pith:FTYVOO5Z
UR$^2$: Unify RAG and Reasoning through Reinforcement Learning
A reinforcement learning framework unifies RAG and reasoning by learning when to retrieve and how to combine knowledge sources.
arxiv:2508.06165 v5 · 2025-08-08 · cs.CL · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{FTYVOO5ZNSHTNTQW2ZQWK3PXFZ}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
UR², built on Qwen-2.5-3/7B and LLaMA-3.1-8B, consistently outperforms existing RAG and RL baselines, and achieves performance comparable to GPT-4o-mini and GPT-4.1-mini on several benchmarks.
The difficulty-aware curriculum and hybrid knowledge access strategy can be reliably learned through RL without introducing new instabilities or requiring extensive hyperparameter tuning that is not reported in the abstract.
UR² is a general RL framework that dynamically coordinates RAG and reasoning via difficulty-aware curriculum and hybrid knowledge access, outperforming baselines on QA, MMLU-Pro, medical, and math tasks with models up to 8B parameters.
Formal links
Receipt and verification
| First computed | 2026-06-03T01:05:05.453833Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
2cf1573bb96c8f36ce16d661656df72e422dfbafe44ac75866e929a641f1909d
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/FTYVOO5ZNSHTNTQW2ZQWK3PXFZ \
| 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: 2cf1573bb96c8f36ce16d661656df72e422dfbafe44ac75866e929a641f1909d
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "73e36473814734f3c5918d47fc2e2f1921671421024901fcb94582f40854694a",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CL",
"submitted_at": "2025-08-08T09:33:20Z",
"title_canon_sha256": "0bfd828ac4e8c9d7774cb48123585f70ecbeb3992eccded2963e2a531b34a1f7"
},
"schema_version": "1.0",
"source": {
"id": "2508.06165",
"kind": "arxiv",
"version": 5
}
}