Pith Number

pith:3A3PRHTY

pith:2026:3A3PRHTYPJYC6QEYXULSYDPGZQ

not attested not anchored not stored refs resolved

GEAR: Genetic AutoResearch for Agentic Code Evolution

Ahmadreza Jeddi, Babak Taati, Hakki C. Karaimer, Konstantinos G. Derpanis, Minh Ngoc Le

GEAR replaces single-path refinement in autonomous research agents with population-based genetic search over multiple research states.

arxiv:2605.13874 v1 · 2026-05-08 · cs.NE · 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{3A3PRHTYPJYC6QEYXULSYDPGZQ}

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

Under the same compute budget and environment, all three versions outperform the AutoResearch baseline. More importantly, while the baseline tends to settle into one local optimum, GEAR continues finding improvements over longer runs.

C2weakest assumption

That selection based on productivity, novelty, and coverage combined with mutation and crossover will productively explore the space of research states without the population collapsing into low-value branches or wasting compute on unproductive directions.

C3one line summary

GEAR applies genetic algorithms to maintain and evolve multiple research states in autonomous code agents, outperforming single-path baselines by continuing to discover improvements over extended runs.

References

26 extracted · 26 resolved · 15 Pith anchors

[1] GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning · arXiv:2507.19457

[2] URLhttps://arxiv.org/abs/2401.09862. A. Borthwick, S. Ash, and A. Galczak. Robophd: Evolving diverse complex agents under tight evaluation budgets,

[3] RoboPhD: Evolving Diverse Complex Agents Under Tight Evaluation Budgets · arXiv:2604.04347

[4] Toward Autonomous Long-Horizon Engineering for ML Research · arXiv:2604.13018

[5] Internagent-1.5: A unified agentic framework for long-horizon autonomous scientific discovery

Receipt and verification

First computed	2026-05-17T23:39:19.277014Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d836f89e787a702f4098bd172c0de6cc3a4ab3d763596abf084a8c9e21f143f4

Aliases

arxiv: 2605.13874 · arxiv_version: 2605.13874v1 · doi: 10.48550/arxiv.2605.13874 · pith_short_12: 3A3PRHTYPJYC · pith_short_16: 3A3PRHTYPJYC6QEY · pith_short_8: 3A3PRHTY

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/3A3PRHTYPJYC6QEYXULSYDPGZQ \
  | 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: d836f89e787a702f4098bd172c0de6cc3a4ab3d763596abf084a8c9e21f143f4

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "0776c1f85fb0de3fe8f55f8ba25b114299ece7b7786e20db4b90c5c62f6475f9",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.NE",
    "submitted_at": "2026-05-08T00:25:09Z",
    "title_canon_sha256": "a7daba85b472096011507f72b502ac377b5e805a7dec2167905cdd3fbc472774"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13874",
    "kind": "arxiv",
    "version": 1
  }
}