Skip to content
Tagged articles

Automated Research

7 articles · Page 1 of 1
SmartApe AI
SmartApe AI
Oct 21, 2026 · Artificial Intelligence

Recursive Open-Sources Flint-40B-A2B: AI-Designed MoE Model for Local Coding Agents

Recursive team open-sources Flint-40B-A2B, a 40B-parameter MoE model optimized for local coding agents, developed in under four months using their Eureka Machine AI research system; it achieves over 125 tokens/sec on MacBook Pro and demonstrates autonomous research capabilities on tasks like circle packing, factory scheduling (26% improvement), and bike-sharing demand prediction (30.8% RMSLE reduction).

Automated ResearchCoding AgentEureka Machine
0 likes · 6 min read
Recursive Open-Sources Flint-40B-A2B: AI-Designed MoE Model for Local Coding Agents
Machine Heart
Machine Heart
Oct 20, 2026 · Artificial Intelligence

AI Agents Evolve by Reading Research: Microsoft & UCSB's ScholarEvolve

Microsoft and UCSB researchers introduce ScholarEvolve, a system where AI agents automatically read arXiv papers, implement new algorithms, and combine them to improve Agent Harness performance, boosting Qwen3.5-27B's AppWorld Challenge success from 49.6% to 63.6% without model retraining.

AI AgentsAgent HarnessAppWorld
0 likes · 11 min read
AI Agents Evolve by Reading Research: Microsoft & UCSB's ScholarEvolve
PaperAgent
PaperAgent
Apr 20, 2026 · Artificial Intelligence

How 9 Parallel Claude Agents Surpassed Human Researchers in Weak‑to‑Strong Supervision

Anthropic’s Automated Weak‑to‑Strong Researcher (AAR) system uses nine parallel Claude Opus agents to replace human researchers, achieving a Performance Gap Recovered (PGR) of 0.97 in five days at a cost of about $18,000, demonstrating that AI‑driven automation can outperform humans on well‑defined alignment tasks.

AARAI alignmentAgentic AI
0 likes · 9 min read
How 9 Parallel Claude Agents Surpassed Human Researchers in Weak‑to‑Strong Supervision
AI Agent Research Hub
AI Agent Research Hub
Mar 9, 2026 · Artificial Intelligence

How Claude Code AI Agents Generated 100 Research Papers in 10 Days

Within 228 hours, the Fully Automated Research System (FARS) built on Claude Code and other AI agents used 160 NVIDIA GPUs to produce 100 peer‑review‑level papers, achieving an average ICLR score of 5.05—higher than human submissions—while highlighting the expanding role, limits, and safety concerns of AI‑driven scientific automation.

AI AgentsAI safetyAutomated Research
0 likes · 31 min read
How Claude Code AI Agents Generated 100 Research Papers in 10 Days
JD Tech Talk
JD Tech Talk
Aug 5, 2024 · Artificial Intelligence

An Introduction to STORM: An LLM‑Powered Knowledge Management System for Automated Research and Writing

This article introduces STORM, a Stanford‑developed large‑language‑model‑based knowledge‑management platform that automates topic research, outline generation, citation‑rich article writing, and iterative refinement through perspective‑guided questioning and simulated conversations, dramatically improving technical investigation efficiency.

AI toolsArticle GenerationAutomated Research
0 likes · 7 min read
An Introduction to STORM: An LLM‑Powered Knowledge Management System for Automated Research and Writing
JD Cloud Developers
JD Cloud Developers
Aug 5, 2024 · Artificial Intelligence

How STORM Uses LLMs to Automate Technical Research and Writing

This article introduces STORM, a Stanford‑developed LLM‑based knowledge‑management system that automates topic research, outline creation, content generation with citations, and optimization through perspective‑guided questioning and simulated dialogue, dramatically improving technical investigation efficiency.

AI writingAutomated ResearchLLM
0 likes · 5 min read
How STORM Uses LLMs to Automate Technical Research and Writing