entity walk took the cosine top-5, found the entities in them, hopped once through a graph of shared entities and added what it found. Entities were any capitalised words. It scored 43% against cosine’s 39%.

The audit found two problems. The function returned k extra chunks on top of the k it started with, so it handed the metric twice as many candidates as cosine had. And capitalised-word entities are crude: every sentence starts with one, and a surname on its own and the same person’s full name count as different entities. A third problem was shared with the rest of the round, the substring-in-any-chunk metric, which rewards size.

## 3. Hypothesis

Stated before running. With proper entities and the result cut to k, Web beats Dense on FactConsolidation multi-hop with a paired interval above zero, and does nothing on single-hop, where the question names the entity already.

The prior is cautious. Published multi-hop scores on this benchmark are very low for everything except a long-context reasoning model: the best retrieval system in the table reaches 7 on a hundred questions at the 262K context, and HippoRAG-v2, which is built on a graph of exactly this kind, reaches 5. Any gain here will be small against a floor that low, and it will be described that way.

## 4. Design

**Entities.** Named entities or noun chunks from an off-the-shelf tagger, normalised so that a short and a long form of one name map together. They replace the capitalised-word rule.

**Hop.** From the top hits, collect every stored fact that shares an entity, one hop only. The union is re-scored against the query.

**Equal k.** The merged set is cut to k, so the hop can only change which k, never how many. The archived version’s extra chunks are gone.

**Order.** Ties follow the harness rule: toward the more recently written fact. A fact and its update share every entity, so the tie-break decides which one the hop returns first.

**Ablation.** The archived capitalised-word entities, at k. It shows how much of any gain is the tagger and how much is the idea.

## 5. How it is tested

Tier 0 on LongMemEval_S, where the question types that need several sessions are the interesting ones (27 of the 100 pilot questions are multi-session), and tier 1 on both FactConsolidation sets. The comparison that matters is Web against Dense and against HippoRAG-v2’s published rows, with the caveat that those are at a different context length from the pilot.

The standing rules for every Engram experiment apply here unchanged.

## 6. Results

## 7. What would change the conclusion

- If Web at equal k does not beat Dense on multi-hop, the first round’s “+3” was the extra chunks.
- If the tagger version beats the capitalised-word version but neither beats Dense, entity quality was a real flaw and still not the bottleneck.
- If Web helps multi-hop and hurts single-hop by pulling in stale versions of the same fact, one hop needs the recency prior from Tide, and the two are combined only after both have been measured alone.

## Sources

Experiment 4 of 10 in the Engram series. [← Ring](/engram/ring) · [Engram overview](/engram) · [Bloodhound →](/engram/bloodhound)

Web is one of ten experiments in Engram. Its rows come from one run on the pilot sets.