pith:PUTD67ZF
Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systems
Goal-Mem improves RAG memory retrieval by decomposing user goals into atomic subgoals and applying backward chaining to fetch missing facts.
arxiv:2605.12213 v2 · 2026-05-12 · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{PUTD67ZFDKZJQ4DBR56VEFNB35}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Through extensive experiments on two datasets and comparing to nine strong memory baselines, we show that Goal-Mem consistently improves performance, particularly on tasks requiring multi-hop reasoning and implicit inference.
That automatic decomposition of goals into atomic subgoals combined with targeted retrieval will reliably surface missing intermediate facts without introducing reasoning errors or requiring human intervention.
Goal-Mem improves RAG memory retrieval in agentic LLMs by explicit goal decomposition and backward chaining via Natural Language Logic, outperforming nine baselines on multi-hop and implicit inference tasks.
Cited by
Receipt and verification
| First computed | 2026-06-09T01:05:46.961364Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
7d263f7f251ab29870618f7d5215a1df53a229eda3c67e4253600f6c1abf2785
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/PUTD67ZFDKZJQ4DBR56VEFNB35 \
| 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: 7d263f7f251ab29870618f7d5215a1df53a229eda3c67e4253600f6c1abf2785
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "598ddbab20a0861b3e2f75165ff7ee40827ac27d20fff9fd2ef45b8f725d122a",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-05-12T14:51:02Z",
"title_canon_sha256": "eed31c490fa286472976ea67cbb361e4237a28bc43fc351d12c6fa18490df991"
},
"schema_version": "1.0",
"source": {
"id": "2605.12213",
"kind": "arxiv",
"version": 2
}
}