AI Coding Agents

Follow this topic Ask about this topic

AI coding agents study how language models can work with repositories and development tools to carry out tasks such as fixing bugs, adding features, and building software. Common approaches combine planning and tool use with repository search, structured code editing, reusable skills or memory, and feedback from tests or execution. Benchmarks such as SWE-bench and Terminal-Bench measure issue resolution and command-line work, while newer evaluations test long-running, multi-file changes and behavior in real applications. Agents can solve many coding tasks, but success varies with the model, harness, and task; passing functional tests still does not guarantee secure, maintainable, or specification-faithful software, so reliable verification and effective human oversight remain open challenges.

Latest papers

329 papers62 papers in the last four weeks, up 130% on the four weeks before. 0.4% of all new papers.

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
May 18, 2026Hongyi Liu, Haoyan Yang, Tao Jiang +4AI Coding Agents LLM Agent Skill Learning
1MemTensor (Shanghai) Technology · 2Harbin Institute of Technology · 3Soochow University +1
ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents
May 18, 2026Jiawei He, Jie Jia, Chenbo Liu +4AI Coding Agents LLM Agent Evaluation
Amap, Alibaba Group
WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games
May 17, 2026Wenyu Zhang, Guoliang You, Tianlun +8Web Application Generation AI Coding Agents
1Baidu · University of Science and Technology of China
SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering
May 17, 2026Qingnan Ren, Shun Zou, Shiting Huang +11Software Engineering AI Coding Agents
University of Science and Technology of China · 2AMAP, Alibaba Group
1GC-7RC: One Graphic Card -- Seven Research Challenges! How Good Are AI Agents at Doing Your Job?
May 16, 2026Robin-Nico Kampa, Fabian Deuser, Anna Bößendörfer +2AI Coding Agents AI Agent Evaluation
University of the Bundeswehr Munich, Munich, Germany
AgentKernelArena: Generalization-Aware Benchmarking of GPU Kernel Optimization Agents
May 16, 2026Sharareh Younesian, Wenwen Ouyang, Sina Rafati +11GPU Kernel Optimization GPU Acceleration
AMD
RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades
May 15, 2026Xinbo Xu, Ruihan Yang, Haiyang Shen +13AI Coding Agents Software Engineering Benchmarks
UniPat AI · Peking University · Fudan University +4
Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning
May 14, 2026Jingjing Wang, Xiwen Chen, Wenhui Zhu +6LLM Pruning AI Coding Agents
Clemson University · Morgan Stanley · Arizona State University +1
Orchard: An Open-Source Agentic Modeling Framework
May 14, 2026Baolin Peng, Wenlin Yao, Qianhui Wu +11AI Coding Agents Computer-Use Agents
Microsoft Research · Columbia University · UIUC
Evaluating Memory Condensation Strategies for Coding Agents in Data-Driven Scientific Discovery
May 13, 2026Renuka Chintalapati, Sid Raskar, Anurag Acharya +3AI Coding Agents AI Agent Benchmarks
Pacific Northwest National Laboratory · National Laboratory of the Rockies
Neurodata Without Boredom: Benchmarking Agentic AI for Data Reuse
May 12, 2026Ling-Qi Zhang, Kristin BransonAI Coding Agents AI Agent Benchmarks
HHMI Janelia Research Campus, Ashburn, VA 20147
gwBenchmarks: Stress-Testing LLM Agents on High-Precision Gravitational Wave Astronomy
May 11, 2026Tousif Islam, Digvijay Wadekar, Zihan ZhouGravitational-Wave Astronomy AI Coding Agents
Kavli Institute for Theoretical Physics, University of California Santa Barbara, Kohn Hall, Lagoon Rd, Santa Barbara, CA 93106 · Center for Gravitational Physics, University of Texas at Austin, Austin, TX 78712, USA · Department of Physics, Princeton University, Princeton, NJ 08540, USA
ASIA: an Autonomous System Identification Agent
May 11, 2026Dario Piga, Marco ForgioneAI Coding Agents System Identification
Dalle Molle Institute for Artificial Intelligence (IDSIA), SUPSI, CH Lugano-Viganello, Switzerland
Nautilus Compass: Black-box Persona Drift Detection for Production LLM Agents
May 11, 2026Chunxiao WangAgent Memory AI Agent Reliability
Yiluo Technology Co., Ltd.
SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning
May 10, 2026Haoqiang Kang, Xiaokang Ye, Yuhan Liu +5Embodied Navigation AI Coding Agents
1UC San Diego · 2New York University
LARGER: Lexically Anchored Repository Graph Exploration and Retrieval
May 8, 2026Yuntong Hu, Tongli Su, Liang Zhao +2AI Coding Agents Agentic Retrieval
Emory University
Constraint Decay: The Fragility of LLM Agents in Backend Code Generation
May 7, 2026Francesco Dente, Dario Satriani, Paolo PapottiAI Coding Agents Code Generation
EURECOM, France · University of Basilicata, Italy
VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?
May 7, 2026Keisuke Kamahori, Shihang Li, Simon Peter +1Multi-Agent LLM Systems LLM Serving
University of Washington
TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering
May 7, 2026Yuan Sui, Yulin Chen, Yibo Li +6AI Coding Agents Long-Horizon LLM Agents
National University of Singapore · Peking University · Meta
Intentmaking and Sensemaking: Human Interaction with AI-Guided Mathematical Discovery
May 7, 2026Alex Bäuerle, Adam Connors, Alexander Novikov +5AI for Science AI Coding Agents
Google DeepMind
Agentic Coding Needs Proactivity, Not Just Autonomy
May 7, 2026Nghi D. Q. Bui, Georgios EvangelopoulosProactive Agents AI Coding Agents
Google Labs
Accountable Agents in Software Engineering: An Analysis of Terms of Service and a Research Roadmap
May 6, 2026Christoph TreudeSoftware Engineering AI Accountability
Singapore Management University Singapore, Singapore
MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
May 5, 2026Jonathan Steinberg, Oren GalLanguage Model Safety Evaluation AI Coding Agents
Swarms & AI Lab (SAIL), University of Haifa
Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?
May 4, 2026Spandan Garg, Vikram Nitin, Yufan HuangAI Coding Agents Small Language Models
Microsoft USA
Learning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agents
Apr 30, 2026Mehmet IscanSelective Prediction AI Coding Agents
PythaLab, Yildiz Technical University, Istanbul, Türkiye.
SWE-Edit: Rethinking Code Editing for Efficient SWE-Agent
Apr 28, 2026Yikai Zhang, Jiaxin Pei, Kenan Li +9AI Coding Agents Multi-Agent Coding
1Microsoft, Redmond, Washington, United States · 3Stanford Institute for Human-Centered Artificial Intelligence (HAI), Stanford University · Department of Computer Sciences, University of Wisconsin–Madison
Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
Apr 28, 2026Jiahang Lin, Shichun Liu, Chengjun Pan +8AI Coding Agents Agent Harness Optimization
Fudan University · Shanghai Qiji Zhifeng Co., Ltd · Peking University
Frontier Coding Agents Can Now Implement an AlphaZero Self-Play Machine Learning Pipeline For Connect Four That Performs Comparably to an External Solver
Apr 27, 2026Joshua Sherwood, Ben Aybar, Benjamin KaplanAI Coding Agents AI Agent Evaluation
Department of Computer Science University of Chicago Chicago, IL 60637 · Independent Researcher
Context-Augmented Code Generation: How Product Context Improves AI Coding Agent Decision Compliance by 49%
Apr 27, 2026Drew Dillon, Kasyap VaranasiRetrieval-Augmented Generation AI Coding Agents
Brief
Read the Paper, Write the Code: Agentic Reproduction of Social-Science Results
Apr 23, 2026Benjamin Kohler, David Zollikofer, Johanna Einsiedler +2AI Coding Agents LLM Agent Evaluation
ETH Zurich · University of Basel

