Organization

Nature

1 mentions in 7 days · 1 in 30 days · 2 total · first seen Aug 15, 2026 · last 7h ago

Timeline2 articles

Stanford Researchers Release Paper2Agent: Turning Research Papers Into AI Agents That Reproduce Results and Run on New Data

Stanford researchers released Paper2Agent, a Nature-published pipeline that turns research papers into MCP servers agents can execute.

A Stanford team led by Jiacheng Miao and James Zou published Paper2Agent in Nature on 16 September 2026. Built on Claude Code's agent SDK, it converts a paper and its codebase into a Model Context Protocol server with validated tools, resources, and prompts. In benchmarks, the AlphaGenome agent built 22 tools in about 45 minutes for US$14, scored 100% on 15 novel queries versus 78.7% for Claude Code with repository access, and cut median runtime 1.9x. In scale tests, 74 of 100 bioRxiv papers were converted and 593 of 599 proposed tools passed validation.

MarkTechPostSep 16, 21:59 UTC · 7h agoAI research1

Memories Mysteriously Survive After Brain Shutdown, And Scientists Don’t Know Why

Science roundup covering medieval European flood reconstruction, frog mate-choice overload, and mouse memory persistence during artificial hibernation.

404 Media's The Abstract column surveys non-cyber research: a Nature study reconstructing 16 major European floods in 1342-1343 including the Magdalena Flood, an iScience study on choice overload in female Cope's gray treefrogs during dense mating choruses, and a Science study on synaptic engram architecture preserving memories in artificially hibernated mice. None of the studies relate to cybersecurity or artificial intelligence.

404 MediaAug 15, 10:00 UTC · Aug 15, 2026Other

Appears with

ai model Claude Sonnet 4 1 organization Hugging Face 1 organization iScience 1 organization Science 1 organization Stanford University 1 organization University of Tennessee 1 organization Vienna University of Technology 1 product Claude Code 1 product Paper2Agent 1 vendor Anthropic 1

Entities are extracted by the model from each article. Watching an entity keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.