# Bloodhound

To teach a search to find the answer, start at the answer and walk back to the question.

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

Can navigation be learned from where answers were found?

Once the answer’s location is known, the path from the question to it is a free label. A policy of a hundred-odd parameters, trained on those labels, would be a nearly weightless way to search a memory it has never seen.

## 1. Idea

Experiment 5 of 10 in the Engram series. [← Web](/engram/web) · [Engram overview](/engram) · [Horizon →](/engram/horizon)

Most search is told how similar things are and nothing about how to move. Bloodhound walks through memory one hop at a time, with a tiny network scoring each possible next hop from a handful of features. Training is the unusual part: start from a known answer, walk back toward the question, and call that path perfect. Every step on it is a positive example.

**Bloodhound · training and use.** Trained on paths walked back from known answers, a tiny kernel later scores each next hop from features alone, with no answers in sight.

The kernel never sees what a fact says, only how the step looks. That is what makes it portable, and what makes it a long shot.

## 2. Where it came from

The archive holds a family of scripts: a reverse bloodhound that trained a small network on perfect paths, an entity version with seven features, kernels of 29, 73, 145 and 273 parameters, a “pack” of four specialised dowsers feeding one ring, and a content-blind navigator of 145 parameters that decided whether to explore or backtrack. They ran on MemoryAgentBench conflict-resolution scenarios.

None of it left a result. The scripts print to the screen, and the scorecard lists the one-feature tests and none of these. The audit also found the training split was often the first four scenarios with evaluation on all eight, which includes the four it trained on; and the paths were built from gold answers, so any run that reused them for scoring had read the answer key. A network of a few hundred weights cannot learn much from thirty queries per scenario either. The timeline simply moves on, with no written conclusion.

## 3. Hypothesis

Stated before running. A kernel trained on paths from rows that are disjoint from the scored ones beats Dense at equal k on FactConsolidation, with a paired interval above zero.

The prior is against it. The features are mostly similarities that Dense already uses, the network is tiny and the training data is thin, so a small gain or none is the expected result. The more useful thing to learn is whether the gap between trained and untrained kernels is zero, which is a cleaner question than whether Bloodhound wins.

## 4. Design

**Paths.** On training rows only, the chunk that holds the gold answer string marks the end of a path, and the walk back to the question is the label. Gold answers are used here and nowhere else.

**Kernel.** A tiny multilayer perceptron over the seven features, about 145 weights, as the archive had it. No larger network, so that a gain cannot be put down to capacity.

**Training split.** MemoryAgentBench rows disjoint from the scored ones, seeded, saved as a file and asserted disjoint in code. The scored questions are never seen in training, and the kernel at test time sees no answers.

**Equal k.** The walk is bounded so that the returned list is k items, the same as every other method.

**Seeds.** Initialisation and walk order are random, so five seeds, mean and range.

**Ablation.** The same network untrained. If it scores like the trained one, the training added nothing.

## 5. How it is tested

Tier 0 on LongMemEval_S and tier 1 on both FactConsolidation sets. The comparison that carries the idea is trained against untrained, then trained against Dense. Training and test losses are reported as well, because a kernel that fits its training paths and no others is the first thing the audit would suspect.

The standing rules for every Engram experiment apply here unchanged.

## 6. Results

## 7. What would change the conclusion

- If trained and untrained kernels score alike, learning from reverse paths did nothing.
- If the trained kernel beats Dense on a training row and not on a held-out one, it memorised paths, and the old design was fitted to its own test.
- If it works on FactConsolidation and fails on LongMemEval, the kernel learned a feature of one dataset, not navigation.

## Sources

Experiment 5 of 10 in the Engram series. [← Web](/engram/web) · [Engram overview](/engram) · [Horizon →](/engram/horizon)

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