Bounded Working Memory for Long-Horizon Agents

#Abstract

Long-running conversational agents degrade in a manner that resembles capacity exhaustion. This paper argues that attention dilution is the better explanation. This paper separates three concerns that a transcript conflates, describes a bounded relevance-scored working memory, and sets out the measurement that would settle the claim. That measurement has not been performed, which is stated plainly.

#Observed behaviour

An agent holding a full transcript performed acceptably for approximately eighty turns, after which answer quality declined in a way that is difficult to characterise. The failure was not fabrication and not loss of the current topic. Answers were consistent with material from several dozen turns earlier and irrelevant to the current question.

The intuitive response is to supply more context. The evidence points the other way: model performance depends on where relevant information sits within a long input and degrades when it is surrounded by material of similar surface relevance [1]. Adding text increases the surrounding material.

#Three concerns, separated

Working memory. A bounded store of what is currently in play, with items scored for relevance against the active goal and decaying when unreferenced. The bound is a chosen parameter rather than a consequence of conversation length, so marginal cost per turn is independent of the agent's age.

Summarised history. The transcript persists and is not what is transmitted. Older segments compress. This is the least novel component and the one whose benefit is least disputed.

Distilled claims. Conclusions emitted at episode close as typed statements with retained provenance, written into a graph. This is what provides a contradiction surface, and it is treated in a companion note.

The form follows the memory stream retrieval used in the generative agents architecture [2], with relevance to an explicit active goal rather than to the most recent observation.

#Why the prompt is the wrong unit

A secondary argument. Agent behaviour is commonly configured through a single long system prompt. Such an artefact cannot be tested, no contributor can identify which passage is load bearing, and a change intended to fix one behaviour reliably alters another.

Prompt structure demonstrably changes behaviour [4] [3], which is exactly why an unstructured prompt is unmanageable. Decomposing configuration into skills, traits, behaviours, cognitive style, communication style and perception allows each to be versioned and evaluated separately.

#Observed effects

• Token expenditure per turn ceased to scale with conversation length.
• Contradiction became detectable, because comparing claims is a query.
• The specific drift toward previously resolved material was no longer observed.
• No improvement in single-turn reasoning quality, which the construction does not address.

#The measurement this paper does not report

The claim is that degradation past a few hundred turns is attention dilution rather than capacity exhaustion. The experiment that would settle it is a fixed long-horizon task, executed by the same underlying model at several context window sizes, with and without bounded working memory, scored per turn against a held-out rubric.

The prediction distinguishing the two explanations is specific: under the capacity account, degradation should recede as the window grows. Under the dilution account, a larger window with unbounded transcript should not help and may hurt, while a bounded memory at any window size should not degrade.

This experiment has not been run. Until it is, the construction is supported by mechanism and by operational observation rather than by controlled measurement, and the paper should be read on that basis.

#Further limitations

Relevance scoring depends on an explicit representation of the active goal, which is not always available and is itself model-produced. Decay parameters were chosen by inspection rather than fitted. The architecture inherits the underlying model's propensity to produce ungrounded statements, which bounded memory does not address [6] [5].