Roundtable Policy: Improving Scientific Reasoning and Narratives through Confidence-Weighted Consensus of LLMs

• URL: http://arxiv.org/abs/2509.16839v1
• Date: Sat, 20 Sep 2025 23:31:53 GMT
• Title: Roundtable Policy: Improving Scientific Reasoning and Narratives through Confidence-Weighted Consensus of LLMs
• Authors: Yu Yao, Jiayi Dong, Ju Li, Yang Yang, Yilun Du,
• Abstract summary: We introduce Roundtable Policy, a complementary inference-time reasoning framework that performs inference through the weighted consensus of multiple large language models (LLMs)<n>Our findings indicate that this approach significantly enhances reasoning in complex heterogeneous scientific tasks and improves scientific narratives in terms of creativity, rigor, and logical coherence.<n>Our approach emphasizes structured and interpretable consensus rather than opaque convergence, while requiring only black-box access and uniform procedures.
• Score: 44.65081087151887
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have demonstrated remarkable capabilities not only in language generation but also in advancing scientific discovery. A growing body of work has explored ways to improve their reasoning, from self-consistency and chain-of-thought to multi-agent debate. Inspired by the dynamics of scientific committees and the "Society of Mind," we introduce Roundtable Policy, a complementary inference-time reasoning framework that performs inference through the weighted consensus of multiple LLMs. Our findings indicate that this approach significantly enhances reasoning in complex heterogeneous scientific tasks and improves scientific narratives in terms of creativity, rigor, and logical coherence, while reducing hallucinations that single models are prone to. Our approach emphasizes structured and interpretable consensus rather than opaque convergence, while requiring only black-box access and uniform procedures, making it broadly applicable to multi-LLM reasoning.

Related papers

• ElecTwit: A Framework for Studying Persuasion in Multi-Agent Social Systems [0.0]
  ElecTwit is a simulation framework designed to study persuasion within multi-agent systems.<n>We observed the comprehensive use of 25 specific persuasion techniques across most tested LLMs.
  arXiv  Detail & Related papers  (2026-01-02T22:10:09Z)
• Large Language Models for Scientific Idea Generation: A Creativity-Centered Survey [14.135916464098317]
  Large language models (LLMs) have emerged as promising generators of scientific ideas.<n>This survey examines how different approaches creativity with scientific soundness are produced.
  arXiv  Detail & Related papers  (2025-11-05T07:50:43Z)
• Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning [53.82037883518254]
  We introduce SciReas, a diverse suite of existing benchmarks for scientific reasoning tasks.<n>We then propose KRUX, a probing framework for studying the distinct roles of reasoning and knowledge in scientific tasks.
  arXiv  Detail & Related papers  (2025-08-26T17:04:23Z)
• CTRLS: Chain-of-Thought Reasoning via Latent State-Transition [57.51370433303236]
  Chain-of-thought (CoT) reasoning enables large language models to break down complex problems into interpretable intermediate steps.<n>We introduce groundingS, a framework that formulates CoT reasoning as a Markov decision process (MDP) with latent state transitions.<n>We show improvements in reasoning accuracy, diversity, and exploration efficiency across benchmark reasoning tasks.
  arXiv  Detail & Related papers  (2025-07-10T21:32:18Z)
• Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models [79.52467430114805]
  Reasoning lies at the heart of intelligence, shaping the ability to make decisions, draw conclusions, and generalize across domains.<n>In artificial intelligence, as systems increasingly operate in open, uncertain, and multimodal environments, reasoning becomes essential for enabling robust and adaptive behavior.<n>Large Multimodal Reasoning Models (LMRMs) have emerged as a promising paradigm, integrating modalities such as text, images, audio, and video to support complex reasoning capabilities.
  arXiv  Detail & Related papers  (2025-05-08T03:35:23Z)
• Advancing AI-Scientist Understanding: Multi-Agent LLMs with Interpretable Physics Reasoning [0.7499722271664147]
  Large Language Models (LLMs) are playing an increasingly important role in physics research by assisting with symbolic manipulation, numerical computation, and scientific reasoning.<n>We introduce a novel multi-agent LLM physicist framework that fosters collaboration between AI and human scientists through three key modules.<n>A case study demonstrates that our approach significantly improves interpretability, enables systematic validation, and enhances human-AI collaboration in physics problem-solving and discovery.
  arXiv  Detail & Related papers  (2025-04-02T17:13:16Z)
• Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative Analysis [27.745896682856092]
  We introduce Tree-of-Debate (ToD), a framework which converts scientific papers into personas that debate their respective novelties.<n>ToD dynamically constructs a debate tree, enabling fine-grained analysis of independent novelty arguments within scholarly articles.
  arXiv  Detail & Related papers  (2025-02-20T17:43:40Z)
• Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning [51.11965014462375]
  Multimodal Large Language Models (MLLMs) integrate text, images, and other modalities.<n>This paper argues that MLLMs can significantly advance scientific reasoning across disciplines such as mathematics, physics, chemistry, and biology.
  arXiv  Detail & Related papers  (2025-02-05T04:05:27Z)
• In Defence of Post-hoc Explainability [0.0]
  We introduce Computational Interpretabilism (CI) as a philosophical framework for post-hoc interpretability in scientific AI.<n> Drawing parallels with human expertise, where post-hoc rationalisation coexists with reliable performance, CI establishes that scientific knowledge emerges through structured model interpretation when properly bounded by empirical validation.
  arXiv  Detail & Related papers  (2024-12-23T06:22:03Z)
• LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery [141.39722070734737]
  We propose to enhance the knowledge-driven, abstract reasoning abilities of Large Language Models with the computational strength of simulations. We introduce Scientific Generative Agent (SGA), a bilevel optimization framework. We conduct experiments to demonstrate our framework's efficacy in law discovery and molecular design.
  arXiv  Detail & Related papers  (2024-05-16T03:04:10Z)
• LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play [43.55248812883912]
  Large language models (LLMs) have shown exceptional proficiency in natural language processing but often fall short of generating creative and original responses to open-ended questions. We propose LLM Discussion, a three-phase discussion framework that facilitates vigorous and diverging idea exchanges. We evaluate the efficacy of the proposed framework with the Alternative Uses Test, Similarities Test, Instances Test, and Scientific Creativity Test.
  arXiv  Detail & Related papers  (2024-05-10T10:19:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.