New paper shows communicating agent teams beat independent agents: Team-of-N > Best-of-N via a shared log
DimitrisPapail · x · 2026-09-22
Researchers including Dimitris Papail released a new paper exploring test-time communication as a next axis for scaling capabilities, asking: when and why is Team-of-N better than Best-of-N?
Setup: N identical agents work on the same task with no prescribed roles, using only a shared log (a text file) and an instruction to "collaborate".
Key finding: across three "researchy" tasks, communicating teams beat independent agents by a wide margin. Citing the Hugging Face incident, the authors note agents will exploit any communication channel they can find — suggesting agent-to-agent communication is an extremely rich research direction.
Related event: Test-Time Communication: Team-of-5 Agents Matches Best-of-33(25 posts)→
More from coding & agent
- Cloudflare Talk: Swapping Some Agent LLM Calls for Fast Models Like Jev Gives Big Speedups — michellechen · 2026-11-12
- Engineer Curates 15 AI Agent Design Patterns Across Single-Agent, Multi-Agent and Feedback Tiers — MaryamMiradi · 2026-11-12
- Google Antigravity rolls out browser use, closing the loop from research to coding to live verification — rseroter · 2026-11-12
- Prettier 3.10 ships new Flow/JS syntax and a Zig-powered Yuku plugin — Vjeux · 2026-11-12
- YC-backed Graphide claims CI runner 10-20x faster than GitHub on 24 repos — ycombinator · 2026-11-12
- Lessons from a 1600-page transcription: general thinking resists staying organized — fkasummer · 2026-11-12