SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling
Paper • 2506.07636 • Published • 3
input listlengths 6 61 | from stringclasses 2
values | f2p_pass int64 -1 -1 | f2p_count int64 -1 -1 | reward int64 -1 -1 | instance_id stringclasses 1
value |
|---|---|---|---|---|---|
[
{
"role": "system",
"content": "You are OpenHands agent, a helpful AI assistant that can interact with a computer to solve tasks.\n<IMPORTANT>\n* If user provides a path, you should NOT assume it's relative to the current working directory. Instead, you should explore the file system to find the file before... | swe-dev | -1 | -1 | -1 | |
[
{
"role": "system",
"content": "You are OpenHands agent, a helpful AI assistant that can interact with a computer to solve tasks.\n<IMPORTANT>\n* If user provides a path, you should NOT assume it's relative to the current working directory. Instead, you should explore the file system to find the file before... | swe-dev | -1 | -1 | -1 | |
[
{
"role": "system",
"content": "You are OpenHands agent, a helpful AI assistant that can interact with a computer to solve tasks.\n<IMPORTANT>\n* If user provides a path, you should NOT assume it's relative to the current working directory. Instead, you should explore the file system to find the file before... | nebius | -1 | -1 | -1 | |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | swe-dev | -1 | -1 | -1 | |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | swe-dev | -1 | -1 | -1 | |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | swe-dev | -1 | -1 | -1 | |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | nebius | -1 | -1 | -1 | |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | swe-dev | -1 | -1 | -1 | |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | swe-dev | -1 | -1 | -1 | |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | swe-dev | -1 | -1 | -1 |
End of preview. Expand in Data Studio
- 🤗 SWE-Dev-7B (Qwen-2.5-Coder-7B-Instruct)
- 🤗 SWE-Dev-9B (GLM-4-9B-Chat)
- 🤗 SWE-Dev-32B (Qwen-2.5-Coder-32B-Instruct)
- 🤗 SWE-Dev-train (Training Data)
🚀 SWE-Dev, an open-source Agent for Software Engineering tasks! This repository contains the SWE-Dev-32B model as presented in the paper SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling.
💡 We develop a comprehensive pipeline for creating developer-oriented datasets from GitHub repositories, including issue tracking, code localization, test case generation, and evaluation.
🔧 Based on open-source frameworks (OpenHands) and models, SWE-Dev-7B and 32B achieved solve rates of 23.4% and 36.6% on SWE-bench-Verified, respectively, even approaching the performance of GPT-4o.
📚 We find that training data scaling and inference scaling can both effectively boost the performance of models on SWE-bench. Moreover, higher data quality further improves this trend when combined with reinforcement fine-tuning (RFT). For inference scaling specifically, the solve rate on SWE-Dev increased from 34.0% at 30 rounds to 36.6% at 75 rounds.
- Downloads last month
- 28