The study evaluates multi‑agent debate (MAD) in small language models, testing whether cognitive diversity—via personas, sampling temperature, or model identity—drives performance gains. Across 23 models, five tasks, and over 5,500 runs, MAD consistently outperforms single‑model inference but, when matched for generation budget, it ties or falls behind self‑consistency sampling, with persona prompting actually reducing accuracy. The authors find that MAD’s benefits largely stem from the first answer exchange and that many reported gains are due to ensemble‑sampling effects rather than true diversity, highlighting the need for budget‑matched, contamination‑checked baselines. whyItMatters":"The findings clarify that MAD’s perceived advantages may be overestimated and that future debate mechanisms must be evaluated against rigorous, budget‑matched baselines to ensure genuine performance improvements."
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.
arXiv:2609.08016v1 Announce Type: new Abstract: Multi-agent debate, in which several LLMs exchange arguments before answering, is widely assumed to improve answer quality by surfacing genuine disagre...
arXiv:2608.23541v1 Announce Type: cross Abstract: Does multi-agent LLM interaction help or hurt? Some work reports gains from debate (Du et al., 2024), critique loops (Chen et al., 2025), and mixture...
MABPD (Multi‑Agent Bias Probing & Detection) is a training‑free pipeline that uses three specialized large language model agents to analyze news articles from complementary perspectives and resolve disagreements via a Structured Argument Debate (SAD) protocol. SAD imposes an asymmetric burden of proof—biased claims lacking grounded textual evidence receive zero weight—along with role‑weighted voting and post‑consensus verification, replacing task‑specific supervised decision boundaries. Ablation studies show that the debate module alone accounts for up to a 10.6‑point F1 gain, and on the BABE benchmark MABPD attains 83.4% macro F1, within 0.7 percentage points of the supervised state‑of‑the‑art, while achieving 75.0% zero‑shot accuracy on the SemEval 2019 HyperPartisan corpus.
arXiv:2510. 20963v2 Announce Type: replace Abstract: Multi-agent debate (MAD) was proposed as a promising approach for ensembling the wisdom of multiple large language models (LLMs) to improve reasoning and provide effective supervision to superhuman LLMs.
arXiv:2601. 05746v2 Announce Type: replace Abstract: Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving.
arXiv:2604. 11840v3 Announce Type: replace-cross Abstract: Language models are increasingly used to simulate people: survey respondents, negotiators, stakeholders in policy exercises.
arXiv:2606. 13197v1 Announce Type: new Abstract: Multi-agent debate (MAD) can improve large language model reasoning, but fixed debate pipelines often waste computation and can amplify correlated errors among similar agents.
arXiv:2609.15849v1 Announce Type: cross Abstract: Can LLMs reason through new information like humans, or do they merely retrieve cached opinions? This is critical for silicon sampling, where LLM per...
arXiv:2606. 02866v1 Announce Type: new Abstract: When does multi-agent debate help data cleaning, and when does it hurt?
Meta-Moderator is a learnable framework that treats moderation as a meta‑cognitive process, monitoring debate utility, controlling deliberation, and adjudicating final answers. It is trained independently of the debaters through outcome‑driven policy optimization, allowing dynamic regulation of debate rather than relying on fixed budgets or untrained judges. Across five benchmarks, Meta‑Moderator outperforms common decision layers, transfers across tasks and system configurations, and selectively allocates debate to reduce mis‑aggregation after informative hypotheses appear.
arXiv:2606. 02646v1 Announce Type: cross Abstract: Inference-time multi-agent LLM scaling lacks a shared unit: counting nominal agents conflates cost with independent evidence.