Pith Number

pith:ZLDIFVCE

pith:2025:ZLDIFVCE5L7K3T5DLSWSPHGKPY

not attested not anchored not stored refs pending

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Fan Yang, Li Lyna Zhang, Mao Yang, Ning Shang, Xinyu Guan, Yifei Liu, Yi Zhu, Youran Sun

Small language models reach expert math reasoning by evolving their own search and evaluation processes over repeated rounds.

arxiv:2501.04519 v1 · 2025-01-08 · cs.CL

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

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

Through 4 rounds of self-evolution with millions of synthesized solutions for 747k math problems, rStar-Math boosts SLMs' math reasoning to state-of-the-art levels. On the MATH benchmark, it improves Qwen2.5-Math-7B from 58.8% to 90.0% and Phi3-mini-3.8B from 41.4% to 86.4%, surpassing o1-preview by +4.5% and +0.9%.

C2weakest assumption

The process preference model trained on self-generated trajectories provides unbiased, accurate step-level guidance during MCTS search and does not overfit to patterns in the synthesized data or the specific benchmarks used for evaluation.

C3one line summary

Small LLMs reach 90% on the MATH benchmark and solve 53% of AIME problems by self-evolving through MCTS with a process preference model, surpassing o1-preview without distillation from larger models.

Formal links

2 machine-checked theorem links

Cited by

22 papers in Pith

Sample-efficient LLM Optimization with Reset Replay

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search

Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs

Sharpness-Guided Group Relative Policy Optimization via Probability Shaping

Receipt and verification

First computed	2026-05-17T23:38:15.094996Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

cac682d444eafeadcfa35cad279cca7e0fd9d97d688f4665766cae59e4018d90

Aliases

arxiv: 2501.04519 · arxiv_version: 2501.04519v1 · doi: 10.48550/arxiv.2501.04519 · pith_short_12: ZLDIFVCE5L7K · pith_short_16: ZLDIFVCE5L7K3T5D · pith_short_8: ZLDIFVCE

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/ZLDIFVCE5L7K3T5DLSWSPHGKPY \
  | 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: cac682d444eafeadcfa35cad279cca7e0fd9d97d688f4665766cae59e4018d90

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "82ab060f96a357f36dba7338071dab1efb58065f8b576e613279dabaa82e228f",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-01-08T14:12:57Z",
    "title_canon_sha256": "2fbcdee4b0e850ff9f844008d3b960df9e2f2ad5a5c20fa8623f24b32d173b53"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2501.04519",
    "kind": "arxiv",
    "version": 1
  }
}