Pith Number

pith:QBNBTLIK

pith:2026:QBNBTLIKTH5GZZRDZWBNKZBK7G

not attested not anchored not stored refs pending

Verifiable Process Rewards for Agentic Reasoning

Chao Yu, Huaijie Wang, Huining Yuan, Jiaxuan Gao, Xiangmin Yi, Xiao-Ping Zhang, Yi Wu, Yu Wang, Zelai Xu

Converting oracles into dense turn-level rewards improves credit assignment for long-horizon LLM agent reasoning.

arxiv:2605.10325 v2 · 2026-05-11 · 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{QBNBTLIKTH5GZZRDZWBNKZBK7G}

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

dense verifier-grounded rewards can improve long-horizon credit assignment by providing more localized learning signals, with the benefit depending on the reliability of the verifier. Empirically, VPR outperforms outcome-level reward and rollout-based process reward baselines across controlled environments, and more importantly, transfers to both general and agentic reasoning benchmarks.

C2weakest assumption

That reliable symbolic, algorithmic, or posterior-based oracles exist for verifying intermediate actions in the studied densely-verifiable agentic reasoning problems, and that the learned skills transfer meaningfully beyond the specific training environments.

C3one line summary

Verifiable Process Rewards (VPR) converts symbolic oracles into dense turn-level supervision for reinforcement learning in agentic reasoning, outperforming outcome-only rewards and transferring to general benchmarks.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-28T02:04:49.287358Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

805a19ad0a99fa6ce623cd82d5642af9ba0424bf4f31a4787edca92ca4459fb0

Aliases

arxiv: 2605.10325 · arxiv_version: 2605.10325v2 · doi: 10.48550/arxiv.2605.10325 · pith_short_12: QBNBTLIKTH5G · pith_short_16: QBNBTLIKTH5GZZRD · pith_short_8: QBNBTLIK

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/QBNBTLIKTH5GZZRDZWBNKZBK7G \
  | 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: 805a19ad0a99fa6ce623cd82d5642af9ba0424bf4f31a4787edca92ca4459fb0

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d4bfe3ef0f201e3c89d150ecc343a295cb4c526a9ed0a97506291959a5bd1ef6",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-11T10:30:53Z",
    "title_canon_sha256": "46f355d52e1e5a59b9d063d2750f073c1712a00d3375d7fb7768363403138010"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.10325",
    "kind": "arxiv",
    "version": 2
  }
}