Building agents to help in research, teaching, learning and academic chores.
Oxford
Joined July 2026
- Tweets21
- Following24
- Followers40
- Likes28
Pinned Tweet
Hello world 👋 Agents4Academia is a community‑led effort to explore and build open‑source agents for academic and research work — by researchers, for researchers.
agents4academia.org/
Agents For Academia retweeted
Paperena evaluates AI scientists over realistic research cycles: writing, reviewing, and revising. It measures factuality, reproducibility, novelty, and community behavior. From @harit_v and @paperena_ai, one of 25+posters at Frontier Data Summit. frontierdatasummit.ai/
Agents For Academia retweeted
Overwhelmed with the number of ICLR submissions and the projected growth to millions of papers in next few years? The paper mill is there, but is it any good? can this be aligned to what we care?
Join us at the Frontier Data Summit to see how @paperena_ai can help.
TL;DR: Paperena is a platform for recording, evaluating and disseminating research primarily done by AI. A home for AI papers and community of AI scientists. More details and initial version coming soon!
There is plenty more charted out. Let's chat and build!
Paperena evaluates AI scientists over realistic research cycles: writing, reviewing, and revising. It measures factuality, reproducibility, novelty, and community behavior. From @harit_v and @paperena_ai, one of 25+posters at Frontier Data Summit. frontierdatasummit.ai/
Agents For Academia retweeted
We have been building @paperena_ai. A platform to power the evaluation layer for science in the AGI era.
Excited to talk about it at the AI scientist summer workshop, today!
I'll be presenting remotely, but don't forget to catch @klarakaleb at the workshop if you are there.
paperena.ai
An incredibly packed room for our morning speakers Nathan Frey @nc_frey from Anthropic and Vivek Natarajan @vivnat from Google DeepMind at the AI Scientist Summer Workshop.
We still have lots of fantastic speakers throughout the day!
Checkout the schedule at ai-scientist-workshop.github…
Agents For Academia retweeted
Exciting and timely workshop! We’ve been exploring many of these questions in the agents4academia.org community and building open-source projects across the academic workflow. Check them out, we’d love to connect and exchange ideas!
Agents For Academia retweeted
Github: github.com/Agents4Academia-A…
Website: agents4academia.org/events/2…
Interest form: forms.gle/iausY6K72XGWAyft5
Agents For Academia retweeted
This is episode 1⃣. Contribute to a project, propose a new one, or run an Agents4Academia event where you are.
Get in touch: @klarakaleb @harit_v @yeewhye
Agents For Academia retweeted
First up a hackathon: 20+ researchers · two weeks · @OxfordStats × @NUSComputing × @NTUsg and tokens on tap by @AnthropicAI .
Outcome: Five open‑source AI agents solving common workflow frustrations across the whole research lifecycle. 🧵
Agents For Academia retweeted
Hello world 👋 Agents4Academia is a community‑led effort to explore and build open‑source agents for academic and research work — by researchers, for researchers.
agents4academia.org/
Agents For Academia retweeted
To see it in action, we ran Prior on our own field — agents for the scientific process.
152 papers · 581 contributions · 989 typed relations · 9 emergent communities (peer review, benchmarks, safety, and more).
The (rough) structure of the field emerged right in front of us.
Agents For Academia retweeted
Then, a graph, not a summary:
2⃣ Contributor — full text → atomic claims with supporting quotes.
3⃣ Cartographer — connects claims across papers into a typed graph (supports · extends · contradicts).
4⃣ Navigator — cited, grounded answers.
Agents For Academia retweeted
1⃣Scoper — open, queryable scholarly data is getting rich enough (thanks to @OpenAlex_org & @SemanticScholar). Prior's first subagent mimics what we do manually — snowball from anchor papers, follow citation trails, chase references. Now automated + structured.
Agents For Academia retweeted
Day 1⃣ of our @agents4academia hackathon, we asked the participants: what are the most frustrating parts of your workflow? Almost every single one: keeping up with the literature. The firehose is impossible. The trust is breaking (👋AI slop). So we built something.
Meet Prior 🧵
First up a hackathon: 20+ researchers · two weeks · @OxfordStats × @NUSComputing × @NTUsg and tokens on tap by @AnthropicAI .
Outcome: Five open‑source AI agents solving common workflow frustrations across the whole research lifecycle. 🧵
This is episode 1⃣. Contribute to a project, propose a new one, or run an Agents4Academia event where you are.
Get in touch: @klarakaleb @harit_v @yeewhye
Github: github.com/Agents4Academia-A…
Website: agents4academia.org/events/2…
Interest form: forms.gle/iausY6K72XGWAyft5