Research / AI Agents
arXiv paper describing QUEST, an open family of deep research agents from 2B to 35B parameters, plus a synthetic-task training recipe and released models, data, and scripts.
The page clearly presents an AI research product: an open family of deep research agents with described capabilities, training method, benchmarks, and released assets. The abstract gives enough evidence to support a useful public listing for AI builders and researchers.
The crawl shows the paper abstract but not the actual repo, model cards, benchmark tables, or download links, so visitors cannot tell how to run the models or what licenses and deployment requirements apply.
Last evaluated 98 days ago. Current rank #1122. Down 3 spots 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.
