SETU：面向多语言、角色感知沟通指导的智能体生态系统
SETU: An Agentic Ecosystem for Multilingual, Persona-Aware Communication Coaching
浏览论文内容
中文总结 AI 辅助
SETU是面向企业沟通指导的智能体生态系统，针对多语言场景设计，通过多模态智能体协调生成指导报告，仅针对销售推介场景验证效果，旨在弥合沟通差距。
中文摘要 AI 辅助
企业培训团队需要可扩展且可解释的工具，以在多语言环境中提升员工沟通能力。现有系统往往孤立地对文本、音频或视频进行评分，或产生难以审计的黑箱输出，无法满足指导需求。本文提出SETU，这是一个面向招聘人员、一线销售专业人员及为特定受众对话做准备的培训部门的企业沟通指导智能体生态系统。SETU针对两个限定场景设计：（i）带有角色上下文的招聘人员-候选人资格与意向通话，（ii）需适配目标受众的销售推介；由于评估资源有限，本文仅报告场景（ii）的结果。该生态系统将分析分解为专门的视频、音频-语音、文本相关性、评分、通知及报告智能体，通过信任感知编排进行协调，生成带有模态属性的指导报告用于形成性培训，最终判断由人工审核人员保留。SETU的名称源于多种印度语言中“桥梁”之意，反映了其弥合区域语言与受众期望之间沟通差距的目标。
英文摘要
Corporate training teams need scalable and explainable tools to improve workforce communication in multilingual settings. Existing systems often score text, audio, or video in isolation, or produce black-box outputs that are difficult to audit for coaching use. This paper presents SETU, an agentic ecosystem for corporate communication coaching aimed at recruiters, frontline sales professionals and training units who prepare for audience specific conversations. SETU is designed for two scoped scenarios: (i) recruiter-candidate eligibility-and-interest calls with persona context and (ii) sales pitches with target-audience adaptation; owing to limited evaluation resources, this paper reports results on scenario (ii) only. The ecosystem decomposes analysis into specialized video, audio-speech, text-relevance, scoring, notification and reporting agents coordinated through trust-aware orchestration. It generates modality-attributed coaching reports for formative training, with human reviewers retaining final judgment. The name SETU (bridge in several Indic languages) reflects the goal of bridging communication gaps across regional languages and audience expectations.
发表机构
- Quanta People Solutions Pvt. Ltd.（Quant People Solutions私人有限公司）
- Panorama AI Solutions（全景人工智能解决方案公司）
- University College of Engineering, Osmania University（奥萨马尼亚大学工程学院）
机构由 AI 辅助整理，请以论文原文为准。
