Software Engineering Agents

Overview

Software engineering agents use language models to work on tasks such as fixing repository issues, writing tests, building projects, reviewing code, and modernizing software. Common approaches combine planning and code retrieval with tools that run builds and tests; other systems use multiple specialized agents, repository memory, reinforcement learning, or formal verification. Performance is often evaluated on repository-level benchmarks such as SWE-bench, alongside terminal tasks and real-world settings that test build success, design constraints, and behavior over multiple steps. Agents can solve many tasks, but dependable performance remains difficult: passing tests may not mean a patch follows project intent, and greater autonomy or more agents can increase cost, regressions, and oversight demands.

Latest papers

CardsList

380 papers45 papers in the last four weeks, down 34% on the four weeks before. 0.3% of all new papers.

  1. Moving Generality from Model to Modeler: LLM Agents for PHM on a Deployment-Style Benchmark

    Nov 18, 2026Zhenling Chen, Zhiguo Zeng, Anne BarrosLLM Agent EvaluationAI Agent Benchmarks

  2. Metrics-in-the-Loop: Complexity Feedback Reshapes Agent-Written Code

    Nov 18, 2026Nicolas Chapados, Jean-François Gagné, Nouha DziriSoftware EngineeringSoftware Engineering Agents

  3. Agent Trajectories as Evidence for Software Quality Assurance

    Nov 17, 2026Jonathan Ullrich, Julien Siebert, Michael Kläs +2Software EngineeringAgent Trajectory Analysis

  4. When the World Is the Test Suite: Agentic Intelligence for the Physical World

    Nov 17, 2026Kaixin Li, Meng Luo, Yanlin Li +9Agentic AI for RoboticsAgent Evaluation

  5. EmbedGym: Letting Coding Agents Develop and Debug Embedded Firmware Without Physical Hardware

    Nov 16, 2026Minghui Zhao, Yiming Li, Sophie Zhu +5Software Engineering AgentsCoding Agent Benchmarks

  6. Revisiting the Survival of Agent-Attributed Code: How Measurement Choices Decide the Verdict

    Nov 16, 2026Musfiqur Rahman, Mahi Begoug, Emad ShihabAI Coding AgentsSoftware Engineering Agents

  7. From Repositories to Training Environments: Scaling Long-Horizon Coding Agents with Environment Evolution Loop

    Nov 16, 2026Yang Tian, Tianyu Zheng, Xiyuan Yang +5LLM Agent TrainingSoftware Engineering Agents

  8. SWE-OPD: On-Policy Distillation for Agentic Coding

    Nov 16, 2026Yuhang He, Yanyu Chen, Chuanzhe Guo +11LLM Agent TrainingOn-Policy Distillation

  9. Re-Reading Is Not Free: Token Traces and Cache-Aware Energy Estimation for LLM Agents in Software Engineering

    Nov 16, 2026Tina Vartziotis, Ketevan Peranidze, Rodopi Kosteli +5Energy-Aware LLM InferenceSoftware Engineering Agents

  10. Inquest: Log-Guided Root-Cause Code Localization with a Staged Agent

    Nov 14, 2026Yuvraj Sehgal, Sneh Patel, Mahsa Panahandeh +1Software EngineeringRoot Cause Analysis

  11. CLEW: Log-Anchored Backward Tracing for Root-Cause Code Localization

    Nov 14, 2026Wenji Bai, Muhammad Waseem, Jaakko Peltonen +1Fault LocalizationRoot Cause Analysis

  12. Beyond Clumsy Agentic Tool Calling: How Cueing and Spotting Make the Difference

    Nov 14, 2026Xindi Yang, Yan Liu, Jiajun SunTool-Using AgentsLLM Agents

  13. When the Mythical Man-Month Meets Agentic Web Systems: Structured Coordination for Scalable Development

    Nov 14, 2026Zhiyao Wu, Zi Liang, Haibo HuMulti-Agent CoordinationMulti-Agent Orchestration

  14. Robo-SWE: An Executable Issue-Resolution Dataset Mined from Robot Software Repositories

    Nov 11, 2026Vahid Haratian, Vahid Ansari, Mohammadhossein Malmir +1Software Engineering BenchmarksSoftware Engineering Agents

  15. Bug Finding With Agentic Symbolic Execution

    Nov 11, 2026George Granberry, Wolfgang Ahrendt, Andy Gordon +1Automated Software TestingSoftware Engineering Agents

  16. Mach2: Scientific Discovery Platform with Deterministic Execution Constraints

    Nov 10, 2026Vansh Sharma, Venkat RamanLLM Agent OrchestrationRuntime Enforcement for AI Agents

  17. EngineAgent: Agentizing On-Device LLM Inference Engines with Inference Stack Hierarchy Awareness and Hardware Abilities

    Nov 10, 2026Zhengxiang Huang, Yujie Sun, Shengheng Chen +6On-Device Language Model InferenceLLM Inference

  18. Repository-Context-Guided Image Understanding for Agentic Software Development

    Nov 9, 2026Fumiki Yohena, Toshiaki Sota, Shota Suzuki +2Software Engineering AgentsFault Localization

  19. NINJA: A Navigator-Inspector Joint Architecture for Context-Efficient Issue Localization

    Nov 5, 2026Wenkai Fang, Shunyu Liu, Wei Luo +8Software Engineering AgentsSoftware Engineering

  20. Getting a Grip: Operating Human-Agent Software Teams Through Governed Messages

    Oct 31, 2026Michael Granitzer, Kanishka Ghosh Dastidar, Andreas Einwiller +2Multi-Agent GovernanceHuman-AI Collaboration

  21. Agentic process evidence

    Oct 29, 2026Yuval Kainan, Carmit HershmanAI Agent GovernanceAI Agent Auditing