Software Design Catalog
Agentic AI
Back to Catalog
Agentic AI Memory

Adaptive Memory Decay

Give each memory item a retention score that decays over time based on relevance, access frequency, and recency — unused items fade out, frequently-used ones stay sharp.

Adaptive Memory Decay keeps long-term memory stores from turning into landfills: every item gets a retention score and a decay function modulated by how semantically relevant, how often accessed, and how recently touched it is — items that get used survive, items that don’t fade to cold storage or disappear.

Intent & Description

🎯 Intent

Give each long-term memory item a retention score that decays over time via a function modulated by relevance, access frequency, and recency — so unreinforced items fade or fuse while useful items persist.

📋 Context

An agent accumulates long-term memory across many sessions: facts, preferences, summaries, observations. Without cleanup, the store grows without bound and old low-value items start polluting retrieval results. Not everything stays useful — some items were always marginal, others were true once and have gone stale.

💡 Solution

On write, assign each item a retention score and a decay function (typically exponential) whose rate is modulated by three signals: semantic relevance to active goals, access frequency, and recency. Each access reinforces the score; neglect lets it decay. When a score crosses a low threshold, the item is demoted to cold storage, fused with similar items, or dropped — producing a per-item forgetting curve rather than a global cap or fixed TTL. Production layers like Mem0 and Zep apply this; FadeMem formalizes the biologically-inspired version.

Real-world Use Case

  • A long-term memory store grows across sessions and stale items are degrading retrieval quality.
  • Importance varies per item and is better inferred from use patterns than declared at write time.
  • Per-item retention scoring can be updated cheaply on each access.

Source

View Original Source →
📌 TL;DR

Score every memory item and let unused ones decay out — your agent’s memory self-curates instead of growing into a retrieval-degrading junk pile.

Advantages
  • Store size stabilizes without a crude global cap — unused items decay out on their own.
  • Retrieval quality holds as stale low-value items fade and reinforced items stay sharp.
  • Importance is inferred from actual use, not upfront declarations — the store self-curates.
Disadvantages
  • A rarely-accessed but genuinely important fact can decay below threshold and be silently lost.
  • Tuning the decay rate and modulation weights is its own ongoing calibration problem.
  • Decay doesn’t fix staleness in high-relevance items that stay reinforced while their content goes out of date.
Previous
80 of 322
Next