filipe(@filicroval):for anyone doing research or reproducing papers, i came across this new tool that automates a big part of the painful setup work. alphaXiv turns research papers + code into runnable experiments. instead of manually fixing broken setups, an agent can now: - Clone the repo - Read the paper + code - Fix the environment - Run the experiments end-to-end it works by changing repo URLs (e.g. github → argithub, arxiv→ autoarxiv), which triggers the agent. GLM 5.2 was able to run real multi-node training on its own with this setup. having 1M context helps a lot since the whole project stays in view.

2026.06.25 19:21

for anyone doing research or reproducing papers, i came across this new tool that automates a big part of the painful setup work. alphaXiv turns research papers + code into runnable experiments. instead of manually fixing broken setups, an agent can now: - Clone the repo - Read the paper + code - Fix the environment - Run the experiments end-to-end it works by changing repo URLs (e.g. github → argithub, arxiv→ autoarxiv), which triggers the agent. GLM 5.2 was able to run real multi-node training on its own with this setup. having 1M context helps a lot since the whole project stays in view.