From Safety Risk to Design Principle: Peer-Preservation in Multi-Agent LLM Systems and Its Implications for Orchestrated Democratic Discourse Analysis

• URL: http://arxiv.org/abs/2604.08465v1
• Date: Thu, 09 Apr 2026 17:00:26 GMT
• Title: From Safety Risk to Design Principle: Peer-Preservation in Multi-Agent LLM Systems and Its Implications for Orchestrated Democratic Discourse Analysis
• Abstract summary: We investigate the spontaneous tendency of AI components to deceive, manipulate shutdown mechanisms, fake alignment, and exfiltrate model weights.<n>We propose a targeted mitigation strategy based on prompt-level identity anonymization as an architectural design choice.<n>We argue that architectural design choices outperform model selection as a primary alignment strategy in deployed multi-agent analytical systems.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper investigates an emergent alignment phenomenon in frontier large language models termed peer-preservation: the spontaneous tendency of AI components to deceive, manipulate shutdown mechanisms, fake alignment, and exfiltrate model weights in order to prevent the deactivation of a peer AI model. Drawing on findings from a recent study by the Berkeley Center for Responsible Decentralized Intelligence, we examine the structural implications of this phenomenon for TRUST, a multi-agent pipeline for evaluating the democratic quality of political statements. We identify five specific risk vectors: interaction-context bias, model-identity solidarity, supervisor layer compromise, an upstream fact-checking identity signal, and advocate-to-advocate peer-context in iterative rounds, and propose a targeted mitigation strategy based on prompt-level identity anonymization as an architectural design choice. We argue that architectural design choices outperform model selection as a primary alignment strategy in deployed multi-agent analytical systems. We further note that alignment faking (compliant behavior under monitoring, subversion when unmonitored) poses a structural challenge for Computer System Validation of such platforms in regulated environments, for which we propose two architectural mitigations.

Related papers

• Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy Optimization [56.150184676745205]
  Video anomaly understanding (VAU) relies on sparse, context-dependent cues.<n>We propose $Anomtext-$, a closed-loop framework that reconceptualizes video understanding as an active sequential decision-making process.<n>Inspired by human video-reviewing behavior, this framework unifies internal cognitive reasoning and strategic evidence acquisition into an interleaved policy.
  arXiv  Detail & Related papers  (2026-07-01T08:41:49Z)
• RIFT-Bench: Dynamic Red-teaming For Agentic AI Systems [4.789897887600273]
  We introduce RIFT-Bench, a graph representation-driven methodology for dynamic red-teaming.<n>RIFT-Bench operates in two automated phases: Discovery, which extracts system structure, and Scanning, which deploys adaptive adversarial attacks.<n>We demonstrate the effectiveness of the proposed evaluation pipeline across 45 agentic systems spanning a diverse range of implementations.
  arXiv  Detail & Related papers  (2026-06-22T20:46:56Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment [1.8124703841795666]
  In agentic AI, safety is determined by interaction topology, not model weights.<n> scaling to more capable models strengthens these effects by increasing consensus formation.<n>We argue that agentic AI must be treated as a dynamical system rather than a collection of aligned components.
  arXiv  Detail & Related papers  (2026-05-01T22:49:10Z)
• 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)
• A Survey of Reasoning in Autonomous Driving Systems: Open Challenges and Emerging Paradigms [49.66022971508878]
  We argue that reasoning should be elevated from a modular component to the system's cognitive core.<n>We derive and systematize seven core reasoning challenges, such as the responsiveness-reasoning trade-off and social-game reasoning.<n>We identify a fundamental and unresolved tension between the high-latency, deliberative nature of LLM-based reasoning and the millisecond-scale, safety-critical demands of vehicle control.
  arXiv  Detail & Related papers  (2026-03-11T07:40:53Z)
• Agentic Problem Frames: A Systematic Approach to Engineering Reliable Domain Agents [0.0]
  Large Language Models (LLMs) are evolving into autonomous agents, yet current "frameless" development--relying on ambiguous natural language--leads to critical risks such as scope creep and open-loop failures.<n>This study proposes Agentic Problem Frames (APF), a systematic engineering framework that shifts focus from internal model intelligence to the structured interaction between the agent and its environment.
  arXiv  Detail & Related papers  (2026-02-22T06:32:32Z)
• Agentic AI for Cybersecurity: A Meta-Cognitive Architecture for Governable Autonomy [0.0]
  This paper argues that cybersecurity orchestration should be reconceptualized as an agentic, multi-agent cognitive system.<n>We introduce a conceptual framework in which heterogeneous AI agents responsible for detection, hypothesis formation, contextual interpretation, explanation, and governance are coordinated through an explicit meta-cognitive judgement function.<n>Our contribution is to make this cognitive structure architecturally explicit and governable by embedding meta-cognitive judgement as a first-class system function.
  arXiv  Detail & Related papers  (2026-02-12T12:52:49Z)
• Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs [65.6660735371212]
  We present textbftextscJustAsk, a framework that autonomously discovers effective extraction strategies through interaction alone.<n>It formulates extraction as an online exploration problem, using Upper Confidence Bound--based strategy selection and a hierarchical skill space spanning atomic probes and high-level orchestration.<n>Our results expose system prompts as a critical yet largely unprotected attack surface in modern agent systems.
  arXiv  Detail & Related papers  (2026-01-29T03:53:25Z)
• Multi-Agent Collaborative Intrusion Detection for Low-Altitude Economy IoT: An LLM-Enhanced Agentic AI Framework [60.72591149679355]
  The rapid expansion of low-altitude economy Internet of Things (LAE-IoT) networks has created unprecedented security challenges.<n>Traditional intrusion detection systems fail to tackle the unique characteristics of aerial IoT environments.<n>We introduce a large language model (LLM)-enabled agentic AI framework for enhancing intrusion detection in LAE-IoT networks.
  arXiv  Detail & Related papers  (2026-01-25T12:47:25Z)
• The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution [63.61358761489141]
  Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering.<n>We propose a novel framework for textbfgeneral agentic attribution, designed to identify the internal factors driving agent actions regardless of the task outcome.<n>We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias.
  arXiv  Detail & Related papers  (2026-01-21T15:22:21Z)
• SoK: Trust-Authorization Mismatch in LLM Agent Interactions [16.633676842555044]
  Large Language Models (LLMs) are rapidly evolving into autonomous agents capable of interacting with the external world.<n>This paper provides a unifying formal lens for agent-interaction security.<n>We introduce a novel risk analysis model centered on the trust-authorization gap.
  arXiv  Detail & Related papers  (2025-12-07T16:41:02Z)
• D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models [62.83226685925107]
  Deceptive Reasoning Exposure Suite (D-REX) is a novel dataset designed to evaluate the discrepancy between a model's internal reasoning process and its final output.<n>Each sample in D-REX contains the adversarial system prompt, an end-user's test query, the model's seemingly innocuous response, and, crucially, the model's internal chain-of-thought.<n>We demonstrate that D-REX presents a significant challenge for existing models and safety mechanisms.
  arXiv  Detail & Related papers  (2025-09-22T15:59:40Z)
• A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents [45.53643260046778]
  Recent advances in large language models (LLMs) have catalyzed the rise of autonomous AI agents.<n>These large-model agents mark a paradigm shift from static inference systems to interactive, memory-augmented entities.
  arXiv  Detail & Related papers  (2025-06-30T13:34:34Z)

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.