pith:IIEAK72Y
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
Reinforcement learning on open software evolution data enables LLMs to recover developer reasoning and solve 41% of real GitHub issues.
arxiv:2502.18449 v2 · 2025-02-25 · cs.SE · cs.AI · cs.CL
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{IIEAK72YB67YYZTRLIIH2KDEWJ}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
our resulting reasoning model, Llama3-SWE-RL-70B, achieves a 41.0% solve rate on SWE-bench Verified -- a human-verified collection of real-world GitHub issues. To our knowledge, this is the best performance reported for medium-sized (<100B) LLMs to date, even comparable to leading proprietary LLMs like GPT-4o.
The assumption that a lightweight rule-based similarity score between ground-truth and generated solutions serves as an effective reward for learning genuine reasoning processes rather than superficial pattern matching.
SWE-RL uses RL on software evolution data to train LLMs achieving 41% on SWE-bench Verified with generalization to other reasoning tasks.
References
Formal links
Cited by
Receipt and verification
| First computed | 2026-05-17T23:38:52.780436Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
4208057f580fbf8c66715a107d2864b2548c8bef57c8e7cc713325e3ddea90f6
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/IIEAK72YB67YYZTRLIIH2KDEWJ \
| 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: 4208057f580fbf8c66715a107d2864b2548c8bef57c8e7cc713325e3ddea90f6
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "730dfc0fa178a079f7ed7e2f80a86ff8ac9f804908893c4a1853b3b8bb5d84b9",
"cross_cats_sorted": [
"cs.AI",
"cs.CL"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.SE",
"submitted_at": "2025-02-25T18:45:04Z",
"title_canon_sha256": "a91330707567ffa0ad37268e5f68258ff99c1316fd5dd035252f3e5e1a1cc008"
},
"schema_version": "1.0",
"source": {
"id": "2502.18449",
"kind": "arxiv",
"version": 2
}
}