Pith Number

pith:56JFTSWG

pith:2025:56JFTSWGPGAHVUGF44HXLKF23G

not attested not anchored not stored refs pending

Towards Iterative End-to-End Software Development: A Feature-Driven Multi-Agent Framework

Chen Xu, Chong Wang, Junwei Liu, Kaseng Wong, Tong Bai, Weitong Chen, Xin Peng, Yiling Lou

EvoDev's Feature Map models feature dependencies and propagates context to let LLM agents outperform linear baselines by 56.8 percent on Android tasks.

arxiv:2511.02399 v3 · 2025-11-04 · cs.SE · 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{56JFTSWGPGAHVUGF44HXLKF23G}

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

We evaluate EvoDev on challenging Android development tasks and show that it outperforms the best-performing baseline, Claude Code, by a substantial margin of 56.8%, while improving single-agent performance by 16.0%-76.6% across different base LLMs.

C2weakest assumption

That the reported performance gains on Android tasks stem primarily from the Feature Map dependency modeling and context propagation rather than from unstated details in agent prompting, evaluation metrics, or task selection.

C3one line summary

EvoDev introduces an iterative feature-driven framework with a DAG-based Feature Map for context propagation that improves LLM agent performance on end-to-end software development tasks by 56.8% over the best baseline.

Formal links

2 machine-checked theorem links

Cited by

2 papers in Pith

FeatX: Editing Software by Editing Features for Repository-Level Code Evolution

Large Language Model-Based Agents for Software Engineering: A Survey

Receipt and verification

First computed	2026-06-08T01:03:50.708128Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ef9259cac679807ad0c5e70f75a8bad9a6e51da699e04f26aaceab94bab4db3e

Aliases

arxiv: 2511.02399 · arxiv_version: 2511.02399v3 · doi: 10.48550/arxiv.2511.02399 · pith_short_12: 56JFTSWGPGAH · pith_short_16: 56JFTSWGPGAHVUGF · pith_short_8: 56JFTSWG

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/56JFTSWGPGAHVUGF44HXLKF23G \
  | 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: ef9259cac679807ad0c5e70f75a8bad9a6e51da699e04f26aaceab94bab4db3e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "7ef04bb111e7f7237d546562af6cf8b3dbe8ebd1fd0466e3710fd1c0d5b028c5",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2025-11-04T09:27:01Z",
    "title_canon_sha256": "4085f73b915aba0f60ba9942997e7559cecb089cd87cb1e0832b135f84a77c12"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2511.02399",
    "kind": "arxiv",
    "version": 3
  }
}