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. Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests

    Jun 5, 2026Thanawat Lodkaew, Johannes Ackermann, Soichiro Nishimori +3Reward HackingCoding Agents

  2. Handoff Debt: The Rediscovery Cost When Coding Agents Take Over Interrupted Tasks

    Jun 1, 2026Dipesh KC, Anjila BudathokiCoding AgentsSoftware Engineering Benchmarks

  3. How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions

    May 28, 2026Ningzhi Tang, Chaoran Chen, Gelei Xu +5Agent Failure AnalysisCoding Agents

  4. SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents

    May 27, 2026Yubin Qu, Yi Liu, Gelei Deng +4Coding AgentsAI Agent Security

  5. CODESKILL: Learning Self-Evolving Skills for Coding Agents

    May 25, 2026Yanzhou Li, Yiran Zhang, Xiaoyu Zhang +2Coding AgentsLLM Agent Skill Learning

  6. Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks

    May 18, 2026Yubin Qu, Ying Zhang, Yanjun Zhang +4Tool Access Control for LLM AgentsComputer-Use Agent Benchmarks

  7. Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning

    May 14, 2026Jingjing Wang, Xiwen Chen, Wenhui Zhu +6LLM PruningAI Coding Agents

  8. SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution

    May 8, 2026Mohit Raghavendra, Soham Dan, Miguel Romero Calvo +12Coding AgentsSoftware Engineering Benchmarks

  9. Agentic Coding Needs Proactivity, Not Just Autonomy

    May 7, 2026Nghi D. Q. Bui, Georgios EvangelopoulosProactive AgentsAI Coding Agents

  10. Can Coding Agents Reproduce Findings in Computational Materials Science?

    May 1, 2026Ziyang Huang, Yi Cao, Ali K. Shargh +15Coding AgentsAI Agent Benchmarks

  11. How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks

    Apr 24, 2026Longju Bai, Zhemin Huang, Xingyao Wang +5Coding AgentsCost-Aware Inference

  12. SWE-chat: Coding Agent Interactions From Real Users in the Wild

    Apr 22, 2026Joachim Baumann, Vishakh Padmakumar, Xiang Li +3Coding AgentsHuman-AI Collaboration

  13. Can Coding Agents Be General Agents?

    Apr 10, 2026Maksim Ivanov, Abhijay Rana, Gokul PrabhakaranCoding AgentsBusiness Process Automation

  14. Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time

    Apr 1, 2026Razvan Mihai Popescu, David Gros, Andrei Botocan +3Mining Software RepositoriesCoding Agents

  15. Coding Agents are Effective Long-Context Processors

    Mar 20, 2026Weili Cao, Xunjian Yin, Bhuwan Dhingra +1Long-Context InferenceCoding Agents

  16. Wink: Recovering from Misbehaviors in Coding Agents

    Feb 19, 2026Rahul Nanda, Chandra Maddila, Smriti Jha +3LLM Agent ReliabilityAgent Reliability

  17. Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?

    Feb 12, 2026Thibaud Gloaguen, Niels Mündler-Sasahara, Mark Niklas Müller +2AI Coding AgentsCoding Agents