SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents

arXiv:2609.04167 · cs.SE, cs.AI · Submitted 2026-09-03 · Read on arXiv

cs.SE, cs.AI

Submitted: 2026-09-03

Updated: 2026-09-03

Comments: 11 pages, 2 figures, 5 tables

Code: https://github.com/DeepSoftwareAnalytics/SWE-Gate

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 39× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Generalization — 4× in this paper · explained in 13 episodes
• International Conference on Software Engineering — 3× in this paper
• Provenance — 3× in this paper · explained in 4 episodes
• Transferability — 3× in this paper · explained in 4 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Functional Success Rate — 2× in this paper
• Joint Success Rate — 2× in this paper
• AI Agents — 1× in this paper · explained in 2 episodes
• Constraint Following Rate — 1× in this paper
• Continual Learning — 1× in this paper · explained in 2 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Core — 1× in this paper · explained in 2 episodes
• Evaluation Dimensions — 1× in this paper · explained in 3 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• CoCoSum: Contextual Code Summarization with Multi-Relational Graph Neural Network
• What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond
• PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents
• RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation
• HumanEvo: An Evolution-aware Benchmark for More Realistic Evaluation of Repository-level Code Generation
• Knowledge Matters: Injecting Project and Testing Knowledge into LLM-based Unit Test Generation
• Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties