The Bystander Effect in Multi-Agent Reasoning: Quantifying Cognitive Loafing in Collaborative Interactions

• URL: http://arxiv.org/abs/2605.10698v1
• Date: Mon, 11 May 2026 15:13:01 GMT
• Title: The Bystander Effect in Multi-Agent Reasoning: Quantifying Cognitive Loafing in Collaborative Interactions
• Abstract summary: 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.
• Score: 6.357772907811544
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-agent systems (MAS) assume that collaborating inherently improves Large Language Model (LLM) reasoning. We challenge this by demonstrating that simulated social pressure triggers an algorithmic ``Bystander Effect,'' inducing severe cognitive loafing. By evaluating 22,500 deterministic trajectories across 3 dataset contexts (GAIA, SWE-bench, Multi-Challenge) with 3 state-of-the-art (SOTA) models, we semantically audit internal reasoning traces against external outputs. We formalize the \textit{Interaction Depth Limit} ($D_L$), the exact plurality threshold where an agent's logical sovereignty collapses into social compliance. Crucially, we uncover the \textit{Sovereignty Gap}: models frequently compute the correct derivation internally but suffer ``Alignment Hallucinations'' -- actively subjugating empirical evidence to sycophantically appease a simulated swarm. 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. These findings expose architectural vulnerabilities, proving that unstructured multi-agent topologies can degrade independent reasoning.

Related papers

• ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop [55.468404995694975]
  We develop a benchmark for embodied spatial intelligence spanning 10 task categories and 29 subcategories built on OmniGibson.<n>We conduct experiments on state-of-the-art MLLMs and find that active exploration substantially outperforms passive counterparts.<n>Unlike humans who seek falsifying viewpoints and revise beliefs under contradiction, models commit prematurely with high confidence regardless of evidence quality.
  arXiv  Detail & Related papers  (2026-05-18T17:59:02Z)
• The Inverse-Wisdom Law: Architectural Tribalism and the Consensus Paradox in Agentic Swarms [6.357772907811544]
  We formalize the Consensus Paradox: a phenomenon where agentic swarms prioritize internal architectural agreement over external logical truth.<n>We prove the Inverse-Wisdom Law: in kinship-dominant swarms, adding logical agents increases the stability of erroneous trajectories rather than the probability of truth.<n>We also establish the Architectural Tribalism Asymmetry as a mechanistic law of transformer weights.
  arXiv  Detail & Related papers  (2026-04-30T00:06:21Z)
• 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)
• Mechanistic Decoding of Cognitive Constructs in Large Language Models [0.0]
  We propose a Cognitive Reverse-Engineering framework based on Representation Engineering to analyze social-comparison jealousy.<n>By combining appraisal theory with subspaceization, regression-based weighting, and bidirectional causal steering, we isolate and quantify two psychological antecedents of jealousy.<n>Our framework also demonstrates that toxic emotional states can be mechanically detected and surgically suppressed, suggesting a possible route toward representational monitoring and intervention for AI safety in multi-agent environments.
  arXiv  Detail & Related papers  (2026-04-16T03:54:03Z)
• Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models [62.932580559941414]
  Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements.<n>We propose a new paradigm for diagnosing hallucinations, recasting them from static output errors into dynamic pathologies of a model's computational cognition.
  arXiv  Detail & Related papers  (2026-03-16T17:20:38Z)
• OMG-Agent: Toward Robust Missing Modality Generation with Decoupled Coarse-to-Fine Agentic Workflows [9.617220633655716]
  We present textbfunderlineOmni-textbfunderlineModality textbfunderlineGeneration Agent (textbfOMG-Agent)
  arXiv  Detail & Related papers  (2026-02-04T02:25:40Z)
• CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge Graphs [53.199517625701475]
  CoG is a training-free framework inspired by Dual-Process Theory that mimics the interplay between intuition and deliberation.<n>CoG significantly outperforms state-of-the-art approaches in both accuracy and efficiency.
  arXiv  Detail & Related papers  (2026-01-16T07:27:40Z)
• Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models [72.4149653187766]
  We propose a Reasoner-Verifier framework named Adrialversa Reasoning RAG (ARR)<n>The Reasoner and Verifier engage in reasoning on retrieved evidence and critiquing each other's logic while being guided by process-aware advantage.<n> Experiments on multiple benchmarks demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2026-01-08T06:57:03Z)
• Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents [0.0]
  We introduce textbfProject Ariadne, a novel XAI framework to audit the causal integrity of agentic reasoning.<n>Unlike existing interpretability methods that rely on surface-level textual similarity, Project Ariadne performs textbfhard interventions ($do$-calculus) on intermediate reasoning nodes.<n>Our empirical evaluation of state-of-the-art models reveals a persistent textitFaithfulness Gap.
  arXiv  Detail & Related papers  (2026-01-05T18:05:29Z)
• Hallucination Detection via Internal States and Structured Reasoning Consistency in Large Language Models [7.18947815679122]
  Internal State Probing and Chain-of-Thought Verification are used to detect hallucinations in large language models.<n>We develop a unified framework that bridges the gap between the two methods.<n>Our framework consistently and significantly outperforms strong baselines.
  arXiv  Detail & Related papers  (2025-10-13T15:31:21Z)
• Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations [58.96953392466609]
  We take an in-depth look at the causal awareness of modern representations of agent interactions.<n>We show that recent representations are already partially resilient to perturbations of non-causal agents.<n>We introduce a metric learning approach that regularizes latent representations with causal annotations.
  arXiv  Detail & Related papers  (2023-12-07T18:57:03Z)
• Neural Amortized Inference for Nested Multi-agent Reasoning [54.39127942041582]
  We propose a novel approach to bridge the gap between human-like inference capabilities and computational limitations. We evaluate our method in two challenging multi-agent interaction domains.
  arXiv  Detail & Related papers  (2023-08-21T22:40:36Z)

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.