# Exploring and Controlling Diversity in LLM-Agent Conversation

arXiv: https://arxiv.org/abs/2412.21102 · HTML: https://mlsanity.com/paper/2412.21102/

## 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 26 of its 36 references that are in the map.
- First posted on arXiv 30 Dec 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, 26 of 26)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus](https://mlsanity.com/paper/2104.08758/) (2021)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration](https://mlsanity.com/paper/2310.02170/) (2023)
- [LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals](https://mlsanity.com/paper/2411.10109/) (2024)
- [MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers](https://mlsanity.com/paper/2012.15828/) (2020)
- [Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies](https://mlsanity.com/paper/2308.03188/) (2023)
- [Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges](https://mlsanity.com/paper/2406.12624/) (2024)
- [Factuality Enhanced Language Models for Open-Ended Text Generation](https://mlsanity.com/paper/2206.04624/) (2022)
- [Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve](https://mlsanity.com/paper/2309.13638/) (2023)
- [Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects](https://mlsanity.com/paper/2401.03428/) (2024)
- [Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions](https://mlsanity.com/paper/2306.04140/) (2023)
- [System 2 Attention (is something you might need too)](https://mlsanity.com/paper/2311.11829/) (2023)
- [Humanoid Agents: Platform for Simulating Human-like Generative Agents](https://mlsanity.com/paper/2310.05418/) (2023)
- [SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation](https://mlsanity.com/paper/2305.11130/) (2023)
- [Cohesive Conversations: Enhancing Authenticity in Multi-Agent Simulated Dialogues](https://mlsanity.com/paper/2407.09897/) (2024)
- [On the Benchmarking of LLMs for Open-Domain Dialogue Evaluation](https://mlsanity.com/paper/2407.03841/) (2024)

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

- [Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?](https://mlsanity.com/paper/2508.17536/) (2025)
- [The Homogenizing Effect of Large Language Models on Human Expression and Thought](https://mlsanity.com/paper/2508.01491/) (2025)
- [When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning](https://mlsanity.com/paper/2510.07517/) (2025)
- [Localized Cultural Knowledge is Conserved and Controllable in Large Language Models](https://mlsanity.com/paper/2504.10191/) (2025)
- [Bayesian Social Deduction with Graph-Informed Language Models](https://mlsanity.com/paper/2506.17788/) (2025)
- [What Does It Take to Be a Good AI Research Agent? Studying the Role of Ideation Diversity](https://mlsanity.com/paper/2511.15593/) (2025)
- [Breaking the Martingale Curse: Multi-Agent Debate via Asymmetric Cognitive Potential Energy](https://mlsanity.com/paper/2603.06801/) (2026)
- [AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation](https://mlsanity.com/paper/2604.16625/) (2026)
- [M3MAD-Bench: Multi-Dimensional Evaluation of Multi-Agent Debate Across Domains and Modalities](https://mlsanity.com/paper/2601.02854/) (2026)
- [Convergence of Outputs When Two Large Language Models Interact in a Multi-Agentic Setup](https://mlsanity.com/paper/2512.06256/) (2025)
- [Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking](https://mlsanity.com/paper/2605.30107/) (2026)
- [BOUNDARY_SYNC: Measuring Communication-Induced Representational Coupling in Multi-Agent LLM Systems](https://mlsanity.com/paper/2607.01600/) (2026)

## Abstract (arXiv)

Controlling diversity in LLM-agent simulations is essential for balancing stability in structured tasks with variability in open-ended interactions. However, we observe that dialogue diversity tends to degrade over long-term simulations. To explore the role of prompt design in this phenomenon, we modularized the utterance generation prompt and found that reducing contextual information leads to more diverse outputs. Based on this insight, we propose Adaptive Prompt Pruning (APP), a novel method that allows users to control diversity via a single parameter, lambda. APP dynamically prunes prompt segments based on attention scores and is compatible with existing diversity control methods. We demonstrate that APP effectively modulates diversity through extensive experiments and propose a method to balance the control trade-offs. Our analysis reveals that all prompt components impose constraints on diversity, with the Memory being the most influential. Additionally, high-attention contents consistently suppress output diversity.