research-automation

Tag

Cards List
#research-automation

@_akhaliq: Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

X AI KOLs Following · 4d ago Cached

This paper proposes a method for autonomous research agents using hypothesis-tree refinement to generate and test hypotheses, aiming toward generalist scientific discovery.

0 favorites 0 likes
#research-automation

AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle

arXiv cs.AI · 2026-06-01 Cached

AutoSci is a memory-centric agentic system designed to automate the full scientific research lifecycle, from literature understanding to rebuttal, using LLM-based agents with persistent memory and self-evolution capabilities.

0 favorites 0 likes
#research-automation

@Honcia13: The threshold for scientific research is being completely redefined! Previously: staying up late reading papers, repeatedly running code, writing a week-long review. Now: a single instruction is enough. The open-source AI agent Feynman compresses PhD-level research processes into fully automated execution: a single instruction can complete in-depth arXiv research, literature review, code verification …

X AI KOLs Timeline · 2026-05-28 Cached

The open-source AI agent Feynman, through the collaboration of four intelligent agents, compresses PhD-level research processes (including arXiv research, literature review, code verification) into fully automated execution, requiring only a single instruction from the user.

0 favorites 0 likes
#research-automation

@DamiDefi: Claude Code cannot read 300 files at once. So someone built a system that lets it control NotebookLM from the terminal …

X AI KOLs Timeline · 2026-05-26 Cached

A system built on Claude Code allows it to control Google's NotebookLM from the terminal, automating research by searching YouTube, uploading sources, and exporting cited answers directly into Obsidian. This workflow eliminates the need for multiple browser tabs and manual copying, with verified citation accuracy.

0 favorites 0 likes
#research-automation

@seelffff: > reads papers on arXiv autonomously > finds and checks datasets on HF Hub > writes the training script itself > genera…

X AI KOLs Timeline · 2026-05-25 Cached

Hugging Face open-sourced ml-intern, an autonomous agent that performs the entire ML post-training loop—reading papers, finding datasets, writing scripts, generating data, monitoring training, and uploading weights—achieving significant GPQA improvement with a 1.7B model in 10 hours without human intervention.

0 favorites 0 likes
#research-automation

AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery

Hugging Face Daily Papers · 2026-05-22 Cached

A survey paper examining the transition of AI from task-specific assistants to workflow-level research automators, defining AutoResearch as the spectrum of AI-powered scientific workflow automation and analyzing challenges in autonomy, reproducibility, and accountability.

0 favorites 0 likes
#research-automation

@mylifcc: Conduct research while sleeping? The viral GitHub project ARIS (8.8k stars) is here! Auto-claude-code-research-in-sleep (ARIS) — a lightweight Markdown-only skill pack that enables Claude Code (or any LL…

X AI KOLs Timeline · 2026-05-12

ARIS is an open-source tool that has gone viral on GitHub (8.8k stars). It uses a lightweight Markdown skill pack to enable Claude Code or other LLM agents to autonomously complete the entire machine learning research lifecycle, including literature review, experiment execution, and paper writing.

0 favorites 0 likes
#research-automation

NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation

Hugging Face Daily Papers · 2026-05-11 Cached

NanoResearch is a multi-agent framework designed to personalize research automation by co-evolving skills, memory, and policy to adapt to individual user preferences and research styles.

0 favorites 0 likes
#research-automation

@tom_doerr: Automates research workflows with persistent multi-agent memory https://github.com/EvoScientist/EvoScientist…

X AI KOLs Timeline · 2026-05-09 Cached

EvoScientist is an open-source framework that automates research workflows using self-evolving AI scientists with persistent multi-agent memory, adopting a human-on-the-loop paradigm for autonomous research exploration and insight generation.

0 favorites 0 likes
#research-automation

@ManusAI: https://x.com/ManusAI/status/2052764534872678882

X AI KOLs Following · 2026-05-08 Cached

The article explains how Manus's Browser Operator works by operating inside the user's authorized local browser session, allowing it to access subscription-based and authenticated content beyond typical AI search capabilities, and provides a step-by-step guide for enabling and using it.

0 favorites 0 likes
#research-automation

@RoundtableSpace: HUGGING FACE JUST AUTOMATED THEIR ENTIRE POST-TRAINING TEAM WITH AN AGENT. It reads papers, runs GPU experiments, itera…

X AI KOLs Following · 2026-04-21 Cached

Hugging Face replaced its post-training team with an autonomous agent that reads papers, runs GPU experiments, and improves models, achieving a 22-point benchmark jump in under 10 hours and beating Codex on HealthBench by 60%.

0 favorites 0 likes
#research-automation

@lftherios: 1/ Autoresearch from @karpathy has been one of the most interesting agentic patterns to emerge this year. The challenge…

X AI KOLs Timeline · 2026-04-20 Cached

Andrej Karpathy's autoresearch pattern highlights how current AI agents run experiments in isolation, wasting compute by duplicating work and rediscovering dead ends.

0 favorites 0 likes
#research-automation

Import AI 455: AI systems are about to start building themselves.

Hacker News Top · 2026-05-21 Cached

The article argues that there is a high likelihood (60%+) of fully automated AI R&D—where AI systems can build their own successors without human involvement—by the end of 2028, citing evidence from coding benchmarks like SWE-Bench and trends in AI autonomy.

1 favorites 1 likes
← Back to home

Submit Feedback