Pith Number

pith:3UMECFYB

pith:2026:3UMECFYBCEQSVQLLY5N2U6OPKZ

not attested not anchored not stored refs pending

From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution

Haoyang Zhang, Junjie Wang, Yiming Ren

A compact Gene representation for reusable experience outperforms documentation-heavy Skill packages in guiding AI code solvers and enabling iterative evolution.

arxiv:2604.15097 v2 · 2026-04-16 · cs.SE · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{3UMECFYBCEQSVQLLY5N2U6OPKZ}

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

A compact Gene representation yields the strongest overall average, remains competitive under substantial structural perturbations, and outperforms matched-budget Skill fragments, while reattaching documentation-oriented material usually weakens rather than improves it. On CritPt, gene-evolved systems improve over their paired base models from 9.1% to 18.57% and from 17.7% to 27.14%.

C2weakest assumption

That the 45 scientific code-solving scenarios and the specific definition of Gene versus Skill fragments are representative of broader experience-reuse needs, and that observed gains stem primarily from representation format rather than unstated differences in prompt construction or model behavior.

C3one line summary

Compact Gene representations of experience outperform documentation-oriented Skill packages for test-time control and iterative evolution in code-solving tasks, with measured gains on CritPt from 9.1% to 18.57% and 17.7% to 27.14%.

Cited by

4 papers in Pith

Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents

MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries

Receipt and verification

First computed	2026-06-03T01:05:13.711959Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

dd1841170111212ac16bc75baa79cf565fd3694940ff1b6aba21b99eb48d3887

Aliases

arxiv: 2604.15097 · arxiv_version: 2604.15097v2 · doi: 10.48550/arxiv.2604.15097 · pith_short_12: 3UMECFYBCEQS · pith_short_16: 3UMECFYBCEQSVQLL · pith_short_8: 3UMECFYB

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/3UMECFYBCEQSVQLLY5N2U6OPKZ \
  | 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: dd1841170111212ac16bc75baa79cf565fd3694940ff1b6aba21b99eb48d3887

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4fe322d1d1dc472935ac2ea79b5dc562d59175ddb08c3f52c528d2912f8cf4fe",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2026-04-16T14:55:49Z",
    "title_canon_sha256": "0faa693fe5c0f6a488db0001f578294f48d91bbbe18141e2b917affeaaedfd92"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.15097",
    "kind": "arxiv",
    "version": 2
  }
}