Pith Number

pith:25A7YFIL

pith:2026:25A7YFIL7RJTRGVCHVQIWUSQJR

not attested not anchored not stored refs pending

MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents

Bronislav Sidik, Lior Rokach

MEMTIER's tiered memory architecture improves long-running AI agent accuracy from 5% to 38% on the LongMemEval-S benchmark using only a 6GB consumer GPU.

arxiv:2605.03675 v2 · 2026-05-05 · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{25A7YFIL7RJTRGVCHVQIWUSQJR}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

On the full 500-question LongMemEval-S benchmark, MEMTIER achieves Acc=0.382, F1=0.412 with Qwen2.5-7B on a consumer 6GB GPU - a +33 percentage point improvement over the full-context baseline (0.050 -> 0.382). With DeepSeek-V4-Flash fact pre-population, single-session recall reaches 0.686-0.714, exceeding the paper's RAG BM25 GPT-4o baseline (0.560).

C2weakest assumption

That the observed accuracy and recall lifts are caused by the tripartite architecture, five-signal engine, consolidation daemon, and PPO weight adaptation rather than by benchmark-specific choices, model selection, or the external DeepSeek pre-population step, and that the infrastructure-validated components will deliver the stated performance gains once the camera-ready version is complete.

C3one line summary

MEMTIER delivers 38% accuracy on the 500-question LongMemEval-S benchmark with a 7B model on 6GB GPU, a 33-point gain over full-context baselines, via structured episodic memory, five-signal retrieval, and semantic consolidation.

Receipt and verification

First computed	2026-05-21T01:05:19.860576Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d741fc150bfc53389aa23d608b52504c498ca583f9bbaa284713e4cec7d25979

Aliases

arxiv: 2605.03675 · arxiv_version: 2605.03675v2 · doi: 10.48550/arxiv.2605.03675 · pith_short_12: 25A7YFIL7RJT · pith_short_16: 25A7YFIL7RJTRGVC · pith_short_8: 25A7YFIL

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/25A7YFIL7RJTRGVCHVQIWUSQJR \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: d741fc150bfc53389aa23d608b52504c498ca583f9bbaa284713e4cec7d25979

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6cf84fd207a612baab20bce9e794db623067caf660684c62a29921c34d51c440",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-05T12:14:10Z",
    "title_canon_sha256": "0927aec2da9b2e91501eaaeea5d28d19e8daea8c46ef3a3e2d7dbc0c0338b479"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.03675",
    "kind": "arxiv",
    "version": 2
  }
}