Pith. sign in

REVIEW 22 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2307.05300 v4 pith:IKJU6V3U submitted 2023-07-11 cs.AI cs.CL

Zhenhailong Wang , Shaoguang Mao , Wenshan Wu , Tao Ge , Furu Wei , Heng Ji This is my paper · ORCID
classification cs.AIcs.CL
keywords cognitivepersonassynergyllmsmultipleabilitiesagentcompared
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 22 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems

    cs.MA 2026-02 conditional novelty 6.0 of 10

    A perturbation-based framework measures how value opinions propagate through multi-agent LLM systems, revealing that susceptibility varies by value, model, and topology.

  2. KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows

    cs.DC 2025-07 conditional novelty 6.0 of 10

    KVFlow uses workflow-aware eviction priorities and overlapped KV prefetching to cut cache-miss latency in LLM multi-agent serving.

  3. Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systems

    cs.AR 2025-06 conditional novelty 6.0 of 10

    On three NIST crypto standards (AES, DSS, HMAC), Spec2RTL-Agent generates RTL via a multi-agent pipeline from pseudocode to Python to synthesizable C++, reporting 3/3 correct designs with about 4.3 human interventions...

  4. MasHost Builds It All: Autonomous Multi-Agent System Directed by Reinforcement Learning

    cs.MA 2025-06 conditional novelty 6.0 of 10

    MasHost uses reinforcement learning to autonomously construct query-adaptive multi-agent graphs, and its authors report the best average accuracy across six LLM benchmarks.

  5. From Virtual Agents to Robot Teams: A Multi-Robot Framework Evaluation in High-Stakes Healthcare Context

    cs.RO 2025-06 conditional novelty 6.0 of 10

    Adding a structured knowledge base raised a simulated CrewAI healthcare robot team's process score from 45.29% to 72.94%, but five failure modes, including false completion and poor recovery, persisted.

  6. Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks

    cs.CL 2025-01 conditional novelty 6.0 of 10

    A hierarchical multi-agent mobile assistant with a self-evolving memory of Tips and Shortcuts reports 22.1% absolute gains over prior mobile agents on a new 25-task long-horizon benchmark.

  7. Enhancing Zero-shot Chain of Thought Prompting via Uncertainty-Guided Strategy Selection

    cs.CL 2024-11 conditional novelty 6.0 of 10

    ZEUS selects chain-of-thought demonstrations by measuring answer uncertainty under perturbations, outperforming prior zero-shot prompting methods on four reasoning benchmarks.

  8. The Virtual Roundtable: Multi-Agent Personas Simulating the Dynamics of Human Brainstorming

    cs.HC 2026-04 conditional novelty 5.0 of 10

    Facilitated multi-agent personas can run divergent-then-convergent brainstorming; longer discussion deepens idea lineage and cross-persona absorption but does not increase idea diversity.

  9. P-CoT: A Pedagogically-motivated Participatory Chain-of-Thought Prompting for Phonological Reasoning in LLMs

    cs.CL 2025-07 reject novelty 5.0 of 10

    P-CoT prompting improves many LLM results on PhonologyBench tasks, but it does not consistently beat baselines across all models and tasks as the paper claims.

  10. SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation

    cs.AI 2025-06 reject novelty 5.0 of 10

    SciSage, a multi-agent reflection-based framework, is reported to outperform previous LLM survey generators on coherence and citation F1, while a new benchmark, SurveyScope, enables standardized evaluation.

  11. Exploring the Impact of Occupational Personas on Domain-Specific QA

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Profession-based personas slightly improve LLM accuracy on science QA, while occupational personality personas often reduce it, even when semantically related.

  12. Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision Making

    cs.CL 2025-05 conditional novelty 5.0 of 10

    A "catfish" agent that injects structured dissent into multi-agent LLM teams improves clinical question-answering accuracy by reducing premature consensus.

  13. TAGS: A Test-Time Generalist-Specialist Framework with Retrieval-Augmented Reasoning and Verification

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Without any parameter updates, a retrieval-augmented generalist-specialist agent pair with consistency-based verification raises accuracy on 862 hard medical QA questions for GPT-4o, DeepSeek-R1, and Qwen2.5-7B.

  14. Agent-Centric Projection of Prompting Techniques and Implications for Synthetic Training Data for Large Language Models

    cs.AI 2025-01 conditional novelty 5.0 of 10

    The paper defines linear and non-linear interaction contexts for LLMs and conjectures that prompting techniques and multi-agent systems are equivalent projections of the same patterns.

  15. DRF: LLM-AGENT Dynamic Reputation Filtering Framework

    cs.AI 2025-09 conditional novelty 4.0 of 10

    DRF combines an LLM rating network, a reputation update rule, and a UCB-style selection strategy to filter low-quality LLM agents during multi-agent task execution, reporting improved pass@1 and lower simulated cost o...

  16. LRCTI: A Large Language Model-Based Framework for Multi-Step Evidence Retrieval and Reasoning in Cyber Threat Intelligence Credibility Verification

    cs.CR 2025-07 reject novelty 4.0 of 10

    LRCTI uses an LLM to summarize threat reports, retrieve evidence in several rounds, and judge each claim credible or incredible, reporting strong F1 gains on CTI-200 and PolitiFact.

  17. Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies

    cs.CL 2025-07 reject novelty 4.0 of 10

    MoR fine-tunes Qwen2.5 on GPT-4o-selected reasoning templates, claiming up to 13.5% accuracy gains, but the reported gains are not robustly supported.

  18. Probing Large Language Models in Reasoning and Translating Complex Linguistic Puzzles

    cs.CL 2025-02 conditional novelty 4.0 of 10

    On Rosetta Stone linguistic puzzles, GPT-4 performs best with plain input-output prompting, outperforming chain-of-thought and multi-persona prompting on all tested metrics.

  19. Harnessing Multi-Agent LLMs for Complex Engineering Problem-Solving: A Framework for Senior Design Projects

    cs.MA 2025-01 conditional novelty 4.0 of 10

    A multi-agent LLM framework using eight specialized personas matched faculty scores on six capstone proposals with lower mean absolute error than a single-agent LLM, though the study is small.

  20. Human Behavior Simulation: Objectives, Methodologies, and Open Problems

    cs.HC 2024-11 accept novelty 4.0 of 10

    The paper reviews human behavior simulation research by behavior type, objective, and methodology, and identifies open problems such as multi-behavior joint simulation and LLM-driven agents.

  21. Evolution of Thought: Diverse and High-Quality Reasoning via Multi-Objective Optimization

    cs.NE 2024-11 reject novelty 4.0 of 10

    EoT applies multi-objective evolutionary search with crossover, mutation, and clustering to MLLM reasoning and reports improved Pass@K accuracy on MathVista, Math-Vision, and GSM8K.

  22. Town Hall Debate Prompting: Enhancing Logical Reasoning in LLMs through Multi-Persona Interaction

    cs.CL 2025-01 reject novelty 3.0 of 10

    A single LLM that debates itself via multiple personas and a final vote improves ZebraLogic puzzle accuracy for GPT-4o and Claude 3.5 but not for GPT-4o Mini.

Pith tools