Pith Number

pith:GEFG2KKU

pith:2025:GEFG2KKUR3KNR4YL7JAWMUD7QH

not attested not anchored not stored refs pending

MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use

Chengdi Ma, Lingbin Kong, Mingxiang Tuo, Weikang Zhao, Xiaowei Shi, Xili Wang, Xunliang Cai, Yitao Zhai, Zhaohua Yang

arxiv:2508.18669 v1 · 2025-08-26 · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{GEFG2KKUR3KNR4YL7JAWMUD7QH}

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.

Cited by

7 papers in Pith

CurateEvo: Data-Curation Evolving for Agentic Post-Training

Synthesize and Reward -- Reinforcement Learning for Multi-Step Tool Use in Live Environments

Trust Region On-Policy Distillation

When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents

CustomerSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators

Receipt and verification

First computed	2026-07-05T11:59:29.011621Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

310a6d29548ed4d8f30bfa4166507f81ebf6b208235632f98abbfdab677cab5e

Aliases

arxiv: 2508.18669 · arxiv_version: 2508.18669v1 · doi: 10.48550/arxiv.2508.18669 · pith_short_12: GEFG2KKUR3KN · pith_short_16: GEFG2KKUR3KNR4YL · pith_short_8: GEFG2KKU

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/GEFG2KKUR3KNR4YL7JAWMUD7QH \
  | 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: 310a6d29548ed4d8f30bfa4166507f81ebf6b208235632f98abbfdab677cab5e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f7e4a56e3c5f54d74afb093d53d52322a9b093cc22a40d0c658bb0b81f138f67",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-08-26T04:26:29Z",
    "title_canon_sha256": "f8b82a87fe3f21b5aacb26c4f4dbd65d9327bf1b693c66e4e0a4cfb5617f8271"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2508.18669",
    "kind": "arxiv",
    "version": 1
  }
}