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.

Soei: Structured Observability of Evidence and Intent for Multi-Agent AI Software Engineering
Oct 29, 2026Mohammed Nayeem Khan, K S Sarun KumarAI Agent Monitoring AI Coding Agents
Intel Corporation
Precedent or Intent? What Coding Agents Follow When Evolving Existing Code
Oct 28, 2026Haichao Zhu, Geyang Xu, Zhaorui Yang +2AI Coding Agents Coding Agents
Independent Researcher · University of California, Riverside · Tulane University
M4Bench: Evaluating Procedural Specification for Clinical EHR Derivation Agents
Oct 27, 2026Hannes Ill, Rafi Al Attrach, Rajna Fani +5Coding Agent Benchmarks AI Coding Agents
Laboratory for Computational Physiology, Massachusetts Institute of Technology, USA · Department of Surgery, Seoul National University Hospital, Korea · Charité, University Medicine Berlin, Germany +2
InfraDev: Can Coding Agents Develop AI Infrastructure, and How Can We Tell?
Oct 27, 2026Yangshen Deng, Jiaqi Ruan, Yeqi Huang +3AI Coding Agents Coding Agent Benchmarks
University of Edinburgh · Tencent Hunyuan
Agent or Human? Detecting Commits by AI Coding Agents in the Absence of Authorship Signatures
Oct 26, 2026Kosei Horikawa, Hao Li, Yutaro Kashiwa +5Authorship Attribution AI Coding Agents
Nara Institute of Science and Technology, Ikoma, Japan · Queen’s University, Kingston, Canada · École de technologie supérieure - Québec University, Montréal, Canada
Do Coding Agents Still Need a Debugger? Frontier-Model-Based Fault Localization at the Accuracy Ceiling
Oct 26, 2026Christoph Daxerer, Johann Glock, Christian Macho +3AI Coding Agents Software Engineering
Software Competence Center Hagenberg GmbH (SCCH), Hagenberg, Austria · Department of Informatics Systems, University of Klagenfurt, Klagenfurt, Austria · School of Informatics, Communications and Media, University of Applied Sciences Upper Austria, Hagenberg, Austria
PROBE: Frontier Coding Agents Find Different Bugs Than Maintainers Fix
Oct 26, 2026Marco Paina, Mark Niklas Müller, Niels Mündler-Sasahara +1AI Coding Agents Coding Agent Benchmarks
ETH Zurich
NameTrap: Steering AI Coding Agents Toward Security Vulnerabilities via Variable Names
Oct 25, 2026Chieh-Yuan Chang, Guan-Wei Chen, Chia-Yi Hsu +3AI Agent Security Data Poisoning Attacks
National Yang Ming Chiao Tung University, Taiwan
How Do Small Coding Agents Use Code Graphs and Embeddings?
Oct 25, 2026Saurav BellamAI Coding Agents Code Localization
The University of Texas at Austin
Can AI Agents Help Robotic Engineers? Lessons from Two Focus Days in Industry
Oct 23, 2026Salim Fares, Steffen HerboldAI Coding Agents Software Engineering Agents
University of Passau Passau, Germany
Knowing When to Stop: The Evidence-Action Gap in Coding Agents
Oct 22, 2026Tianyu Chen, Xinran Zhao, Vijay Viswanathan +3AI Coding Agents Process-Based Agent Evaluation
The University of Texas at Austin · Carnegie Mellon University · The University of North Carolina at Chapel Hill
VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team
Oct 22, 2026Wenbo Hu, Ken Li, Jiazhe Wei +13AI Coding Agents Multi-Agent LLM Systems
PRLab, Nanjing University · S-Lab, Nanyang Technological University
BrickWright: Agentic Creation of Physically Feasible Brick Builds
Oct 22, 2026Ava Pun, Kevin Dai, Sally Chen +73D Asset Generation AI Coding Agents
Carnegie Mellon University · Independent Researcher · Stanford University
IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems
Oct 22, 2026A. Jian Yang, An Huang, Bo Dan +174LLM Agent Training AI Coding Agents
What Open-Source Projects Tell Their Coding Agents: A Census of AGENTS.md and CLAUDE.md
Oct 22, 2026Pawel ZarzyckiAI Coding Agents AI Use Disclosure
What the Specification Did Not Say: Specification-Oracle Gaps in Test-Graded Coding-Agent Benchmarks
Oct 22, 2026Fei DingSoftware Engineering Benchmarks Benchmark Auditing
Alibaba Group
Back Up Before You Regret: Measuring Backup Awareness and Automating Backup in Coding Agents
Oct 20, 2026Xu Li, Simon Yu, Minzhou Pan +4AI Coding Agents Tool-Using Agents
Northeastern University · University of California, Berkeley · University of Chicago +1
Unsupervised Tool Evolution for Coding Agents in Data-Lake Analytics
Oct 19, 2026Yuqing Yang, Yurong Liu, Deqing Fu +5AI Coding Agents LLM Agent Self-Improvement
University of Southern California · Google · New York University
When Coding Agents Outpace Review: Evaluating PRD-Driven Development in Mature Enterprise Repositories
Oct 19, 2026Tianqi Liu, Yandong Guan, Songze Li +3AI Coding Agents LLM Agent Evaluation
Zhejiang University · Alibaba Taobao & Tmall Group
SWE-Residual: Evaluating Starting-State Robustness of Coding Agents
Oct 19, 2026Jinze Li, Weijie Liu, Jinfeng Xu +6AI Coding Agents Software Engineering Benchmarks
The University of Hong Kong · The University of British Columbia · University of Tokyo +2
One Skill Takes Over: Clashing Agent Skills and a One-File Fix
Oct 18, 2026Parsa Razmara, Seyedarmin Azizi, Ardalan AryashadAI Coding Agents LLM Agent Skill Evaluation
University of Southern California, Los Angeles, USA
Over-Defense in Coding Agents Begins at Silent Forks
Oct 18, 2026Hanjun Luo, Xuecheng Liu, Xiucheng Zhang +5AI Coding Agents RL for Code Generation
New York University · New York University Abu Dhabi · Carnegie Mellon University +3
Teaching Code Agents to Ask Without Leaking Private Code
Oct 17, 2026Wenjia Jiang, Jieke Shi, Zhensu Sun +9AI Coding Agents Privacy Protection for LLM Agents
Singapore Management University · University of Alberta · Alberta Machine Intelligence Institute (Amii) +6
Cortex: A Fixed-Point Theory of Governed Coding Agents - Technical Report
Oct 16, 2026Marius-Constantin Dinu, Florian ZebaAI Coding Agents AI Agent Governance
Alpha Omega Labs
MetaCurate: Evolving Curation Filters for High-Quality Agentic Coding Data
Oct 16, 2026Donghoon Kim, Seunghyuk Oh, Kevin Galim +6Training Data Curation LLM Agent Training
FuriosaAI · University of California, Berkeley
WebCoder: Scaling General Frontend Development with Artifact-Grounded Agentic Reinforcement Learning
Oct 16, 2026Zijun Dou, Zhen Yang, Xijun Liu +3AI Coding Agents Agentic RL
Tsinghua University · Zhipu AI · Beihang University +1
Self-Evolving Coding Agents via Harness-Policy Optimization
Oct 16, 2026Zhepei Wei, Wenlin Yao, Baolin Peng +5AI Coding Agents Agent Harness Optimization
Microsoft Research · University of Virginia · Carnegie Mellon University
Spatial Memory by Agents, for Agents
Oct 15, 2026Qianwei Wang, Ce Zhang, Zhanpeng Luo +3Robotic Spatial Memory Agent Memory
Qianwei Wang is with Princeton University · Ce Zhang is with Carnegie Mellon University · Zhanpeng Luo is with Johns Hopkins University +2
OPRD: On-Policy Reminder Distillation for Long-Horizon Coding Agents
Oct 15, 2026Yuechen Luo, Zhiyi Lai, Miao Ziqi +9AI Coding Agents LLM Agent Training
Tsinghua University · Independent Researcher · Shanghai Artificial Intelligence Laboratory +1
Mallea: Building, Steering, and Memorizing Worlds with Coding Agent
Oct 15, 2026Xuanyi Liu, Ruiqi Li, Siwei MaCode World Models World Models

