pith. sign in
Pith Number

pith:W6LXFWZS

pith:2026:W6LXFWZSBPEO3LDGK5XPVYJ4X7
not attested not anchored not stored refs pending

MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents

Hung Pham Van, Khang Pham Tran Tuan, Linh Ngo Van, Nam Le Hai, Nguyen Manh Hieu, Nguyen Thi Ngoc Diep, Trung Le

MemORAI equips LLMs with selective memory filtering, provenance tracking, and adaptive retrieval to enable coherent long-term personalized conversations.

arxiv:2605.01386 v2 · 2026-05-02 · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{W6LXFWZSBPEO3LDGK5XPVYJ4X7}

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

Evaluated on LOCOMO and LongMemEval benchmarks, MemORAI achieves state-of-the-art performance in memory retrieval and personalized response generation, demonstrating that selective storage, enriched representation, and adaptive retrieval are essential for coherent, personalized LLM agents.

C2weakest assumption

The assumption that the three proposed components (dual-layer compression with selective filtering, turn-level provenance in the multi-relational graph, and query-conditioned edge weighting in Dynamic Weighted PageRank) will reliably solve information dilution and uniform retrieval problems without introducing new overhead or retrieval biases that could degrade performance on unseen conversation styles or domains.

C3one line summary

MemORAI combines selective filtering, provenance tracking in multi-relational graphs, and dynamic weighted PageRank retrieval to achieve state-of-the-art memory retrieval and personalized responses in LLM agents on LOCOMO and LongMemEval benchmarks.

Receipt and verification
First computed 2026-06-03T01:05:14.332464Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

b79772db320bc8edac66576efae13cbfd1f050446c828b9e30319a0783b7dee7

Aliases

arxiv: 2605.01386 · arxiv_version: 2605.01386v2 · doi: 10.48550/arxiv.2605.01386 · pith_short_12: W6LXFWZSBPEO · pith_short_16: W6LXFWZSBPEO3LDG · pith_short_8: W6LXFWZS
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/W6LXFWZSBPEO3LDGK5XPVYJ4X7 \
  | 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: b79772db320bc8edac66576efae13cbfd1f050446c828b9e30319a0783b7dee7
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "4d33836d1f2a2d1df2195fdccc19c2e56b95e489c85cd597d7aff64c807acc91",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-02T11:20:34Z",
    "title_canon_sha256": "4086ccdd6cb62d12a8ec69483f72670afecedc9404b1dac9161e22f6eaf9f6fc"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.01386",
    "kind": "arxiv",
    "version": 2
  }
}