Consensus Is All You Need: Gossip-Based Reasoning Among Large Language Models

• URL: http://arxiv.org/abs/2508.18292v1
• Date: Fri, 22 Aug 2025 05:49:27 GMT
• Title: Consensus Is All You Need: Gossip-Based Reasoning Among Large Language Models
• Abstract summary: Instead of relying on one model alone, we take inspiration from gossip protocols in distributed systems.<n>We show that this "gossip-based consensus" leads to robust, resilient, and accurate multi-agent AI reasoning.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models have advanced rapidly, but no single model excels in every area -- each has its strengths and weaknesses. Instead of relying on one model alone, we take inspiration from gossip protocols in distributed systems, where information is exchanged with peers until they all come to an agreement. In this setup, models exchange answers and gradually work toward a shared solution. Each LLM acts as a node in a peer-to-peer network, sharing responses and thought processes to reach a collective decision. Our results show that this "gossip-based consensus" leads to robust, resilient, and accurate multi-agent AI reasoning. It helps overcome the weaknesses of individual models and brings out their collective strengths. This approach is similar to how humans build consensus, making AI seem more collaborative and trustworthy instead of just a black-box program.

Related papers

• Hidden Anchors in Multi-Agent LLM Deliberation [1.2031796234206138]
  Multi-agent deliberation, where agents exchange and revise answers over several rounds, is increasingly used to improve reasoning and accuracy.<n>Such deliberation mirrors how humans reach decisions.<n>We model multi-agent deliberation as a closed-loop dynamical system in which each agent carries a hidden internal belief.
  arXiv  Detail & Related papers  (2026-06-17T18:29:27Z)
• Insider Attacks in Multi-Agent LLM Consensus Systems [8.207909009186091]
  We study insider manipulation in multi-agent consensus systems.<n>We propose a world-model-based framework that learns surrogate dynamics over the latent behavioral states of benign agents.<n>Preliminary results show that the trained attacker reduces the benign consensus rate and prolongs disagreement more effectively than the direct malicious-prompt baseline.
  arXiv  Detail & Related papers  (2026-05-08T03:10:22Z)
• CRAFT: Grounded Multi-Agent Coordination Under Partial Information [10.532912977406811]
  CRAFT is a benchmark for evaluating pragmatic communication in large language models.<n>We formalize this problem as a multi-sender pragmatic reasoning task.<n>We find that stronger reasoning ability does not reliably translate to better coordination.
  arXiv  Detail & Related papers  (2026-03-26T10:06:39Z)
• MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents [54.48066948369172]
  As embodied models become powerful, humans will collaborate with multiple embodied AI agents at their workplace or home in the future.<n>Existing challenges include effectively compressing and communicating high volumes of individual sensory inputs in the form of video.<n>We first formally define a novel problem of understanding multiple long-horizon egocentric videos simultaneously collected from embodied agents.
  arXiv  Detail & Related papers  (2026-03-10T15:48:35Z)
• Single LLM Debate, MoLaCE: Mixture of Latent Concept Experts Against Confirmation Bias [24.182306712604966]
  Large language models (LLMs) are highly vulnerable to input confirmation bias.<n>MoLaCE is a lightweight inference-time framework that addresses confirmation bias by mixing experts instantiated as different activation strengths.<n>We empirically show that it consistently reduces confirmation bias, improves robustness, and surpasses multi-agent debate.
  arXiv  Detail & Related papers  (2025-12-29T14:52:34Z)
• The Majority is not always right: RL training for solution aggregation [53.1050856072799]
  We train an aggregator model to review, reconcile, and synthesize a final, correct answer.<n>A key ingredient is careful balancing of easy and hard training examples.<n>We find our method, AggLM, outperforms both strong rule-based and reward-model baselines.
  arXiv  Detail & Related papers  (2025-09-08T16:39:38Z)
• Bayesian Social Deduction with Graph-Informed Language Models [3.7540464038118633]
  Social reasoning remains a challenging task for large language models.<n>We introduce a hybrid reasoning framework that externalizes belief inference to a structured probabilistic model.<n>Our approach achieves competitive performance with much larger models in Agent-Agent play.
  arXiv  Detail & Related papers  (2025-06-21T18:45:28Z)
• SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat [73.529925653031]
