From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents

• URL: http://arxiv.org/abs/2604.01496v1
• Date: Thu, 02 Apr 2026 00:11:17 GMT
• Title: From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents
• Abstract summary: SWE-ZERO is a two-stage SFT recipe that achieves state-of-the-art results on SWE-bench.<n>We release a dataset of 300k SWE-ZERO and 13k SWE-HERO trajectories distilled from Qwen3-Coder-480B.<n>Despite being trained exclusively on Python, our agents demonstrate robust zero-shot transferability on SWE-bench.
• Score: 42.7127695634038
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce SWE-ZERO to SWE-HERO, a two-stage SFT recipe that achieves state-of-the-art results on SWE-bench by distilling open-weight frontier LLMs. Our pipeline replaces resource-heavy dependencies with an evolutionary refinement strategy: (1) SWE-ZERO utilizes large-scale, execution-free trajectories to master code semantics and repository-level reasoning, and (2) SWE-HERO applies targeted, execution-backed refinement to transition these semantic intuitions into rigorous engineering workflows. Our empirical results set a new benchmark for open-source models of comparable size. We release a dataset of 300k SWE-ZERO and 13k SWE-HERO trajectories distilled from Qwen3-Coder-480B, alongside a suite of agents based on the Qwen2.5-Coder series. Notably, SWE-HERO-32B achieves a 62.2% resolution rate on SWE-bench Verified. Furthermore, despite being trained exclusively on Python, our agents demonstrate robust zero-shot transferability on SWE-bench Multilingual, reaching 44.1% and confirming the paradigm's generalizability across diverse languages.

Related papers

• Open-SWE-Traces: Advancing Dual-Mode Multilingual Distillation for Software Engineering Agents [42.7127695634038]
  ourdataset is a dataset of 207,489 agentic trajectories spanning nine programming languages.<n>This data facilitates the training of models capable of long-horizon reasoning.<n>The best performing model achieves resolve rates of 61.7% on SWE-bench Verified, 57.1% on SWE-bench Multilingual, and 36.8% on SWE-bench Pro.
  arXiv  Detail & Related papers  (2026-06-14T22:10:06Z)
• Orchard: An Open-Source Agentic Modeling Framework [124.68499958175111]
  We present Orchard, an open-source framework for scalable agentic modeling.<n>At its core is Orchard Env, a lightweight environment service providing reusable primitives for sandbox lifecycle management.<n>On top of Orchard Env, we build three agentic modeling recipes.
  arXiv  Detail & Related papers  (2026-05-14T16:35:12Z)
• SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training [78.37721886775215]
  We present SWE-Master, an open-source framework for building effective software engineering agents.<n>SWE-Master systematically explores the complete agent development pipeline, including teacher-trajectory synthesis and data curation.<n>We evaluate SWE-Master on SWE-bench Verified, a standard benchmark for realistic software engineering tasks.
  arXiv  Detail & Related papers  (2026-02-03T11:38:48Z)
• SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving [44.2496723329337]
  SWE-Lego is a supervised fine-tuning (SFT) recipe designed to achieve state-ofthe-art performance in software engineering (SWE) issue resolving.<n>SWE-Lego comprises three core building blocks, with key findings summarized as follows.
  arXiv  Detail & Related papers  (2026-01-04T08:07:27Z)
• SWE-RM: Execution-free Feedback For Software Engineering Agents [61.86380395896069]
  Execution-based feedback is widely used in the development of coding agents through test-time scaling (TTS) and reinforcement learning (RL)<n>In contrast, execution-free feedback from reward models can provide more fine-grained signals without depending on unit test cases.<n>We introduce SWE-RM, an accurate and robust reward model adopting a mixture-of-experts architecture with 30B total parameters and 3B activated during inference.
  arXiv  Detail & Related papers  (2025-12-26T08:26:18Z)
• Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs [19.766885088032932]
  Software engineering (SWE) has emerged as a crucial testbed for next-generation LLM agents.<n>Most existing datasets are limited to only a few thousand GitHub-sourced instances.<n>We propose an incremental, automated data-curation pipeline that systematically scales both the volume and diversity of SWE datasets.
  arXiv  Detail & Related papers  (2025-06-24T03:53:36Z)
• R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents [32.06393076572057]
  AgentGym is the largest procedurally-curated executable gym environment for training real-world SWE-agents.<n>It is powered by two main contributions: SYNGEN, a synthetic data curation recipe, and Hybrid Test-time Scaling.<n>Overall, our approach achieves 51% on the SWE-Bench Verified benchmark, reflecting a new state-of-the-art for open-weight SWE-agents.
  arXiv  Detail & Related papers  (2025-04-09T17:55:19Z)
• Training Software Engineering Agents and Verifiers with SWE-Gym [89.55822534364727]
  SWE-Gym is the first environment for training real-world software engineering (SWE) agents.<n>SWE-Gym contains 2,438 real-world Python task instances.<n>We use SWE-Gym to train language model based SWE agents, achieving up to 19% absolute gains in resolve rate.
  arXiv  Detail & Related papers  (2024-12-30T18:15:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.