# Coral

The headline was 93%. It was fourteen of fifteen questions on a thirty-five-fact set the author wrote.

Pilot results · d/rksci research · Published 2026-10-08 · Tags: Agent Memory, Retrieval, MemoryAgentBench, LongMemEval, Engram, Self-organisation, Supersession

Does a whole ecosystem of small rules beat a recency prior?

Coral has several mechanisms at once, so a result for the whole says nothing about which part earned it. The experiment is the whole, then each part removed in turn.

## 1. Idea

Experiment 8 of 10 in the Engram series. [← Loom](/engram/loom) · [Engram overview](/engram) · [Canopy →](/engram/canopy)

Each fact is a polyp. It drifts toward the reef of related facts and settles there, with a probability that rises with affinity. Every cycle a living polyp lays down a ring, and a query feeds the polyps it retrieves. Polyps that go unfed for three lean cycles calcify: the surface dies and the structure stays. When a new fact contradicts an old one, the reef detects non-self. The old polyp calcifies, loses half its score, and keeps a pointer to its heir. A query that lands on the old polyp walks the pointer to the newest living version.

**Coral · lifecycle.** A polyp drifts, settles, grows, calcifies and erodes; a contradiction passes an immune check and leaves an heir; a read walks to the newest living fact and feeds what it reads.

The thresholds are meant to come from the reef itself rather than from constants: a contradiction is declared when a rival’s similarity is an outlier against the reef’s own distribution, and a fact with many dependants resists being replaced.

## 2. Where it came from

Coral was the last design of the first round and the one with the most results, which is why it needs the most care. There were four numbers under one name. 93% was fourteen questions of fifteen on a thirty-five-fact synthetic scenario the author wrote, and the project page later labelled it an LLM evaluation of a MemoryAgentBench scenario. On MemoryAgentBench with text matching, Coral scored 20% to cosine’s 17% on one scenario. With an LLM answering, three scenarios gave 27, 17 and 23 against 23, 10 and 23 for cosine: a mean of 22 against 19, from thirty questions each, so one question was worth 3.3 points and the mean difference is about one question per scenario.

The audit adds to that. Coral retrieved thirty candidates and re-ordered them before keeping ten, while cosine kept a plain ten. The prompt told the model to prefer the most recent fact and presented the facts in order, which gives recency to any retriever for free. One scenario’s seven-point gain was credited to a faster index that let competition “fire over a wider sample”, so an engineering change moved the accuracy. Settling is random, with one seed. “No external constants” was overstated: the code has a maintenance cost, a 30/70 mass split, a settling exponent, two cut-offs and a minimum reef size. And nothing was ever switched off to see which part mattered.

## 3. Hypothesis

Stated before running. Coral as shipped, at equal k, beats Dense on FactConsolidation single-hop with a paired interval above zero, and does not beat Tide: most of what the reef does to a conflict is the date, reached by a longer road.

Most of what this experiment can teach is in the ablations. If heirs are the active ingredient, removing them should cost most of the gain. If calcification and the immune response matter only through the heirs they create, removing either alone should change little.

## 4. Design

**As shipped.** The reef code as it stands, with no re-tuning and its thresholds as they were. The only change is that a read returns exactly k, not thirty candidates cut to ten after a private re-order.

**No calcification.** Superseded polyps keep their full score.

**No heirs.** Calcified polyps stay in the ranking but no longer point to a successor.

**No immune response.** A contradicting fact never triggers the cascade that displaces the old one.

**Seeds.** Settling is random and the approximate index adds its own variation, so five seeds, mean and range.

**Order.** Facts are given to the reader in the same order for every method. The reef does not get a re-order the others do not.

## 5. How it is tested

Tier 0 on LongMemEval_S and tier 1 on both FactConsolidation sets, with paired tests against Dense and Tide. The published rows the reef is read against are Mem0, Cognee and MemGPT, the memory systems in the paper’s table, alongside BM25 and the plain embedding retriever. Their numbers are at a longer context than the pilot, so the comparison is indicative, and it is labelled that way beside it.

The ablation table, one part off at a time, is the main output of this page, and it is reported even when the whole does not beat Dense.

The standing rules for every Engram experiment apply here unchanged.

## 6. Results

## 7. What would change the conclusion

- If Coral as shipped does not beat Dense at equal k, the first round’s plus three points was a larger candidate set and a prompt that favoured recent facts.
- If it beats Dense and ties Tide, the reef is a recency prior with extra steps.
- If removing heirs costs more than removing calcification or the immune response, the supersession pointer is the idea worth keeping, and the biology around it is the story.
- If the five seeds disagree with each other by more than the gap to Dense, the reef is too random to say anything about.

## Sources

Experiment 8 of 10 in the Engram series. [← Loom](/engram/loom) · [Engram overview](/engram) · [Canopy →](/engram/canopy)

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