May 18, 2026J/K move · Enter open · S save

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

Hongyi Liu, Haoyan Yang, Tao Jiang, Bo Tang+3

1MemTensor (Shanghai) Technology · 2Harbin Institute of Technology · 3Soochow University+1

AI Coding Agents LLM Agent Skill Learning AI Agent Governance

Open paper AskPDF arXiv

Long-horizon LLM agents generate traces that could become reusable experience, but raw trajectories are noisy, local, and hard to govern. Agent Skills offer a structured artifact for combining procedural guidance, executable resources, and applicability boundaries. Yet open skill ecosystems contain redundant, uneven, environment-sensitive artifacts, and indiscriminate updates can pollute future context. We present SkillsVote, a lifecycle-governance framework for Agent Skills across collection, recommendation, attribution, and evolution. SkillsVote profiles a million-scale open source corpus for environment requirements, quality, and verifiability, and synthesizes tasks for verifiable skills. Before execution, it performs agentic library search over structured skill folders to expose instructional context. After execution, it decomposes trajectories into skill-linked subtasks, attributes outcomes to skill-guided execution, agent exploration, environment, and result signals, and admits only successful reusable discoveries to evidence-gated updates. Experiments on Terminal-Bench 2.0 and SWE-Bench Pro show that SkillsVote improves agent performance on challenging agentic coding benchmarks. The gains arise from two complementary pathways: online evolution over task streams at test time and offline transfer via frozen libraries built from either historical trajectories or curated open source skills.