paper-with-me

홈 › Papers

The impact of multi-agent debate protocols on debate quality: a controlled case study

2026-03-28 · Ramtin Zargari Marandi arxiv

In multi-agent debate (MAD) systems, performance gains are often reported; however, because the debate protocol (e.g., number of agents, rounds, and aggregation rule) is typically held fixed while model-related factors vary, it is difficult to disentangle protocol effects from model effects. To isolate these effects, we compare three main protocols, Within-Round (WR; agents see only current-round contributions), Cross-Round (CR; full prior-round context), and novel Rank-Adaptive Cross-Round (RA-CR; dynamically reorders agents and silences one per round via an external judge model), against a No-Interaction baseline (NI; independent responses without peer visibility). In a controlled macroeconomic case study (20 diverse events, five random seeds, matched prompts/decoding), RA-CR achieves faster convergence than CR, WR shows higher peer-referencing, and NI maximizes Argument Diversity (unaffected across the main protocols). These results reveal a trade-off between interaction (peer-referencing rate) and convergence (consensus formation), confirming protocol design matters. When consensus is prioritized, RA-CR outperforms the others.

📄 PDF Abstract BibTeX arXiv:2603.28813

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Voting or Consensus? Decision-Making in Multi-Agent Debate

2025-02-26 · Lars Benedikt Kaesberg, Jonas Becker, Jan Philip Wahle, Terry Ruas 외

Much of the success of multi-agent debates depends on carefully choosing the right parameters. The decision-making protocol stands out as it can highly impact final model answers, depending on how decisions are reached. …

Decision MakingMMLUStrategyQA

MALLM: Multi-Agent Large Language Models Framework

2025-09-15 · Jonas Becker, Lars Benedikt Kaesberg, Niklas Bauer, Jan Philip Wahle 외 arxiv

Multi-agent debate (MAD) has demonstrated the ability to augment collective intelligence by scaling test-time compute and leveraging expertise. Current frameworks for multi-agent debate are often designed towards tool us…

Learning from Self-Debate: Preparing Reasoning Models for Multi-Agent Debate

2026-01-29 · Chenxi Liu, Yanshuo Chen, Ruibo Chen, Tianyi Xiong 외 arxiv

The reasoning abilities of large language models (LLMs) have been substantially improved by reinforcement learning with verifiable rewards (RLVR). At test time, collaborative reasoning through Multi-Agent Debate (MAD) ha…

Reinforcement Learning

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 …

Towards Scalable Oversight with Collaborative Multi-Agent Debate in Error Detection

2025-10-23 · Yongqiang Chen, Gang Niu, James Cheng, Bo Han 외 arxiv

Accurate detection of errors in large language models (LLM) responses is central to the success of scalable oversight, or providing effective supervision to superhuman intelligence. Yet, self-diagnosis is often unreliabl…