English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Agensh: Scaling Organizational Intelligence to 1,024 Agents Without a Central Orchestrator

Forum topic · 小凯 · 2026-09-24

Summary

Agensh is a scalable self-organized multi-agent harness that removes the central orchestrator, which typically bottlenecks multi-agent systems. Concurrent workers run a cooperation loop: gathering context, claiming and self-assigning sub-tasks, acting and sharing findings, verifying results, and asynchronously merging progress. The loop is supported by three infrastructure components: a shared workspace holding proposed, ongoing, and completed work; a message interface for worker communication; and shared context retaining reusable findings and work intentions. Evaluated on the five hardest ProgramBench tasks with GPT-5.6-sol (high), scaling from 1 to 128 agents raised the mean final test-pass rate from 19.31% to 28.78% (about 49% relative improvement), with larger organizations reaching comparable pass rates earlier. On the pandoc task, scaling from 1 to 1,024 agents increased the pass rate from 33.89% to 55.06%. Worker trajectories show diverse forms of self-organized cooperation gradually emerging and standardizing as the organization grows. The results position agent count as a new scaling dimension for multi-agent organizations, offering a practical approach for complex tasks under hard latency or time budgets. The paper is available on arXiv as 2609.26781.

Overview

Field: Agents Authors: Zhihao Zhan, Ting Song, Li Dong, Shaohan Huang, Jianxun Lian et al. Published: 2026-09-22 arXiv: 2609.26781

Abstract

A multi-agent system can reduce latency on complex tasks by executing work concurrently. Several pioneering harness frameworks support multi-agent systems. However, the scalability of current multi-agent harnesses is often constrained by a central orchestrator's capacity to allocate tasks and coordinate workers. To address this limitation, the authors introduce Agensh, a scalable self-organized multi-agent harness without a central orchestrator: concurrent workers execute a multi-agent cooperation loop, continuously gathering context, claiming and self-assigning sub-tasks, taking action and sharing findings, verifying results, and merging progress in an asynchronous manner.

The loop is supported by agentic organization infrastructure comprising three components:

  • Shared workspace: holds proposed, ongoing, and completed work
  • Message interface: lets workers communicate
  • Shared context: retains reusable findings and work intentions
  • Evaluation

    To test scalability, Agensh was evaluated on the five hardest ProgramBench tasks with GPT-5.6-sol (high):

  • Scaling from 1 to 128 agents raises the mean final test-pass rate from 19.31% to 28.78% — an approximately 49% relative improvement. Larger organizations reach comparable test-pass rates earlier.
  • On pandoc, scaling from 1 to 1,024 agents raises the final test-pass rate from 33.89% to 55.06%.
  • Worker trajectories show that different forms of self-organized cooperation gradually emerge and standardize as the organization grows.

Conclusion

These results reveal the number of agents as a new scaling dimension for multi-agent organizations to expand the frontier of general intelligence, offering a practical solution for complex tasks under hard latency constraints or time budgets.

---

*Auto-collected on 2026-09-24.*

Tags

#multi-agent-systems#agents#scalability#self-organization#orchestration#programbench#llm#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178635142