paper-with-me

Papers

Debate2Create: Robot Co-design via Multi-Agent LLM Debate

2025-10-29 · Kevin Qiu, Marek Cygan arxiv

We introduce Debate2Create (D2C), a multi-agent LLM framework that formulates robot co-design as structured, iterative debate grounded in physics-based evaluation. A design agent and control agent engage in a thesis-antithesis-synthesis loop, while criterion-specific LLM judges provide multi-objective feedback to steer exploration. Across five MuJoCo locomotion benchmarks, D2C achieves the highest default-normalized score among the evaluated LLM-based and black-box baselines, with gains up to 3.2x on Ant and nearly 9x on Swimmer. Iterative debate yields 18-35% gains over compute-matched zero-shot generation, and D2C-generated rewards transfer to default morphologies in 4/5 tasks. These results suggest that structured, simulator-grounded multi-agent interaction is a useful mechanism for joint morphology-reward optimization under a fixed-topology, per-candidate-RL protocol. Project page: debate2create.github.io.

📄 PDF Abstract BibTeX arXiv:2510.25850

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution

2025-07-31 · Han Li, Yuling Shi, Shaoxin Lin, Xiaodong Gu 외 arxiv

Issue resolution has made remarkable progress thanks to the advanced reasoning capabilities of large language models (LLMs). Recently, agent-based frameworks such as SWE-agent have further advanced this progress by enabl…

Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate

2026-04-27 · John Seon Keun Yi, Aaron Mueller, Dokyun Lee arxiv

Multi-agent debate has been shown to improve reasoning in large language models (LLMs). However, it is compute-intensive, requiring generation of long transcripts before answering questions. To address this inefficiency,…

Can LLMs Beat Humans in Debating? A Dynamic Multi-agent Framework for Competitive Debate

2024-08-08 · Yiqun Zhang, Xiaocui Yang, Shi Feng, Daling Wang 외

Competitive debate is a complex task of computational argumentation. Large Language Models (LLMs) suffer from hallucinations and lack competitiveness in this field. To address these challenges, we introduce Agent for Deb…

Relational Priors as Convergence Pressure in LLM-Based Multi-Agent Systems

2026-08-04 · Ming Shen, Chao Shang, Sadat Shahriar, Devang Kulshreshtha 외 arxiv

Large language model-based multi-agent systems (LLM-MAS) are designed through roles, debate protocols, and aggregation rules. These choices create implicit social expectations: agents may be expected to trust, challenge,…

Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate

2025-09-27 · Binwei Yao, Chao Shang, Wanyu Du, Jianfeng He 외 arxiv

Large language models (LLMs) often display sycophancy, a tendency toward excessive agreeability. This behavior poses significant challenges for multi-agent debating systems (MADS) that rely on productive disagreement to …