AI Paper Atlas

Research map / Large language models / Agents, code and math

AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing

Qingyu Zhang, Chunlei Xin, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, Qing Ye, Qianlong Xie, Xingxing Wang

AAAI 2026 · Large language models › Agents, code and math · approach: Agent instruction-following benchmarks · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train directly with GRPO and the Bayesian reward (no SFT) plus DOGA inferenceQwen2.5-7B-Instruct · TeleSales Syn-Data (mean)LLM-judge mean score: 5.46 -> 6.49Improved
add SFT before GRPO (ablation)GRPO · TeleSales Syn-Data (mean)LLM-judge mean score: 6.49 -> 5.77Hurt
add GRPO on top of SFT modelSFT-only · TeleSales Syn-Data (mean)LLM-judge mean score: 5.69 -> 5.77No clear effect
add domain SFT to baselineQwen2.5-7B-Instruct · TeleSales Syn-Data (Role-playing)LLM-judge mean score: 5.54 -> 5.66No clear effect
add domain SFT to baselineQwen2.5-7B-Instruct · TeleSales Syn-Data (Business Analysis)LLM-judge mean score: 6.49 -> 6.78Improved
add Bayesian-supervised reasoning reward (ablation)GRPO · TeleSales Syn-Data (mean)LLM-judge mean score: 6.15 -> 6.49Improved
add semantic similarity reward (ablation)GRPO · TeleSales Syn-Data (mean)LLM-judge mean score: 6.39 -> 6.49Improved
use DOGA dynamic outline instead of static prompt (ablation)Ours · Objection Handling / Operational Guidance / Business AnalysisLLM-judge score: +11.9% / +14.8% / +5.1%Improved
use DOGA instead of static prompt on simple tasks (ablation)Ours · Role-playing and Idle-chat RejectionLLM-judge scoreHurt
scale base model from 7B to 14B (ablation)Ours · Real-Dataperformance score: 6.62 -> 6.67No clear effect
scale base model from 32B to 72B (ablation)Ours · Real-Dataperformance score: 7.17 -> 7.01Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy