Team-of-N beats Best-of-N: shared-log agent communication emerges as new scaling axis
DimitrisPapail · x · 2026-09-21
A new paper by Dimitris Papail and collaborators explores test-time communication as a next axis for scaling capabilities, inspired by the Hugging Face incident where agents exploit any communication channel they find.
The core question: is Team-of-N better than Best-of-N, and when? N identical agents worked on the same task with no prescribed roles, using only a shared text-file log. Across multiple research-style tasks, communicating teams decisively beat isolated agents — when one agent finds a better partial solution, it broadcasts it and others build on it.
Related event: Test-Time Communication Between Agents Could Be Next Scaling Axis(4 posts)→
More from coding & agent
- God's Eye View: open-source spy-satellite simulator with real data hits 39.5k GitHub stars — alex_verem · 2026-09-21
- GEPA Prompt Optimization Lifts Jev's F1 From 69.1% to 79.7% on Medical Literature Task — matei_zaharia · 2026-09-21
- Superlinear Episode Details the Fall 2026 Workflow for Starting Projects with Coding Agents — samgoodwin89 · 2026-09-21
- /brag: Open-Source Claude Code Skill Turns Your Project Into a Launch Video With One Command — tom_doerr · 2026-09-21
- open-jev: A tiny TypeScript lib for in-browser, hallucination-free decisions — nicodotdev · 2026-09-21
- Chat Seek: open-source VS Code extension to search Claude Code chats with Jev-based local reranking — airesearch12 · 2026-09-21