Consolidation and forgetting in memory systems
Be able to implement rules for when episodes become facts and when facts should be forgotten.
Intuition
Episodic memory grows without limit. Without consolidation it becomes a heap of events nobody can use.
Consolidation is the job that periodically reads the new episodes and updates a short list of facts: «prefers code examples», «is working towards the LoRA project by December», «knows linear algebra».
Three rules that decide the quality:
- Support: a fact requires at least k episodes (or an explicit statement from the user). Otherwise isolated coincidences become «truths».
- Confidence: every fact carries a number that is raised on new support and falls with time.
- Validity: facts that are time-bound («revising for the May exam») get an expiry date.
Forgetting is not a shortcoming — it is what keeps the list usable.
Code
import time, math
HALF_LIFE_DAYS = {"preference": 180, "knowledge": 365, "goal": 90, "temporary": 14}
MIN_CONFIDENCE, MIN_SUPPORT = 0.3, 2
def consolidate(facts: list[dict], new_episodes: list[dict], llm) -> list[dict]:
candidates = llm.extract_facts(new_episodes) # [{text, type, sources}]
index = {f["text"].lower(): f for f in facts}
now = time.time()
for c in candidates:
key = c["text"].lower()
if key in index: # reinforce an existing one
f = index[key]
f["sources"] = sorted(set(f["sources"]) | set(c["sources"]))
f["confidence"] = min(1.0, f["confidence"] + 0.25)
f["last_supported"] = now
elif len(c["sources"]) >= MIN_SUPPORT: # a new fact requires support
index[key] = {**c, "confidence": 0.5, "last_supported": now}
return forget(list(index.values()), now)
def forget(facts, now):
kept = []
for f in facts:
age_d = (now - f["last_supported"]) / 86400
hl = HALF_LIFE_DAYS.get(f.get("type", "preference"), 180)
f["confidence"] *= 0.5 ** (age_d / hl)
if f["confidence"] >= MIN_CONFIDENCE:
kept.append(f)
return sorted(kept, key=lambda f: -f["confidence"])[:50] # a hard ceiling
Measure the precision of the list of facts: take a sample of 30 facts and let a human being (or the user themselves) mark them correct / incorrect / out of date. Below 90 % precision the memory does more harm than good — then the thresholds should be raised.
Mastery means
- Implements rules for when episodes become facts
- Introduces forgetting with confidence and time
- Measures the precision of the list of facts
Prerequisites
- FSemantic memory and consolidationrequired
Sign in to do the exercises and build your mastery up.
Sources
- arXiv — MemGPT: Towards LLMs as Operating Systems — arXiv (open access; licence per article)
- arXiv — Generative Agents: Interactive Simulacra of Human Behavior — arXiv (open access; licence per article)