Oct 29, 2026J/K move · Enter open · S save

Soei: Structured Observability of Evidence and Intent for Multi-Agent AI Software Engineering

Mohammed Nayeem Khan, K S Sarun Kumar

Intel Corporation

AI Agent Monitoring AI Coding Agents AI Agent Auditing AI Agent Security

Open paper AskPDF arXiv

AI coding agents now do long, multi-step and multi-session software work with little supervision. When a developer comes back to that work, the useful question is not what the model said but what was actually done, by whom, and whether it is finished. We study this in three parts. First, we verify Agenttrail, an open-source local observability tool for coding agents, against its source at commit e4ba2da: nine documented constants and mechanisms hold at file-and-line level, two event pipelines are never unified, and its Map service has an unauthenticated local mutation surface. Second, we run a prototype of our system on 45 real coding-agent sessions (102,233 records, 20,577 tool executions, 2,336 human-to-agent episodes). With a blind-audited classifier (precision 83.3% and 96.7%) we estimate that 23.4% (95% CI 17.1 to 35.7) of code-editing episodes end with no independent check after the last edit, and that 57.8% of to-dos the agent marked complete after editing had no proof in between. A 10-minute timing heuristic for session hand-offs recovers 6 of the 24 session pairs that content lineage links. 42% of sessions run longer than 24 hours, 48.1% of transcript bytes lie past a 2 MiB replay bound, and 1,326 records in 16 sessions contain credential-like strings. Third, we propose Soei (Structured Observability of Evidence and Intent): an acknowledgement-aware event schema, a hash-chained local ledger, a W3C PROV-aligned graph, calibrated inference for attribution and lineage, and a verification layer that keeps a claim of completion apart from proof. On the same corpus the ledger is 20% of raw size, holds no content or credentials, verifies at about 126k events/s, detects tampering and replays deterministically. We position the work against concurrent 2026 proposals and define autonomy levels with evidence gates and harness metrics baselined on our data.