# An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency

Source: [arXiv](https://arxiv.org/abs/2609.22043v1)  
Feed7 permalink: https://feed7.dev/p/2609-22043v1-0442mc1  
Published: 2026-09-18T17:34:13.000Z  
Trust: Needs Review (needs_review)

## Why Included

MDL adds a white-box trust decision between retrieval and generation, using relevance, reliability, and task risk to reject conflicting memories without another model call.

## Source Summary

The Memory Decision Layer is a **zero-parameter** controller between retrieval and generation. It combines relevance, reliability, and task risk, separates confidence from consistency, and can abstain instead of injecting a retrieved memory.

## Practical Implication

Agent builders should treat retrieval and trust as separate decisions, especially when stored memories conflict. In the reported evaluations, MDL reduced hallucinations by **about 56.04%** in general conflict scenarios and added **about 0.14 ms** per decision.

## Agent-Ready Context

The Memory Decision Layer is a **zero-parameter** controller between retrieval and generation. It combines relevance, reliability, and task risk, separates confidence from consistency, and can abstain instead of injecting a retrieved memory.

Agent builders should treat retrieval and trust as separate decisions, especially when stored memories conflict. In the reported evaluations, MDL reduced hallucinations by **about 56.04%** in general conflict scenarios and added **about 0.14 ms** per decision.

The results span multiple models and open datasets, but the abstract does not identify them or describe production workloads. Near-zero hallucination in high-risk scenarios therefore remains a paper result rather than a deployment guarantee.

## Connected Context

Feed7 judgment across 831 accumulated Signals:

MDL makes memory admission a distinct, inspectable control after retrieval: relevance alone does not justify injecting a memory when reliability is low or task risk is high. It complements query-scoped suppression and provenance-aware stores with a cheap abstention point, but does not address model-upgrade portability or establish that its reported conflict results transfer to production workloads.

- [MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents](https://feed7.dev/p/2609-09115v1-1xq0kqg) — MeClear suppresses harmful combinations after retrieval, while MDL decides whether retrieved memory should be injected from relevance, reliability, and risk; together they cover complementary conflict controls.
- [Citation Needed: Provenance for LLM-Built Knowledge Graphs — Daniel Chalef, Zep AI](https://feed7.dev/p/citation-needed-provenance-for-llm-built-knowledge-graphs-daniel-chalef-1iob5t8) — Provenance supplies evidence that a reliability signal could use, especially when synthesized memories merge, change, or outlive their sources.
- [Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability](https://feed7.dev/p/2609-05339v1-06dws1c) — Memory-portability failures remain upstream of MDL: unchanged decision rules cannot ensure reliable admission if a model upgrade or mixed embedding index changes what gets retrieved.
- [Your agents lack context: Here's how to fix "You're absolutely right!" — Brandon Waselnuk, Unblocked](https://feed7.dev/p/your-agents-lack-context-here-s-how-to-fix-you-re-absolutely-right-brand-0pdoj93) — The context-engine proposal likewise separates retrieval from conflict ranking and permissions; MDL adds an explicit risk-aware abstention mechanism to that design.

## Context Map

- Layer: context
- Domains: None
- Topics: agent-memory, retrieval, agent-reliability

## Uncertainty

- The results span multiple models and open datasets, but the abstract does not identify them or describe production workloads. Near-zero hallucination in high-risk scenarios therefore remains a paper result rather than a deployment guarantee.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.