alphaXiv launches autoarxiv, letting users run automated AI agent reproductions of arXiv papers by changing the URL · Digg
/Tech5d ago
alphaXiv launches autoarxiv, letting users run automated AI agent reproductions of arXiv papers by changing the URL
- The service resolves software dependencies and estimates reproduction costs
--0--<br>*]:-ml-2 flex max-w-full flex-wrap gap-y-2 z-0">svg]:pointer-events-none [&>svg]:size-3! hover:bg-muted hover:text-muted-foreground dark:hover:bg-muted/50 z-10 h-auto overflow-visible rounded-full p-0 gap-0 border-transparent bg-transparent transition-colors duration-150 ease-out absolute left-0 top-0" data-state="closed">CT#542|@CHENHAOTAN<br>svg]:pointer-events-none [&>svg]:size-3! hover:bg-muted hover:text-muted-foreground dark:hover:bg-muted/50 z-10 h-auto overflow-visible rounded-full p-0 gap-0 border-transparent bg-transparent transition-colors duration-150 ease-out absolute left-0 top-0" data-state="closed">CL#468|@CHENGLEISI<br>svg]:pointer-events-none [&>svg]:size-3! hover:bg-muted hover:text-muted-foreground dark:hover:bg-muted/50 z-10 h-auto overflow-visible rounded-full p-0 gap-0 border-transparent bg-transparent transition-colors duration-150 ease-out absolute left-0 top-0" data-state="closed">DE#274|@DEEDYDAS<br>svg]:pointer-events-none [&>svg]:size-3! hover:bg-muted hover:text-muted-foreground dark:hover:bg-muted/50 z-10 h-auto overflow-visible rounded-full p-0 gap-0 border-transparent bg-transparent transition-colors duration-150 ease-out absolute left-0 top-0 avatar-stack-chip-bg ring-2 ring-background" data-state="closed">GN#89|@GNEUBIG
Original post
Chenhao Tan@ChenhaoTan#542in/Tech
This is very cool. We have been building something similar. Cool to see what it could look like!
alphaXiv@askalphaxiv
Introducing paper replications for arXiv<br>Research codebases are notoriously hard to set up<br>We deploy autoresearch agents to ingest popular arXiv repos, resolve setup issues, and get the core claim running. You can now sort papers by ease of implementation 🚀
9:40 AM · Jun 17, 2026 · 4.8K Views
Sentiment
Users are excited about AI agents like AutoArxiv and AlphaXiv that automatically replicate arXiv papers because they view the automation as impressive work advancing accessible science.<br>Pos<br>100.0%
Neg<br>0.0%
23 comments with sentiment.View comments
Cluster Engagement
Views
Comments
Reposts
Bookmarks
Expand data
Digg Deeper<br>Ask Question<br>No Digg Deeper questions have been answered for this story yet.
Posts from X<br>Most ActivityMost ActivityTimeline
VIEWS177.3KBOOKMARKS1KLIKES1.1KRETWEETS71REPLIES18<br>Deedy@deedydas
Pretty neat that with one URL change, you can now replicate and iterate on AI papers without having to even provision your own GPUs
alphaXiv@askalphaxiv
Introducing autoresearch for arXiv papers<br>Change 'arxiv' to 'autoarxiv' in any paper URL<br>An agent deploys to resolve setup issues on the codebase, run a minimal reproduction, and estimate full replication cost. Read more below
4d|Views 177.3KLikes 1.1KBookmarks 1K
Graham Neubig@gneubig
This is very cool! I have tried to have auto research agents reimplement my own papers to check whether the implementation was solid, but it's great to see alphaXiv deploy it generally
alphaXiv@askalphaxiv
Introducing paper replications for arXiv<br>Research codebases are notoriously hard to set up<br>We deploy autoresearch agents to ingest popular arXiv repos, resolve setup issues, and get the core claim running. You can now sort papers by ease of implementation 🚀
5d|Views 13.3KLikes 65Bookmarks 26
alphaXiv@askalphaxiv
4/N To try it out change the url of any CS arxiv paper from ‘http://arxiv.org (http://arxiv.org/)’ -> ‘http://autoarxiv.org (http://autoarxiv.org/)’ You can also try it out on a private codebase by visiting http://openresearch.sh (http://openresearch.sh/)
4d|Views 6.5KLikes 40Bookmarks 31
alphaXiv@askalphaxiv
1/N Model capabilities today are subpar for end-to-end autonomous research, what we would categorize as the ability to make “novel discoveries”. However, in our experimentation, research agents have proven to be an excellent way to resolve implementation issues and carry out reproductions of academic works.
4d|Views 12.3KLikes 55Bookmarks 6
Dani Alami@Daniel_Alami
Really cool @askalphaxiv<br>Check my repo out, it’s autoresearch inspired: https://github.com/sparckix/ztare<br>It’s a zero-trust adversarial kernel for validating claims/outputs - with an LLM cheating catalog, deterministic gates, ledgers, and org primitives and a battery of tools to carry out experiments.<br>Could be useful to harden agent reproductions against gaming or make outputs more auditable. Fully open source.<br>Happy to share specifics or discuss if any parts are reusable!!
4d|Views 2.4KLikes 13Bookmarks 11
alphaXiv@askalphaxiv
Introducing autoresearch for arXiv papers<br>Change 'arxiv' to 'autoarxiv' in any paper URL<br>An agent deploys to resolve setup issues on the codebase, run a minimal reproduction, and estimate full...