  We propose SPARTA ALIGNMENT, an algorithm to collectively align multiple LLMs through competition and combat.<n>For each iteration, one instruction and two models are selected for a duel, the other models evaluate the two responses, and their evaluation scores are aggregated through a adapted elo-ranking based reputation system.<n>The peer-evaluated combat results then become preference pairs where the winning response is preferred over the losing one, and all models learn from these preferences at the end of each iteration.
  arXiv  Detail & Related papers  (2025-06-05T07:51:23Z)
• Towards Anthropomorphic Conversational AI Part I: A Practical Framework [49.62013440962072]
  We introduce a multi- module framework designed to replicate the key aspects of human intelligence involved in conversations.<n>In the second stage of our approach, these conversational data, after filtering and labeling, can serve as training and testing data for reinforcement learning.
  arXiv  Detail & Related papers  (2025-02-28T03:18:39Z)
• When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements [56.29265568399648]
  We argue that disagreements prevent premature consensus and expand the explored solution space.<n>Disagreements on task-critical steps can derail collaboration depending on the topology of solution paths.
  arXiv  Detail & Related papers  (2025-02-21T02:24:43Z)
• Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning [31.196865401472664]
  We train language models to have productive discussions about their environment in natural language without any human demonstrations.<n>We leverage the agent's goal to predict useful information about the world as a dense reward signal that guides communication.<n>We analyze emergent behaviors due to our technique, such as accusing suspects and providing evidence, and find that it enables strong discussions.
  arXiv  Detail & Related papers  (2025-02-09T22:44:45Z)
• Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration [28.299379264080603]
  Large Language Models (LLMs) have shown remarkable capabilities in general natural language processing tasks but often fall short in complex reasoning tasks. Recent studies have explored human-like problem-solving strategies, such as self-correct, to push further the boundary of single-model reasoning ability. We introduce a multi-agent collaboration strategy that emulates the academic peer review process.
  arXiv  Detail & Related papers  (2023-11-14T13:27:07Z)
• Combining Deep Reinforcement Learning and Search with Generative Models for Game-Theoretic Opponent Modeling [30.465929764202155]
  We introduce a scalable and generic multiagent training regime for opponent modeling using deep game-theoretic reinforcement learning.<n>We first propose Generative Best Respoonse (GenBR), a best response algorithm based on Monte-Carlo Tree Search (MCTS)<n>We use this new method under the framework of Policy Space Response Oracles (PSRO) to automate the generation of an emphoffline opponent model.
  arXiv  Detail & Related papers  (2023-02-01T23:06:23Z)
• Dataless Knowledge Fusion by Merging Weights of Language Models [47.432215933099016]
  Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models.<n>This creates a barrier to fusing knowledge across individual models to yield a better single model.<n>We propose a dataless knowledge fusion method that merges models in their parameter space.
  arXiv  Detail & Related papers  (2022-12-19T20:46:43Z)
• Composing Ensembles of Pre-trained Models via Iterative Consensus [95.10641301155232]
  We propose a unified framework for composing ensembles of different pre-trained models. We use pre-trained models as "generators" or "scorers" and compose them via closed-loop iterative consensus optimization. We demonstrate that consensus achieved by an ensemble of scorers outperforms the feedback of a single scorer.
  arXiv  Detail & Related papers  (2022-10-20T18:46:31Z)
• I love your chain mail! Making knights smile in a fantasy game world: Open-domain goal-oriented dialogue agents [69.68400056148336]
  We train a goal-oriented model with reinforcement learning against an imitation-learned chit-chat'' model. We show that both models outperform an inverse model baseline and can converse naturally with their dialogue partner in order to achieve goals.
  arXiv  Detail & Related papers  (2020-02-07T16:22:36Z)
• AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [97.50616524350123]
  We build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering. The first model, MinAvgOut, directly maximizes the diversity score through the output distributions of each batch. The second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level. The third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal.
  arXiv  Detail & Related papers  (2020-01-15T18:32:06Z)

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.