Pith. sign in
Pith Number

pith:MEMTMOH2

pith:2026:MEMTMOH2I65U2UFU73PRCDTNND
not attested not anchored not stored refs pending

LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent

Bince Qu, Bo Pan, Bo Zhang, Jianyu Zhang, Pan Zhang, Wanli Li, Wei Chen, Zheng Liu

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

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

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.

C2weakest assumption

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.

C3one line summary

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

3 papers in Pith

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

arxiv: 2604.17931 · arxiv_version: 2604.17931v3 · doi: 10.48550/arxiv.2604.17931 · pith_short_12: MEMTMOH2I65U · pith_short_16: MEMTMOH2I65U2UFU · pith_short_8: MEMTMOH2
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
  }
}