pith:MEMTMOH2
LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent
A lite virtual world mirroring real searches lets a 4B agent master deep research via scalable RL.
arxiv:2604.17931 v3 · 2026-04-20 · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{MEMTMOH2I65U2UFU73PRCDTNND}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
LiteResearcher is a training framework that makes Agentic RL scalable: by constructing a lite virtual world that mirrors real-world search dynamics, we enable a continuously improving training recipe that empowers a tiny search agent to outperform large-scale open-source and commercial models (e.g., Tongyi DeepResearch and Claude-4.5 Sonnet). Specifically, on common benchmarks such as GAIA and Xbench, our LiteResearcher-4B achieves open-source state-of-the-art results of 71.3% and 78.0% respectively.
The lite virtual world accurately captures the essential dynamics of real-world search so that capabilities learned inside it transfer to genuine research tasks without introducing simulation-specific artifacts or instability.
LiteResearcher uses a lite virtual world to make agentic RL training scalable and stable, enabling a 4B model to achieve 71.3% on GAIA and 78.0% on Xbench, outperforming larger open-source and commercial systems.
Cited by
Receipt and verification
| First computed | 2026-07-01T01:18:24.677761Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
61193638fa47bb4d50b4fedf110e6d68c480f1a8a063af6dd2f694bf8a957766
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/MEMTMOH2I65U2UFU73PRCDTNND \
| 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: 61193638fa47bb4d50b4fedf110e6d68c480f1a8a063af6dd2f694bf8a957766
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "99d9257e1d274090de3f46c6fdec73c9ae36b346baa271cb3d244ecb792ba3fb",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-04-20T08:11:09Z",
"title_canon_sha256": "ac7556e0f8c53b366181318e144fcfab277bb2e89ef313070b6db69cdfe1a841"
},
"schema_version": "1.0",
"source": {
"id": "2604.17931",
"kind": "arxiv",
"version": 3
}
}