PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societies

• URL: http://arxiv.org/abs/2605.19351v1
• Date: Tue, 19 May 2026 04:40:09 GMT
• Title: PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societies
• Abstract summary: Generative agents can reproduce believable human behavior in cooperative settings, but how they should reason in situations where rule-breaking may be required remains poorly characterized.<n>We propose PAVE, a novel four- module cognitive architecture that addresses this gap end to end.<n>We instantiate PAVE in Voville, a tile-based traffic environment forked from Smallville, and evaluate across three scenarios.
• Score: 3.8300637171362752
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative agents based on large language models reproduce believable human behavior in cooperative settings, but how they should reason in situations where rule-breaking may be required, such as fire evacuation or authority-supervised emergency, remains poorly characterized. We propose PAVE (Perception, Assessment, Verdict, Emulation), a novel four-module cognitive architecture that addresses this gap end to end: (i) Perception extracts a structured context with explicit authority distance, peer behaviors, and severity-tagged situational cues; (ii) Assessment scores the context along five scalars including an explicit legitimacy judgment that checks necessity, proportionality, and absence of alternatives; (iii) Verdict decides to comply or violate under a hard legitimacy gate, with a per-agent threshold elicited from the persona; (iv) Emulation enacts the verdict and scopes the violation to the rule the trigger justifies. We instantiate PAVE in Voville, a tile-based traffic environment forked from Smallville, and evaluate across three scenarios, four LLM backbones, and a focused ablation. PAVE agents satisfy four properties simultaneously: legitimate violation (only when a trigger justifies it), authority deference (officer instructions override even high legitimacy), bounded scope (violations confined to the targeted rule), and recovery (baseline restored once the trigger ends). PAVE agents make more structured and interpretable decisions than vanilla across all four properties, and human evaluators rate them as more plausible. Ablating the legitimacy gate reproduces vanilla-like failures. We release Voville, the PAVE prompts and code, and the evaluation pipeline.

Related papers

• Human-on-the-Loop Orchestration for AI-Assisted Legal Discovery [0.0]
  We propose a structured taxonomy of agentic failures in legal information retrieval.<n>We introduce a four-layer verification architecture designed to intercept these failures before they compound.<n>Our results suggest that calibrated uncertainty thresholds can reduce privilegewaiver risk by up to 61% versus fully autonomous deployment.
  arXiv  Detail & Related papers  (2026-06-18T05:37:52Z)
• Intent Signal Theory: A Computational Framework for Intent-State Control in Human-AI Interaction [0.585480332059272]
  Current AI interaction models treat the prompt as the primary object of exchange, omitting a critical layer: the user's latent source intent.<n>Here we introduce Intent Signal Theory (IST), a computational framework that formalises this missing intent layer.<n>IST distinguishes four objects routinely conflated: latent source intent (I*), observable intent proxy (I-hat), encoded carrier (P), and model output (O)
  arXiv  Detail & Related papers  (2026-05-24T13:10:33Z)
• Interpretation, Learning, and Empathy as One Constraint: A Residual-Adequacy Architecture with Accountable Abstention [0.0]
  We develop a small cognitive architecture in which limits arise from a single quantity.<n>An Interpretation-Decision Unit (IDU) interprets a content vector through a family of regimes and decides which actions it licenses.<n>We prove the unit is total and deterministic: for any content and fixed configuration it halts in finitely many bounded-cost steps with a unique terminal witness.
  arXiv  Detail & Related papers  (2026-05-24T10:57:28Z)
• PRISM: : Planning and Reasoning with Intent in Simulated Embodied Environments [59.07829883257003]
  Built on five multi-room apartments, PRISM structures 300 human-verified tasks into three capability tiers.<n>PRISM exposes an agent-agnostic executable action API that allows arbitrary agents to be evaluated end-to-end.
  arXiv  Detail & Related papers  (2026-05-12T04:59:47Z)
• Decision Evidence Maturity Model for Agentic AI: A Property-Level Method Specification [0.0]
  Agentic AI systems produce decision evidence at scale through execution telemetry, but property-level reconstruction often fails.<n>We name this pattern the container fallacy: the automatic equation of evidence-container presence with audit sufficiency.<n>This paper specifies the Decision Evidence Maturity Model (DEMM), a property-level reconstructability method for agentic decisions.
  arXiv  Detail & Related papers  (2026-04-29T09:59:36Z)
• Structural Enforcement of Goal Integrity in AI Agents via Separation-of-Powers Architecture [0.10152838128195464]
  Policy-Execution-Authorization (PEA) architecture is a "separation-of-powers" design that enforces safety at the system level.<n>PEA decouples intent generation, authorization, and execution into independent, isolated layers connected via cryptographically constrained capability tokens.
  arXiv  Detail & Related papers  (2026-04-26T10:31:13Z)
• To Throw a Stone with Six Birds: On Agents and Agenthood [0.0]
  Six Birds Theory (SBT) treats macroscopic objects as induced closures rather than primitives.<n>We give a type-correct account of agency within SBT.<n>We operationalize this contract in finite controlled systems using four checkable components.
  arXiv  Detail & Related papers  (2026-02-03T10:46:23Z)
• Preventing the Collapse of Peer Review Requires Verification-First AI [49.995126139461085]
  We propose truth-coupling, i.e. how tightly venue scores track latent scientific truth.<n>We formalize two forces that drive a phase transition toward proxy-sovereign evaluation.
  arXiv  Detail & Related papers  (2026-01-23T17:17:32Z)
• Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification [71.98473277917962]
  Recent advances in Deep Research Agents (DRAs) are transforming automated knowledge discovery and problem-solving.<n>We propose an alternative paradigm: self-evolving the agent's ability by iteratively verifying the policy model's outputs, guided by meticulously crafted rubrics.<n>We present DeepVerifier, a rubrics-based outcome reward verifier that leverages the asymmetry of verification.
  arXiv  Detail & Related papers  (2026-01-22T09:47:31Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• Making LLMs Reliable When It Matters Most: A Five-Layer Architecture for High-Stakes Decisions [51.56484100374058]
  Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes.<n>This gap, driven by mutually cognitive biases in both humans and artificial intelligence (AI) systems, threatens the defensibility of valuations and sustainability of investments in the sector.<n>This report describes a framework emerging from systematic qualitative assessment across 7 frontier-grade LLMs and 3 market-facing venture vignettes under time pressure.
  arXiv  Detail & Related papers  (2025-11-10T22:24:21Z)
• The Epistemic Suite: A Post-Foundational Diagnostic Methodology for Assessing AI Knowledge Claims [0.7233897166339268]
  This paper introduces the Epistemic Suite, a diagnostic methodology for surfacing the conditions under which AI outputs are produced and received.<n>Rather than determining truth or falsity, the Suite operates through twenty diagnostic lenses to reveal patterns such as confidence laundering, narrative compression, displaced authority, and temporal drift.
  arXiv  Detail & Related papers  (2025-09-20T00:29:38Z)
• Criticality and Safety Margins for Reinforcement Learning [53.10194953873209]
  We seek to define a criticality framework with both a quantifiable ground truth and a clear significance to users.<n>We introduce true criticality as the expected drop in reward when an agent deviates from its policy for n consecutive random actions.<n>We also introduce the concept of proxy criticality, a low-overhead metric that has a statistically monotonic relationship to true criticality.
  arXiv  Detail & Related papers  (2024-09-26T21:00:45Z)

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.