# ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents

arXiv: https://arxiv.org/abs/2407.03884 · HTML: https://mlsanity.com/paper/2407.03884/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 29 of its 50 references that are in the map.
- First posted on arXiv 4 Jul 2024.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 29 of 29)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [ToolQA: A Dataset for LLM Question Answering with External Tools](https://mlsanity.com/paper/2306.13304/) (2023)
- [REFINER: Reasoning Feedback on Intermediate Representations](https://mlsanity.com/paper/2304.01904/) (2023)
- [A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems](https://mlsanity.com/paper/2402.18013/) (2024)
- [Open-Domain Question Answering Goes Conversational via Question Rewriting](https://mlsanity.com/paper/2010.04898/) (2020)
- [Agents: An Open-source Framework for Autonomous Language Agents](https://mlsanity.com/paper/2309.07870/) (2023)
- [Proactive Human-Machine Conversation with Explicit Conversation Goals](https://mlsanity.com/paper/1906.05572/) (2019)
- [Target-Guided Open-Domain Conversation](https://mlsanity.com/paper/1905.11553/) (2019)
- [CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset](https://mlsanity.com/paper/2002.11893/) (2020)
- [Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning](https://mlsanity.com/paper/2305.13660/) (2023)
- [RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling](https://mlsanity.com/paper/2010.08738/) (2020)
- [Planning Like Human: A Dual-process Framework for Dialogue Planning](https://mlsanity.com/paper/2406.05374/) (2024)
- [OTTers: One-turn Topic Transitions for Open-Domain Dialogue](https://mlsanity.com/paper/2105.13710/) (2021)
- [Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curation](https://mlsanity.com/paper/2310.07397/) (2023)
- [Dialogue Planning via Brownian Bridge Stochastic Process for Goal-directed Proactive Dialogue](https://mlsanity.com/paper/2305.05290/) (2023)
- [X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents](https://mlsanity.com/paper/2306.17674/) (2023)
- [LARA: Linguistic-Adaptive Retrieval-Augmentation for Multi-Turn Intent Classification](https://mlsanity.com/paper/2403.16504/) (2024)
- [A Linguistic Comparison between Human and ChatGPT-Generated Conversations](https://mlsanity.com/paper/2401.16587/) (2024)
- [Follow Me: Conversation Planning for Target-driven Recommendation Dialogue Systems](https://mlsanity.com/paper/2208.03516/) (2022)
- [Target-Guided Open-Domain Conversation Planning](https://mlsanity.com/paper/2209.09746/) (2022)
- [NAPG: Non-Autoregressive Program Generation for Hybrid Tabular-Textual Question Answering](https://mlsanity.com/paper/2211.03462/) (2022)

## Built on by (most cited first, 12 of 12)

- [Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning](https://mlsanity.com/paper/2605.10923/) (2026)
- [DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision](https://mlsanity.com/paper/2510.05691/) (2025)
- [EvoSci: A Bio-Inspired Multi-Agent Framework for the Evolution of Scientific Discovery](https://mlsanity.com/paper/2605.24018/) (2026)
- [Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation](https://mlsanity.com/paper/2609.03727/) (2026)
- [When Actions Teach You to Think: Reasoning-Action Synergy via Reinforcement Learning in Conversational Agents](https://mlsanity.com/paper/2512.11277/) (2025)
- [CallBench: A Benchmark for Dual-Goal Coordination in Phone Call Assistants](https://mlsanity.com/paper/2607.22635/) (2026)
- [SOPRAG: Multi-view Graph Experts Retrieval for Industrial Standard Operating Procedures](https://mlsanity.com/paper/2602.01858/) (2026)
- [Online Self-Calibration Against Hallucination in Vision-Language Models](https://mlsanity.com/paper/2605.00323/) (2026)
- [MASS: Deep Research for Social Sciences with Memory-Augmented Social Simulation](https://mlsanity.com/paper/2606.09198/) (2026)
- [DS@GT ARC at eRisk 2026: Hybrid Multi-Agent LLM System with Structured Algorithmic Guidance for Conversational Depression Screening](https://mlsanity.com/paper/2607.16712/) (2026)
- [ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models](https://mlsanity.com/paper/2608.20355/) (2026)
- [When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models](https://mlsanity.com/paper/2608.30395/) (2026)

## Abstract (arXiv)

Dialogue agents powered by Large Language Models (LLMs) show superior performance in various tasks. Despite the better user understanding and human-like responses, their **lack of controllability** remains a key challenge, often leading to unfocused conversations or task failure. To address this, we introduce Standard Operating Procedure (SOP) to regulate dialogue flow. Specifically, we propose **ChatSOP**, a novel SOP-guided Monte Carlo Tree Search (MCTS) planning framework designed to enhance the controllability of LLM-driven dialogue agents. To enable this, we curate a dataset comprising SOP-annotated multi-scenario dialogues, generated using a semi-automated role-playing system with GPT-4o and validated through strict manual quality control. Additionally, we propose a novel method that integrates Chain of Thought reasoning with supervised fine-tuning for SOP prediction and utilizes SOP-guided Monte Carlo Tree Search for optimal action planning during dialogues. Experimental results demonstrate the effectiveness of our method, such as achieving a 27.95% improvement in action accuracy compared to baseline models based on GPT-3.5 and also showing notable gains for open-source models. Dataset and codes are publicly available.