Pith Number

pith:2RYTZS34

pith:2026:2RYTZS34WMZMQI5RTH7DGMX5UU

not attested not anchored not stored refs pending

OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search

Erhan Zhang, Jiaxin Mao, Wei Yang, Xiaochi Wei, Yan Gao, Yao Hu, Yiqun Chen, Yi Wu, Zechun Niu

OASES improves agentic search by co-training policies with outcome-aligned evaluators for better process rewards.

arxiv:2604.03675 v3 · 2026-04-04 · cs.AI · cs.CL · cs.IR

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{2RYTZS34WMZMQI5RTH7DGMX5UU}

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

Experiments on five multi-hop QA benchmarks show that OASES consistently outperforms strong RL baselines, with further analyses confirming the benefits of outcome-aligned process rewards and search-evaluation co-training.

C2weakest assumption

That co-training the evaluator on the evolving policy will produce reliable, non-stale process rewards without introducing new biases or instability that undermine the final outcome alignment.

C3one line summary

OASES co-trains search policies and evaluators to generate outcome-aligned process rewards, outperforming standard RL baselines on five multi-hop QA benchmarks.

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-26T01:03:29.356430Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d4713ccb7cb332c823b199fe3332fda529f5dae2b9ae4a1527deb400f9dd1402

Aliases

arxiv: 2604.03675 · arxiv_version: 2604.03675v3 · doi: 10.48550/arxiv.2604.03675 · pith_short_12: 2RYTZS34WMZM · pith_short_16: 2RYTZS34WMZMQI5R · pith_short_8: 2RYTZS34

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/2RYTZS34WMZMQI5RTH7DGMX5UU \
  | 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: d4713ccb7cb332c823b199fe3332fda529f5dae2b9ae4a1527deb400f9dd1402

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2a8d2fcba6312f453f9406c66e80f6951f3c8790171ffa936b2134e3ff1ae125",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.IR"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-04-04T10:23:46Z",
    "title_canon_sha256": "bcac663e8edd466d1911229db2b77e3a43cbca804b9ff5130cce9540ded13485"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.03675",
    "kind": "arxiv",
    "version": 3
  }
}