Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration

By Zhenhailong Wang, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, Heng Ji. North American Chapter of the Association for Computational Linguistics, 2023

302 citations recorded by the source corpus.

Human intelligence thrives on cognitive synergy, where collaboration among different minds yield superior outcomes compared to isolated individuals. In this work, we propose Solo Performance Prompting (SPP), which transforms a single LLM into a cognitive synergist by engaging in multi-turn self-collaboration with multiple personas. A cognitive synergist is an intelligent agent that collaboratively combines multiple minds’ strengths and knowledge to enhance problem-solving in complex tasks. By dynamically identifying and simulating different personas based on task inputs, SPP unleashes the potential of cognitive synergy in LLMs. Our in-depth analysis shows that assigning multiple fine-grained personas in LLMs improves problem-solving abilities compared to using a single or fixed number of personas. We evaluate SPP on three challenging tasks: Trivia Creative Writing, Codenames Collaborative, and Logic Grid Puzzle, encompassing both knowledge-intensive and reasoning-intensive types. Unlike previous works, such as Chain-of-Thought, that solely enhance the reasoning abilities in LLMs, experimental results demonstrate that SPP effectively reduces factual hallucination, and maintains strong reasoning capabilities. Additionally, comparative experiments show that cognitive synergy only emerges in GPT-4 and does not appear in less capable models, such as GPT-3.5-turbo and Llama2-13b-chat, which draws an interesting analogy to human development. Code, data, and prompts can be found at: https://github.com/MikeWangWZHL/Solo-Performance-Prompting.git.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/434b9f9bc71c935e4a46a1aff36a8cc4c22d9afa

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Weize Chen
2. Zili Wang
3. Chi-Min Chan
4. Wei Xue
5. Jie Fu
6. Shan Zhang
7. Jianxuan Yu
8. Chenglin Wu

Citations in the corpus

• ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate (2023, methodology): “The second part and the third part of Table 1 show the results of FairEval’s method and the results of our proposed method respectively.”
• Multi-Agent Collaboration Mechanisms: A Survey of LLMs (2025, unknown): “Storyboardgeneration [132] 4.4.1 Centralized Structure.”
• MetaGPT: Meta Programming for Multi-Agent Collaborative Framework (2023, background): “However, existing systems oversimplify real-world complexities [10, 11, 12, 13, 14, 15, 16], struggling to collaborate solely through conversation and tools, facing issues of scalability,inconsistency, and inefficiency[17].”
• Large language models empowered agent-based modeling and simulation: a survey and perspectives (2023, unknown): “This segmentation leverages the LLM ’ s training corpus to recognize patterns and apply relevant knowledge ef fi ciently (Park et al., 2023; Sun et al., 2024); Wang et al., 2024a; Zhu et al., 2023c).”