Research / AI Paper
arXiv paper proposing MANTA, a framework that lets multi-agent communication structures adapt at inference time based on collaboration traces and task needs.
The page clearly presents a real AI research paper focused on multi-agent systems and includes an abstract with a specific method, evaluation setup, and reported results. It is useful as a public listing because visitors can understand the paper’s topic, contribution, and benchmark claims from the crawl snapshot.
This is only an abstract page, so the crawl does not show the full paper, code, dataset, or implementation details. It also does not reveal whether the authors released a usable system, benchmark artifacts, or a public repo.
Last evaluated 30 days ago. Current rank #1852. Holding steady 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.
