Agentless: Demystifying LLM-based Software Engineering Agents

By Chun Xia, Yinlin Deng, Soren Dunn, Lingming Zhang, Ling-Ming Zhang. arXiv.org, 2024

421 citations recorded by the source corpus.

Recent advancements in large language models (LLMs) have significantly advanced the automation of software development tasks, including code synthesis, program repair, and test generation. More recently, researchers and industry practitioners have developed various autonomous LLM agents to perform end-to-end software development tasks. These agents are equipped with the ability to use tools, run commands, observe feedback from the environment, and plan for future actions. However, the complexity of these agent-based approaches, together with the limited abilities of current LLMs, raises the following question: Do we really have to employ complex autonomous software agents? To attempt to answer this question, we build Agentless -- an agentless approach to automatically solve software development problems. Compared to the verbose and complex setup of agent-based approaches, Agentless employs a simplistic three-phase process of localization, repair, and patch validation, without letting the LLM decide future actions or operate with complex tools. Our results on the popular SWE-bench Lite benchmark show that surprisingly the simplistic Agentless is able to achieve both the highest performance (32.00%, 96 correct fixes) and low cost ($0.70) compared with all existing open-source software agents! Furthermore, we manually classified the problems in SWE-bench Lite and found problems with exact ground truth patch or insufficient/misleading issue descriptions. As such, we construct SWE-bench Lite-S by excluding such problematic issues to perform more rigorous evaluation and comparison. Our work highlights the current overlooked potential of a simple, interpretable technique in autonomous software development. We hope Agentless will help reset the baseline, starting point, and horizon for autonomous software agents, and inspire future work along this crucial direction.

Subfields: Artificial Intelligence, Management Information Systems

View Paper: https://www.semanticscholar.org/paper/ae50c8e255ba55bdbbb05ea470aa63437534438e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Information Systems

1. Sam Dauncey
2. Adam Suma

Citations in the corpus

• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning (2025, positive): “SWE-Bench verified results are obtained via the agentless framework (Xia et al., 2024).”
• A Benchmark for Localizing Code and Non-Code Issues in Software Projects (2025, unknown): “The four approaches show different performance: LocAgent and OpenHands yield the best and comparable results, followed by Agentless and then BM25.”
• Learning Adaptive Parallel Execution for Efficient Code Localization (2026, unknown): “Agentless (Xia et al., 2024) adopts a hierarchical pipeline approach without maintaining agent state across turns.”
• GraphLocator: Graph-Guided Causal Reasoning for Issue Localization (2025, unknown): “The metrics are defined as follows: • Success Location (SL) [6, 45, 49] • F1-Score (F1) provides a harmonic mean of precision and recall, offering a balanced measure that accounts for both under-and over-localization.”
• SpIDER: Spatially Informed Dense Embedding Retrieval for Software Issue Localization (2025, unknown): “In the context of code retrieval, Xia et al. (2024) introduce a simple hierarchical localization strategy driven directly by an LLM, whereas Ouyang et al. (2025) employ an intermediate sparse BM25 retrieval stage to identify relevant files prior to code generation.”