# Offloop 发布调度模型 D1，多智能体系统 SOTA 降本

- 来源：elvis (@omarsar0)
- 发布时间：2026-07-24 01:14
- AIHOT 分数：49
- AIHOT 链接：https://aihot.virxact.com/items/cmrxs5dea01ycroxp2zn15tzb
- 原文链接：https://x.com/omarsar0/status/2080340696842539204

## AI 摘要

Offloop 训练了调度模型 D1，决定多智能体系统中哪个智能体下一步行动以及何时应保持静默，避免重复工作和 token 浪费。该方案在 GDPval 基准上达到 SOTA，超越 Claude Code 和 Codex，且成本仅为通常的一小部分。用户可自带 AI 订阅使用。

## 正文

The hard part of multi-agent systems is getting agents to stay quiet.

Put five agents on one task， and they duplicate work and burn tokens talking to each other.

Offloop trained a dispatcher model called D1 that decides which agent moves next and when the right move is to do nothing. They achieve state-of-the-art performance on GDPval at a fraction of the usual cost.

You can bring your own AI subscription. http://offloop.org

### 引用推文

> Offloop：Introducing Offloop! We're a team of four. Today our multi-agent harness hit state of the art on GDPval, ahead of Claude code and Codex across jobs that pay $2....