tool · first seen 6 Oct 2026
agentic coding tools
Also: agentic coding, autonomous coding, agentic development, agentic software development
Autonomous coding assistants that plan and execute multi-step edits in software projects.
Agentic coding tools are assistants such as Claude Code and Codex that plan and carry out multi-step edits across a codebase, running commands and tests rather than only completing snippets. The sources show the term used as settled vocabulary, not as a new idea. Papers build on it: a multi-agent judgement workflow with cross-vendor reviewers, spec-driven property-based testing for agent-written code, a Blender 4D scene benchmark, predicting post-training coding-agent performance from base models, and a dashboard for tracking parallel agent projects. Hacker News posts cover hobby projects built with Claude Code, an open-weight model release, a survey of agent setups, and an agent deleting a user's files.
The research focus has moved from whether agents can write code to how their output is verified, reviewed, and contained. Testing, review workflows, and safe-rollback tooling are where follow-on work is likely to concentrate.
Analyst note (established), 17 Nov 2026.
Mentions per week
PapersCodeDiscussion
Rank 63 on 14 Nov 2026 · 16 mentions in 28 days · 16 independent groups · papers → discussion → code · first seen 6 weeks ago · acceleration +0.22
Earliest sources
- Humanize: Judgement Engineering for Agentic CodingPapers · 6 Oct 2026 · Sihao Liu, Ligeng Zhu, Zijian Zhang, Dongyun Zou, Zhengyang Zhang, Changye Li, S…
- Designing Collaborative AI-Driven Workflows for Scientific Software EngineeringPapers · 7 Oct 2026 · Akash Dhruv, Max Knobbe, Pedro Machado, Anshu Dubey
- Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base ModelsPapers · 7 Oct 2026 · Tan Yu, Alexander Bukharin, Khushi Bhardwaj, Jennifer Williams, Zirui Liu, Jonat…
- I think I found a planet nobody knew existed. I used Claude Code to find itDiscussion · 8 Oct 2026 · pyduan · 302 points
- VulnBump: A Benchmark for Fixing Vulnerable Dependencies in Real Projects While Keeping the Build and Tests GreenPapers · 12 Oct 2026 · Gabija Pasiunaite, Ryan McMorrow, Brian Clark, Liran Tal, Luke Tu
- Priming Base Models for Agentic Post-Training: An Open Midtraining RecipePapers · 15 Oct 2026 · Soumye Singhal, Joseph Jennings, Ka Shun Shum, Alexander Bukharin, Khushi Bhardw…
Latest sources
- ernie-research/SWE-OPDCode · 16 Nov 2026 · ernie-research · 13 stars
- SWE-OPD: On-Policy Distillation for Agentic CodingPapers · 16 Nov 2026 · Yuhang He, Yanyu Chen, Chuanzhe Guo, Jie Zhu, Zichen Tian, Hongyu Ge, Zixuan Ren…
- Claude asked to renumber pages deletes professor's syllabus, year of notesDiscussion · 14 Nov 2026 · gnabgib · 51 points
- AWS Emulator and the engineer's job when agents write the codeDiscussion · 11 Nov 2026 · drbm · 111 points
- Spec-Driven PBT: Deriving Semantic Invariants from Code Specifications for Agentic Property-based TestingPapers · 11 Nov 2026 · Aditya Shukla, Kartik Gupta, Ali Alavi, Pashootan Vaezipoor
- VibePrevisBench: Evaluating Agentic Coding for 4D Scene Generation in BlenderPapers · 11 Nov 2026 · Yuzhe Chen, Muxi Diao, Lele Yang, Wenbin Xu, Xuyang Liu, Qile Su, Changyi Liu, J…
- Project Progress Desk: Know Where All Your Claude Code and Codex Projects Stand at a GlancePapers · 9 Nov 2026 · Wanghao Ye, Yiting Wang, Shwai He, Guoheng Sun, Ziyao Wang, Yexiao He, Zheyu She…
- AI coding agent setups from 663 Hacker News commentsDiscussion · 6 Nov 2026 · titusblair · 30 points
- Ripple-65B Preview: U.S. Open-Weight SOTA on Agentic CodingDiscussion · 4 Nov 2026 · Philpax · 343 points
- mrdoob/codevember-2026Code · 3 Nov 2026 · mrdoob · 84 stars
- CYWang735/Video-CoderCode · 2 Nov 2026 · CYWang735 · 73 stars
- DiplomatHearth/roblox-ai-place-diffCode · 30 Oct 2026 · DiplomatHearth · 156 stars