beat · 6 stories
A new arXiv preprint turns merging parallel AI agents' edits into a graph problem, and shows that partially committing compatible edits keeps a guaranteed share of the verified gains — at a real token cost on larger, conflict-free work.
CASTLE, a technique that gives each agent a frozen offline world model (arXiv 2610.
A new arxiv preprint on mixed multi-agent AI simulations finds base model choice predicts engagement more than persona assignment, a result that reorders the design hierarchy for builders.
Google's engineering post claims a 1.69× speedup on its TPU v6e AI chip at 1440p. The underlying idea is older, and the speedup is smaller than the academic paper behind it.
A Google Cloud team rebuilt the Allen Institute's open Olmo 3 on Google's TPU chips. Held-out tests matched the original, and exposed a data-loader bug that made the new stack look better than it was.
ELMS, short for Evidence-based LLM-guided Monte Carlo Search, from a Georgia Tech team reuses failed protein structures as repair instructions and solved 26.7 of 30 tasks on MotifBench, a protein-scaffolding benchmark, up from 16.