# Salesforce 发布企业智能体模型 Koa

- 来源：elvis (@omarsar0)
- 发布时间：2026-09-16 12:34
- AIHOT 分数：43
- AIHOT 链接：https://aihot.news/items/cmu3m6rmy03trroc1wn9htahq
- 原文链接：https://x.com/omarsar0/status/2100080746056777899

## AI 摘要

Salesforce 基于开源 Nemotron-3-Super-120B 训练出企业智能体模型 Koa，用配置 Agentforce 智能体的 Agent Script 声明式文件扩展成多轮任务与模拟用户角色，并以 GRPO 训练、按工具调用是否正确给予奖励。

## 正文

Banger report from Salesforce.

Pretty interesting to see more of these custom enterprise models.

Salesforce trained the enterprise agent model from the same files it uses to configure agents.

Koa starts from the open-weight Nemotron-3-Super-120B.

Salesforce takes Agent Script specifications, the declarative files that define Agentforce agents, and expands them into multi-turn tasks with simulated user personas.

The reward checks whether the agent resolved the task with the right tool calls, and training uses GRPO.

The gains are modest and consistent.

Koa scores 69.41 on Tau2Bench against 68.64 for its base and 54.48 for GPT-4.1. On CRM Bench it reaches 0.86, close to Claude Opus 4.8 at 0.87, and function-call accuracy rises from 0.71 to 0.77.

If your company already describes its workflows in a structured format, those descriptions might be useful to turn into RL environments.

Paper: https://arxiv.org/abs/2609.15066

Chat with Paper: https://academy.dair.ai/papers/salesforce-koa-an-enterprise-language-model-for-agentic-tool-use-2609.15066