Multi-agent scaling can be compute-optimal: N parallel agents beat one agent run N-times longer

DimitrisPapail · x · 2026-09-22

Sharing data from ARC-AGI-3 ablations: for some problems, a team of N agents running 1x as long outperforms a single agent run for Nx as long — meaning multi-agent scaling is compute-optimal, not just speed-optimal. Anecdotally, a single agent with a bigger budget plateaus faster than best-of-N with 1/N budget each. Practical implication for parallel sampling vs. long single runs in agent engineering.

Related event: Multi-Agent Teams Beat Single Agents by 10-100x Tokens, Sparking Baseline Debate(7 posts)→

Original post →

More from coding & agent

coding & agent channel →