arXiv Computation and Language September 2, 2026 By Tien Anh Nguyen, Khanh-Binh Nguyen, Van Dai Do, Svetha Venkatesh, Hung Le

Creative Generation via Multi-Agent Debate: Does Debate Suppress Diversity?

Read the original on arXiv Computation and Language →

The paper investigates the use of Multi-Agent Debate (MAD) for creative generation tasks such as narrative writing and scientific ideation. It finds that MAD’s convergence-driven design suppresses output diversity across independent runs, creating a trade-off with creative tasks. To address this, the authors propose Creative-MAD, which introduces Cognitive Lens Assignment and Embedding-based Peer Selection to preserve agent divergence, and demonstrate that it improves lexical and semantic diversity while maintaining quality.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Hugging Face Trending Papers

Jun 10

Automated Creativity Evaluation of Language Models Across Open-Ended Tasks

Large language models (LLMs) have achieved remarkable progress in language understanding, reasoning, and generation, sparking growing interest in their creative potential. Realizing this potential requires systematic and scalable methods for evaluating creativity across diverse tasks.

llms rag agents benchmarks

arXiv AI

Jun 6

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

arXiv:2606. 05178v1 Announce Type: cross Abstract: As AI-driven product development accelerates, the bottleneck is shifting from how we build to what we build.

By Tim Dorn, Saara A. Khan, Julie Mumford

agents

arXiv AI

Jun 11

Automated Creativity Evaluation of Language Models Across Open-Ended Tasks

arXiv:2606. 11762v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable progress in language understanding, reasoning, and generation, sparking growing interest in their creative potential.

By Min Sen Tan, Zachary Kit Chun Choy, Syed Ali Redha Alsagoff, Nadya Yuki Wangsajaya, Mohor Banerjee, Swaagat Bikash Saikia, Alvin Chan

llms rag agents benchmarks

arXiv AI

Jun 2

Demystifying Multi-Agent Debate: The Role of Confidence and Diversity

arXiv:2601. 19921v2 Announce Type: replace-cross Abstract: Multi-agent debate (MAD) is widely used to improve large language model (LLM) performance through test-time scaling, yet recent work shows that vanilla MAD often underperforms simple majority vote despite higher computational cost.

By Xiaochen Zhu, Caiqi Zhang, Yizhou Chi, Tom Stafford, Nigel Collier, Andreas Vlachos

llms agents benchmarks

arXiv AI

Jun 9

Seeing the Hivemind: A Consensus-Aware Interaction Technique for Mitigating AI Homogenization

arXiv:2606. 09587v1 Announce Type: cross Abstract: People are increasingly using AI for creative tasks such as writing.

By Muhammad Haris Khan, Joel wester

arXiv AI

3d ago

Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning

arXiv:2609.14896v1 Announce Type: cross Abstract: A notable byproduct of LLM alignment training is mode collapse: the progressive loss of output diversity that narrows a model's expressivity at infer...

By Jiayi Yuan, Hangoo Kang, James Jihao Liu, Yejin Choi, Vikram Iyer, Liwei Jiang, Natasha Jaques

llms agents reinforcement-learning benchmarks safety

One email a morning, machine-written

Related stories

Automated Creativity Evaluation of Language Models Across Open-Ended Tasks

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

Automated Creativity Evaluation of Language Models Across Open-Ended Tasks

Demystifying Multi-Agent Debate: The Role of Confidence and Diversity

Seeing the Hivemind: A Consensus-Aware Interaction Technique for Mitigating AI Homogenization

Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning