# Injecting Salesperson's Dialogue Strategies in Large Language Models with Chain-of-Thought Reasoning

arXiv: https://arxiv.org/abs/2404.18564 · HTML: https://mlsanity.com/paper/2404.18564/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 29 Apr 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 17 of 17)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [Towards Deep Conversational Recommendations](https://mlsanity.com/paper/1812.07617/) (2018)
- [SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization](https://mlsanity.com/paper/2212.10465/) (2022)
- [The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning](https://mlsanity.com/paper/2305.14045/) (2023)
- [INSPIRED: Toward Sociable Recommendation Dialog Systems](https://mlsanity.com/paper/2009.14306/) (2020)
- [A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects](https://mlsanity.com/paper/2305.02750/) (2023)
- [A User Simulator for Task-Completion Dialogues](https://mlsanity.com/paper/1612.05688/) (2016)
- [Adding Chit-Chat to Enhance Task-Oriented Dialogues](https://mlsanity.com/paper/2010.12757/) (2020)
- [Enhancing Task Bot Engagement with Synthesized Open-Domain Dialog](https://mlsanity.com/paper/2212.10008/) (2022)
- [INSPIRED2: An Improved Dataset for Sociable Conversational Recommendation](https://mlsanity.com/paper/2208.04104/) (2022)

## Built on by (most cited first, 9 of 9)

- [SOTOPIA-Omega: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agents](https://mlsanity.com/paper/2502.15538/) (2025)
- [The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends](https://mlsanity.com/paper/2409.14195/) (2024)
- [DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling](https://mlsanity.com/paper/2412.04905/) (2024)
- [Towards Personalized Conversational Sales Agents: Contextual User Profiling for Strategic Action](https://mlsanity.com/paper/2504.08754/) (2025)
- [Exploring Personality-Aware Interactions in Salesperson Dialogue Agents](https://mlsanity.com/paper/2504.18058/) (2025)
- [Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents](https://mlsanity.com/paper/2511.08835/) (2025)
- [Narrative-Driven Travel Planning: Geoculturally-Grounded Script Generation with Evolutionary Itinerary Optimization](https://mlsanity.com/paper/2502.14456/) (2025)
- [A Multi-Agent Probabilistic Inference Framework Inspired by Kairanban-Style CoT System with IdoBata Conversation for Debiasing](https://mlsanity.com/paper/2506.21565/) (2025)
- [From Simulation to Strategy: Automating Personalized Interaction Planning for Conversational Agents](https://mlsanity.com/paper/2510.08621/) (2025)

## Abstract (arXiv)

Recent research in dialogue systems and corpora has focused on two main categories: task-oriented (TOD) and open-domain (chit-chat) dialogues. TOD systems help users accomplish specific tasks, while open-domain systems aim to create engaging conversations. However, in real-world scenarios, user intents are often revealed during interactions. A recent study introduced SalesBot, which simulates dialogues transitioning from chit-chat to task-oriented scenarios to train sales agents. Unfortunately, the initial data lacked smooth transitions and coherent long-turn dialogues, resulting in poor naturalness in sales-customer interactions. To address these issues, this paper presents SalesBot 2.0, an improved dataset. It leverages commonsense knowledge from large language models (LLMs) through strategic prompting. Additionally, we introduce a novel model called SalesAgent, trained on salesperson's interactions, using chain-of-thought (CoT) reasoning. This model excels in transitioning topics, understanding user intents, and selecting appropriate strategies. Experiments using diverse user simulations validate the effectiveness of our method in controlling dialogue strategies in LLMs. Furthermore, SalesBot 2.0 enhances coherence and reduces aggression, facilitating better model learning for sales-customer interactions.