Agentic Software Engineering: Foundational Pillars and a Research Roadmap
cs.SE, cs.AI
Submitted: 2025-09-07
Updated: 2026-11-02
Code: https://github.com/obra/Superpowers11https:
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- SWE-Bench+: Enhanced Coding Benchmark for LLMs
- Hear Your Code Fail, Voice-Assisted Debugging for Python
- SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
- Agent READMEs: An Empirical Study of Context Files for Agentic Coding
- SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
- Continual Learning for Generative AI: From LLMs to MLLMs and Beyond
- Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers
- Towards AI-Native Software Engineering (SE 3.0): A Vision and a Challenge Roadmap
- Agentic Refactoring: An Empirical Study of AI Coding Agents
- Qwen2.5-Coder Technical Report
- The Rise of AI Teammates in Software Engineering (SE) 3.0: How Autonomous Coding Agents Are Reshaping Software Engineering
- AIDev: Studying AI Coding Agents on GitHub
- Do AI Coding Agents Log Like Humans? An Empirical Study
- Watson: A Cognitive Observability Framework for the Reasoning of LLM-Powered Agents
- Context-Aware CodeLLM Eviction for AI-assisted Coding
- Agentic Verification of Software Systems
- Are "Solved Issues" in SWE-bench Really Solved Correctly? An Empirical Study
- SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
- SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving
Related papers
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
- TestPrism: Rethinking Test Evaluation Beyond a Single Reference
- Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- For Coding Agents, the Repository Matters