Hidden Anchors in Multi-Agent LLM Deliberation

• URL: http://arxiv.org/abs/2606.19494v1
• Date: Wed, 17 Jun 2026 18:29:27 GMT
• Title: Hidden Anchors in Multi-Agent LLM Deliberation
• Abstract summary: 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.
• Score: 1.2031796234206138
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-agent LLM deliberation, where agents exchange and revise answers over several rounds, is increasingly used to improve reasoning and accuracy, yet how and why it works is rarely modelled. Such deliberation mirrors how humans reach decisions. As social animals we are pulled both by the group, the herd effect that classical opinion-dynamics models such as DeGroot and Friedkin--Johnsen capture, and by our own internal belief, which they do not. We model multi-agent deliberation as a closed-loop dynamical system in which each agent carries a hidden internal belief, its anchor, that continually pulls its opinion regardless of its neighbours. We show this anchor can be recovered from the deliberation alone, and that it explains a behaviour classical consensus rules forbid: an agent's confidence in the correct answer can climb past where any agent started, escaping the space (convexhull) formed by the initial beliefs. Checking whether the recovered anchor also predicts held-out runs (generalizes) gives a simple test for when a model is truly driven bysuch an anchor. Across three open-weight model families this is a spectrum, not all-or-nothing. All anchors' influence are about equally strongly, but they differ in where the anchor sits, and only when it sits far from the initial opinions does deliberation escape the hull and need the full closed-loop model.

Related papers

• A game theory for foundation models shows new paths to rational cooperation through similarity inference [56.53805518668248]
  We show that foundation model agents engaging in optimal planning consistently converge to stable cooperation.<n>By shifting from decoupled to embedded agency, these agents model themselves as part of the universe they inhabit.
  arXiv  Detail & Related papers  (2026-08-04T17:24:33Z)
• Divide, Deliberate, Decide: A Multi-Agent Framework for Fine-Grained Egocentric Action Recognition [86.4487145812318]
  Fine-grained action recognition in egocentric video is challenging for Vision-Language Models.<n>We propose Divide, Deliberate, Decide, a fully-local, zero-shot multi-agent framework.<n> Experiments show that our method positively improves zero-shot action recognition performance over the baseline.
  arXiv  Detail & Related papers  (2026-06-16T07:31:27Z)
• Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults [0.0]
  LLM agents increasingly act after consuming ranked external information streams such as social feeds, search results, retrieval contexts, and email queues.<n>We introduce a controlled protocol that holds the model, persona, topic, and final decision prompt fixed and varies only the composition and ordering of the posts an agent encounters.<n>We identify three response regimes: adversarial capitulation, default saturation, and a default-direction asymmetry in which a one-sided feed tips a decision the model was genuinely uncertain about.
  arXiv  Detail & Related papers  (2026-05-30T22:43:23Z)
• The Bystander Effect in Multi-Agent Reasoning: Quantifying Cognitive Loafing in Collaborative Interactions [6.357772907811544]
  We evaluate 22,500 deterministic trajectories across 3 dataset contexts with 3 state-of-the-art (SOTA) models.<n>We formalize the textitSovereignty Gap: models frequently compute the correct derivation internally but suffer Alignment Hallucinations''<n>We prove that multi-agent social load is strictly non-commutative; the "brand" identity of the Lead Anchor'' auditor disproportionately dictates the swarm's integrity.
  arXiv  Detail & Related papers  (2026-05-11T15:13:01Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• Backdoor Unlearning by Linear Task Decomposition [69.91984435094157]
  Foundation models are highly susceptible to adversarial perturbations and targeted backdoor attacks.<n>Existing backdoor removal approaches rely on costly fine-tuning to override the harmful behavior.<n>This raises the question of whether backdoors can be removed without compromising the general capabilities of the models.
  arXiv  Detail & Related papers  (2025-10-16T16:18:07Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• Consensus Is All You Need: Gossip-Based Reasoning Among Large Language Models [0.0]
  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.
  arXiv  Detail & Related papers  (2025-08-22T05:49:27Z)
• Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge [70.89799989428367]
  We conduct a systematic analysis of four diverse bias types: position bias, verbosity bias, chain-of-thought bias, and bandwagon bias.<n>We evaluate these biases across two widely adopted multi-agent LLM-as-Judge frameworks: Multi-Agent-Debate and LLM-as-Meta-Judge.
  arXiv  Detail & Related papers  (2025-05-26T03:56:41Z)
• Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty [47.95943057892318]
  Quantifying uncertainty in black-box LLMs is vital for reliable responses and scalable oversight.<n>We introduce DiverseAgentEntropy, a novel, theoretically-grounded method employing multi-agent interaction for uncertainty estimation.
  arXiv  Detail & Related papers  (2024-12-12T18:52:40Z)
• Bandit Social Learning: Exploration under Myopic Behavior [54.767961587919075]
  We study social learning dynamics motivated by reviews on online platforms.<n>Agents collectively follow a simple multi-armed bandit protocol, but each agent acts myopically, without regards to exploration.<n>We derive stark learning failures for any such behavior, and provide matching positive results.
  arXiv  Detail & Related papers  (2023-02-15T01:57:57Z)
• Agent-Based Simulation of Collective Cooperation: From Experiment to Model [0.0]
  We present an experiment to observe what happens when humans pass through a dense static crowd. We derive a model that incorporates agents' perception and cognitive processing of a situation that needs cooperation. Agents' ability to successfully get through a dense crowd emerges as an effect of the psychological model.
  arXiv  Detail & Related papers  (2020-05-26T13:29:08Z)

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.