AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing

• URL: http://arxiv.org/abs/2511.12133v1
• Date: Sat, 15 Nov 2025 09:44:42 GMT
• Title: AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing
• Authors: Qingyu Zhang, Chunlei Xin, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, Qing Ye, Qianlong Xie, Xingxing Wang,
• Abstract summary: We release TeleSalesCorpus, the first real-world-grounded dialogue dataset for this domain.<n>We then propose AI-Salesman, a novel framework featuring a dual-stage architecture.<n>We show that our proposed AI-Salesman significantly outperforms baseline models in both automatic metrics and comprehensive human evaluations.
• Score: 79.0112532518727
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Goal-driven persuasive dialogue, exemplified by applications like telemarketing, requires sophisticated multi-turn planning and strict factual faithfulness, which remains a significant challenge for even state-of-the-art Large Language Models (LLMs). A lack of task-specific data often limits previous works, and direct LLM application suffers from strategic brittleness and factual hallucination. In this paper, we first construct and release TeleSalesCorpus, the first real-world-grounded dialogue dataset for this domain. We then propose AI-Salesman, a novel framework featuring a dual-stage architecture. For the training stage, we design a Bayesian-supervised reinforcement learning algorithm that learns robust sales strategies from noisy dialogues. For the inference stage, we introduce the Dynamic Outline-Guided Agent (DOGA), which leverages a pre-built script library to provide dynamic, turn-by-turn strategic guidance. Moreover, we design a comprehensive evaluation framework that combines fine-grained metrics for key sales skills with the LLM-as-a-Judge paradigm. Experimental results demonstrate that our proposed AI-Salesman significantly outperforms baseline models in both automatic metrics and comprehensive human evaluations, showcasing its effectiveness in complex persuasive scenarios.

Related papers

• Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs [72.08224879435762]
  textttLearn-to-Ask is a simulator-free framework for learning and deploying proactive dialogue agents.<n>Our approach culminates in the successful deployment of LLMs into a live, large-scale online AI service.
  arXiv  Detail & Related papers  (2025-10-29T12:08:07Z)
• SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents [93.26456498576181]
  This paper focuses on the development of native Autonomous Single-Agent models for Deep Research.<n>Our best variant SFR-DR-20B achieves up to 28.7% on Humanity's Last Exam benchmark.
  arXiv  Detail & Related papers  (2025-09-08T02:07:09Z)
• DeepForm: Reasoning Large Language Model for Communication System Formulation [14.249525913644884]
  Communication system formulation is critical for advancing 6G and future wireless technologies.<n>We propose the world-first large-scale, open-source dataset meticulously curated for this domain called Communication System Formulation Reasoning Corpus (CSFRC)<n>Our framework employs a two-stage training strategy: first, Supervised Fine-Tuning (SFT) with Chain-of-Thought (CoT) data to distill domain knowledge; second, a novel rule-based Reinforcement Learning (RL) algorithm, C-ReMax based on ReMax.
  arXiv  Detail & Related papers  (2025-06-10T08:16:24Z)
• A Survey on Post-training of Large Language Models [185.51013463503946]
  Large Language Models (LLMs) have fundamentally transformed natural language processing, making them indispensable across domains ranging from conversational systems to scientific exploration.<n>These challenges necessitate advanced post-training language models (PoLMs) to address shortcomings, such as restricted reasoning capacities, ethical uncertainties, and suboptimal domain-specific performance.<n>This paper presents the first comprehensive survey of PoLMs, systematically tracing their evolution across five core paradigms: Fine-tuning, which enhances task-specific accuracy; Alignment, which ensures ethical coherence and alignment with human preferences; Reasoning, which advances multi-step inference despite challenges in reward design; Integration and Adaptation, which
  arXiv  Detail & Related papers  (2025-03-08T05:41:42Z)
• AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO [0.0]
  Large Language Models (LLMs) have demonstrated impressive capabilities in language processing, yet they often struggle with tasks requiring visual spatial reasoning.<n>We introduce a novel two-stage training framework designed to equip standard LLMs with visual reasoning abilities for maze navigation.
  arXiv  Detail & Related papers  (2025-02-20T16:05:18Z)
• Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
  Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks.<n>However, they still struggle with problems requiring multi-step decision-making and environmental feedback.<n>We propose a framework that can automatically learn a reward model from the environment without human annotations.
  arXiv  Detail & Related papers  (2025-02-17T18:49:25Z)
• Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests [6.33281463741573]
  Indirect User Requests (IURs) are common in human-human task-oriented dialogue and require world knowledge and pragmatic reasoning from the listener. While large language models (LLMs) can handle these requests effectively, smaller models deployed on virtual assistants often struggle due to resource constraints.
  arXiv  Detail & Related papers  (2024-06-12T01:18:04Z)
• Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning [79.38140606606126]
  We propose an algorithmic framework that fine-tunes vision-language models (VLMs) with reinforcement learning (RL) Our framework provides a task description and then prompts the VLM to generate chain-of-thought (CoT) reasoning. We demonstrate that our proposed framework enhances the decision-making capabilities of VLM agents across various tasks.
  arXiv  Detail & Related papers  (2024-05-16T17:50:19Z)
• Injecting Salesperson's Dialogue Strategies in Large Language Models with Chain-of-Thought Reasoning [23.919423630938226]
  SalesBot simulates dialogues transitioning from chit-chat to task-oriented scenarios to train sales agents. Initial data lacked smooth transitions and coherent long-turn dialogues, resulting in poor naturalness in sales-customer interactions. We introduce a novel model called SalesAgent, trained on salesperson's interactions, using chain-of-thought (CoT) reasoning.
  arXiv  Detail & Related papers  (2024-04-29T10:12:04Z)
• From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models [11.999652715036643]
  RAISE (Reasoning and Acting through Scratchpad and Examples) is an advanced architecture enhancing the integration of Large Language Models (LLMs) into conversational agents. It incorporates a dual-component memory system, mirroring human short-term and long-term memory, to maintain context and continuity in conversations.
  arXiv  Detail & Related papers  (2024-01-05T12:26:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.