Test-time communication as the next scaling axis: collaborating agents crush Best-of-N
DimitrisPapail · x · 2026-09-23
A new paper from Dimitris Papailiopoulos and colleagues proposes test-time communication as a next axis for scaling agent capabilities. N identical agents with no assigned roles, sharing only a log file, dramatically outperformed independent agents on three research-style tasks; a four-agent GPT-6 Astra swarm hit 98.04% mean packing density on FrontierCS Polyomino packing in just 81 active minutes. Stronger models amplify the gains.
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