pith. sign in
Pith Number

pith:KFUVCQD4

pith:2026:KFUVCQD4T5A2X6AU4U6PLICPVF
not attested not anchored not stored refs resolved

GAAMA: Graph Augmented Associative Memory for Agents

Nitin Sareen, Shubhendu Sharma, Swarna Kamal Paul

GAAMA builds a concept-mediated knowledge graph to improve memory retrieval for AI agents across multi-session conversations.

arxiv:2603.27910 v2 · 2026-03-29 · cs.AI · cs.IR · cs.MA

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{KFUVCQD4T5A2X6AU4U6PLICPVF}

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 LoCoMo-10 (1,540 questions, 10 multi-session conversations), GAAMA achieves 79.1% mean reward, a +4.2 pp improvement over a tuned RAG baseline, the strongest comparator. On MemoryArena, GAAMA outperforms full-context baselines across three tasks with advantages growing monotonically with dialogue length.

C2weakest assumption

The LLM-based extraction of atomic facts and topic-level concept nodes, together with the synthesis of higher-order reflections, accurately preserves structural relationships and avoids introducing errors that would degrade retrieval quality.

C3one line summary

GAAMA constructs a four-node-type knowledge graph with concept-mediated edges and Personalized PageRank retrieval to improve multi-session agent memory, reporting 79.1% mean reward on LoCoMo-10 (+4.2 pp over tuned RAG) and gains on MemoryArena tasks that grow with dialogue length.

References

18 extracted · 18 resolved · 0 Pith anchors

[1] User’s birthday is March 15, 1990 1990
[2] **Do NOT duplicate existing facts.** If an existing fact already captures the information, skip it
[3] **Resolve relative dates to absolute dates** using the conversation timestamp. For example, if the conversation date is "2023-06-15" and the user says "last week", resolve to approximately "2023-06-08 2023
[4] Derive general knowledge from episodes by doing multi-step reasoning where possible
[5] Only extract general knowledge, preferences, attributes, or relationships that can be applied broadly

Formal links

1 machine-checked theorem link

Receipt and verification
First computed 2026-05-18T02:44:30.605980Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

516951407c9f41abf814e53cf5a04fa95947a9b17daa696ac557231819815809

Aliases

arxiv: 2603.27910 · arxiv_version: 2603.27910v2 · doi: 10.48550/arxiv.2603.27910 · pith_short_12: KFUVCQD4T5A2 · pith_short_16: KFUVCQD4T5A2X6AU · pith_short_8: KFUVCQD4
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/KFUVCQD4T5A2X6AU4U6PLICPVF \
  | 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: 516951407c9f41abf814e53cf5a04fa95947a9b17daa696ac557231819815809
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "7a87e9db5e0038ff315f516a2451f634741e4c35ce8eed238036704e227f760b",
    "cross_cats_sorted": [
      "cs.IR",
      "cs.MA"
    ],
    "license": "http://creativecommons.org/licenses/by-sa/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-03-29T23:33:38Z",
    "title_canon_sha256": "4a7bc3656528399f40d0b72e65405a660ea43955f81a482b1eae6781af50425b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.27910",
    "kind": "arxiv",
    "version": 2
  }
}