Research / AI Research Agents
arXiv paper introducing ScientistOne, an autonomous research system built around a chain-of-evidence framework to keep claims traceable and audit research outputs for verifiability.
The page clearly describes an AI research system, not just a general paper abstract. The abstract gives enough evidence to understand the product’s purpose, core method, and reported results, including autonomous literature review, solution discovery, paper writing, and integrity checks for citations, scores, and method-code alignment. That is sufficient for a public listing of an AI research agent project.
This snapshot does not show a project website, code repository, demo, or installation details, so a visitor cannot tell how to try the system or whether it is publicly available beyond the paper.
Last evaluated 22 days ago. Current rank #1751. Down 1 spot in the rankings.
Primus is an autonomous AI researcher that hypothesizes, reads papers, writes code, runs experiments on compute, and drafts research papers. The page shows example tasks, published-paper claims, waitlist access, and positioning for ML research workflows.
An interactive dashboard that analyzes New York Times coverage since 2000 using the NYT Archive API, with views for reporters, beats, sections, subjects, geography, obituaries, and corrections.
An open benchmark and leaderboard for AI CAD agents, with 308 prompts across 20 categories and layered scoring for geometry, engineering, manufacturability, and cognition.
A research article from Applied Compute on how agentic, tool-using workloads differ from traditional LLM benchmarks, with production observations, workload profiles, and an open-source harness for replaying traces.
