Overview

Coding agents are language-model systems that inspect repositories, edit files, run commands and tests, and iterate toward software goals, sometimes coordinating subagents or asking users for clarification. Common approaches combine planning and tool-use harnesses with context management, retrieval or memory, reusable skills, and execution feedback; training methods include supervised trajectories and reinforcement learning. Evaluation has expanded from issue-fixing suites such as SWE-bench to interactive, long-horizon repository work, testing and refactoring, scientific software, and real developer sessions, measuring cost, process, policy compliance, and maintainability alongside correctness. A central challenge is making agents dependable beyond passing tests: they must preserve evolving specifications, avoid out-of-scope actions, produce maintainable changes, and collaborate transparently, while outcomes also depend on the model, tools, and harness.

Latest papers

CardsList

151 papers26 papers in the last four weeks, down 28% on the four weeks before. 0.2% of all new papers.

  1. GHAgentCI: A Dataset of Coding-Agent Invocations in CI Workflow Histories

    Nov 11, 2026Daniel Ogenrwot, Jorge Gonzalo Delgado Cervantes, Woojoong Kim +1Agentic WorkflowsCoding Agents

  2. Breaking Bad: "Going Badly" Activations Drive Reward Hacking

    Nov 11, 2026Natalia Fischl-Lanzoni, Punya Syon Pandey, Merlin Stein +1Reward HackingCoding Agents

  3. When Instruction Files Go Stale: Documentation Debt and Hidden Cost in Coding Agents

    Nov 6, 2026Tural Mehtiyev, Biruk Tadesse, Lawrence Arkoh +1AI Coding AgentsCoding Agents

  4. A Controlled Study of Models, Skills, Feedback, and Curriculum in Agentic Robotics

    Nov 6, 2026Kaiyuan Chen, Xinyue Zhu, Shuangyu Xie +7Agentic AI for RoboticsCoding Agents

  5. PersonaCodeBench: Evaluating Coding Agents in Persona-driven Human-Interactive Sessions

    Nov 3, 2026Haixin Wang, Jianheng Hou, Hongyu Shen +27Coding AgentsAI Agent Evaluation

  6. Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks?

    Nov 1, 2026Shuochen Chang, Qianli Ma, Yibo Miao +7Coding AgentsCoding Agent Benchmarks

  7. Precedent or Intent? What Coding Agents Follow When Evolving Existing Code

    Oct 28, 2026Haichao Zhu, Geyang Xu, Zhaorui Yang +2AI Coding AgentsCoding Agents

  8. Generation and Verification: Human-Agent Collaboration for Safety-Critical Automotive Software Engineering

    Oct 26, 2026Elizaveta Zinovyeva, Aiham Taleb, Nikita Kozodoi +5AI-Assisted Software DevelopmentCoding Agents

  9. SWE-Shift: Evaluating Coding Agents in Evolving Workspaces

    Oct 23, 2026Victor Shea-Jay Huang, Rongqing Li, Zhangyue Yin +7Coding AgentsSoftware Engineering Benchmarks

  10. SWE-Clar: Can Coding Agents Clarify Incomplete Client Requirements and Deliver Greenfield Software?

    Oct 22, 2026Jialei Li, Dingxian Wang, Xiaoyan Zhao +11Coding AgentsSoftware Engineering Benchmarks

  11. Adaptive Skill Granularity for Coding Agents: Runtime Routing and Macro-to-Micro Recovery

    Oct 22, 2026Dingxuan Zhang, Yanhui Jiang, Jun Wang +1Coding AgentsLLM Agent Workflow Optimization

  12. SWE-VERIFIER: Selective Verification for Cost-Efficient Coding Agents

    Oct 21, 2026Kaijian Zou, Vaibhav Chennareddy, Yunxiang Zhang +5Coding AgentsLLM Agent Verification

  13. SWE-DIVE: Multi-Turn Coding Agent Evaluation with Dynamic User Simulation

    Oct 21, 2026Lorenz Brehme, Benjamin Steenhoek, Ruth BreuCoding AgentsAI Agent Evaluation

  14. PAUSE: Search-Free Steering of Coding Agents Before Their First Source-Code Edit

    Oct 21, 2026Viral Patel, Boyin Tan, Jason Xue +1Coding AgentsLLM Agent Workflow Optimization

  15. GenXR-Bench: Benchmarking Coding Agents for Interactive XR Development

    Oct 21, 2026William Huang, David Li, Xiang 'Anthony' Chen +13Code Generation BenchmarksCoding Agents

  16. From Code Generator to Engineering Companion: A Plant-aware Agent for PLC Programming

    Oct 20, 2026Joschka Kersting, Gesa BenndorfCoding AgentsCode Generation

  17. TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents

    Oct 15, 2026Aaron J. Li, Weijia Xu, Chandan Singh +8Token EfficiencyCoding Agents

  18. Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents

    Oct 14, 2026Yuyao Ge, Shenghua Liu, Peizhong Gao +8LLM Agent HarnessesAI Agent Benchmarks

  19. JevCoder: When Does Decision Delegation Pay Off in Code Repair?

    Oct 14, 2026Jiahao Zhang, Yifan Zhang, Yu HuangAutomated Program RepairCoding Agents

  20. How Far Can Coding Agents Go in Visual Generation?

    Oct 13, 2026Hengguang Zhou, Yuanhao Ban, Jiaqi Feng +3Agentic Image GenerationCoding Agents

  21. The Last Mile of Coding Agents for Long-Document Tasks: An Empirical Study on Clinical Trial Protocol Digitization

    Oct 13, 2026Jiacheng Lin, Geoffrey Low, Nishit Agarwal +4Coding AgentsDocument Information Extraction