Pith Number

pith:3RCJZ5ZK

pith:2026:3RCJZ5ZKJYWIVHXJDRAH6SA2XM

not attested not anchored not stored refs pending

Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games

Jiarui Gan, Jiexin Wang, Mengchen Zhao, Pengxu Yang, Yi Cai, Yidong He, Yutao Lai

Strat-Reasoner improves LLM performance in multi-agent games by 22.1 percent through recursive modeling of other agents' reasoning and group-relative reinforcement learning.

arxiv:2605.04906 v2 · 2026-05-06 · 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{3RCJZ5ZKJYWIVHXJDRAH6SA2XM}

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

Experimental results show that Strat-Reasoner substantially improves strategic abilities of underlying LLMs, achieving 22.1% average performance improvements across various multi-agent games.

C2weakest assumption

That the centralized Chain-of-Thought comparison module supplies unbiased, effective reward signals for intermediate reasoning sequences without introducing evaluation circularity or requiring hand-tuned thresholds that favor the proposed method.

C3one line summary

Strat-Reasoner boosts LLMs' strategic performance in multi-agent games by 22.1% on average via recursive reasoning that includes other agents' thought processes and a centralized CoT evaluator for intermediate rewards.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-26T02:04:12.138521Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

dc449cf72a4e2c8a9ee91c407f481abb36f918b2c16267b105322c89e6a60d55

Aliases

arxiv: 2605.04906 · arxiv_version: 2605.04906v2 · doi: 10.48550/arxiv.2605.04906 · pith_short_12: 3RCJZ5ZKJYWI · pith_short_16: 3RCJZ5ZKJYWIVHXJ · pith_short_8: 3RCJZ5ZK

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/3RCJZ5ZKJYWIVHXJDRAH6SA2XM \
  | 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: dc449cf72a4e2c8a9ee91c407f481abb36f918b2c16267b105322c89e6a60d55

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6682c5ba6ba04186213d5e48b22c9dd04edd20d962feaeb17b7ae76ee46e8c40",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-06T13:35:14Z",
    "title_canon_sha256": "5099b995350a9d628d4c1d02b5beb97eae7363ad3d2470883cf01cd75ac79321"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.04906",
    "kind": "arxiv",
    "version": 2
  }
}