‹ back to 2026-09-23

Agensh: Scaling Organizational Intelligence to 1,024 Agents

arXiv cs.CL LLM Agents Zhihao Zhan, Ting Song, Li Dong, Shaohan Huang, Jianxun Lian, Yan Xia, Furu Wei 2026-09-22

TL;DR - Agensh is a self-organizing multi-agent framework that replaces centralized orchestration with asynchronous task claiming, communication, and shared context. Experiments suggest that increasing the agent count can improve coding-task performance and reduce time to reach comparable results.

Workers independently gather context, claim subtasks, execute actions, share findings, verify results, and merge progress through a shared workspace.
On five difficult ProgramBench tasks, scaling from 1 to 128 agents increased the mean final test-pass rate from 19.31% to 28.78%, a roughly 49% relative gain.
On the pandoc task, scaling from 1 to 1,024 agents raised the final test-pass rate from 33.89% to 55.06%.
Agent trajectories indicated that cooperation patterns emerged and became more standardized as the organization grew.

view merged work →