ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring

• URL: http://arxiv.org/abs/2605.02200v1
• Date: Mon, 04 May 2026 03:58:53 GMT
• Title: ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring
• Abstract summary: ARGUS is a policy-adaptive governance system that enables evolving reinforcement through adversarial umpiring.<n> experiments on both industrial and public datasets demonstrate that ARGUS significantly outperforms traditional fine-tuning baselines.
• Score: 29.13889418783881
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Online advertising governance faces significant challenges due to the non-stationary nature of regulatory policies, where emerging mandates (e.g., restrictions on education or aesthetic anxiety) create severe label inconsistencies and reasoning ambiguities in historical datasets. In this paper, we propose ARGUS, a policy-adaptive governance system that enables evolving reinforcement through multi-agent adversarial umpiring. ARGUS addresses the sparsity of new policy data by employing a three-stage framework: (1) Policy Seeding for initial perception; (2) Adversarial Label Rectification, which utilizes a ``Prosecutor-Defender-Umpire'' architecture to resolve conflicts between stale labels and new mandates; and (3) Latent Knowledge Discovery, which employs a tripartite dialectical discussion to unearth sophisticated, ``gray-area'' violations. By leveraging RAG-enhanced policy knowledge and Chain-of-Thought synthesis as dynamic rewards for reinforcement learning, ARGUS synchronizes its reasoning pathways with evolving regulations. Extensive experiments on both industrial and public datasets demonstrate that ARGUS significantly outperforms traditional fine-tuning baselines, achieving superior policy-adaptive learning with minimal gold data.

Related papers

• PolicyMem: Geometric Policy Memory for LLM Governance [72.04962480384322]
  We introduce PolicyMem, a geometric policy memory that externalizes natural-language policies as reusable geometric memory objects.<n>A memory writer compiles natural-language policies into policy memory slots, and query-response pairs read the policy memory through projection energy.<n>The resulting policy-evidence profile directly mediates the safety verdict and is reused for policy attribution and post-intervention verification.
  arXiv  Detail & Related papers  (2026-09-12T06:07:43Z)
• Coordinated incentives in AI-generated misinformation governance [2.3806068873746784]
  AI-driven misinformation is becoming increasingly pervasive and difficult to govern.<n>This study models the strategic interdependence among a government regulator, an AI enterprise, and users through a three-party evolutionary game.
  arXiv  Detail & Related papers  (2026-08-07T10:24:09Z)
• R^3: Advertisement Compliance Rectification via Group-Relative Experience Extractor and Curriculum Reinforcement [14.426627534391086]
  Rigorous content moderation is crucial for online advertising but leads to millions of daily rejections.<n>We propose R3, a novel framework designed to harmonize compliance with original semantic intent preservation.<n>Our approach integrates three key innovations: (1) an experience-driven data synthesis framework that bootstraps high-quality supervision via a group-Relative compliance experience extractor; (2) a curriculum Reinforcement learning strategy with hierarchical rewards designed to enforce compliance while maximizing semantic consistency; and (3) a comprehensive video Rectification framework seamlessly integrating text recognition, rewriting, and re-rendering for industrial deployment.
  arXiv  Detail & Related papers  (2026-07-08T12:05:41Z)
• PolicyBank: Evolving Policy Understanding for LLM Agents [51.86716874651299]
  PolicyBank maintains structured, tool-level policy insights and iteratively refines them.<n>PolicyBank closes up to 82% of the gap toward a human oracle.
  arXiv  Detail & Related papers  (2026-04-16T20:29:30Z)
• Responsible AI: The Good, The Bad, The AI [1.932555230783329]
  This paper presents a comprehensive examination of AI's dual nature through the lens of strategic information systems.<n>We develop the Paradox-based Responsible AI Governance (PRAIG) framework that articulates: (1) the strategic benefits of AI adoption, (2) the inherent risks and unintended consequences, and (3) governance mechanisms that enable organizations to navigate these tensions.<n>The paper concludes with a research agenda for advancing responsible AI governance scholarship.
  arXiv  Detail & Related papers  (2026-01-28T22:33:27Z)
• Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm [58.350254095190365]
  Unsupervised domain adaptation (UDA) aims to transfer knowledge from a label-rich source domain to an unlabeled target domain by addressing domain shifts.<n>Most UDA approaches emphasize transfer ability, but often overlook robustness against adversarial attacks.<n>This paper focuses on answering three key questions: 1) Why does VAT, known as its defensive effectiveness, fail in the UDA paradigm? 2) What is the generalization bound theory under attacks and how does it evolve from classical UDA theory?
  arXiv  Detail & Related papers  (2025-11-14T06:54:06Z)
• ArGen: Auto-Regulation of Generative AI via GRPO and Policy-as-Code [0.0]
  ArGen is a framework for aligning Large Language Models with complex rules spanning ethical principles, operational safety protocols, and regulatory compliance standards.<n>We show that ArGen's methodology offers a path to 'Governable Al' systems that are technically proficient, ethically robust, and verifiably compliant for safe deployment in diverse global contexts.
  arXiv  Detail & Related papers  (2025-09-06T04:33:16Z)
• Classification is a RAG problem: A case study on hate speech detection [6.716186124523375]
  We present classification using Retrieval-Augmented Generation (RAG)<n>RAG shifts traditional classification tasks to evaluate content in relation to contextual knowledge retrieved at inference.<n>In hate speech detection, this transforms the task from "is this hate speech?" to "does this violate the hate speech policy?"
  arXiv  Detail & Related papers  (2025-08-08T10:35:41Z)
• Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filtering [9.814926166669366]
  We propose Know3-RAG, a knowledge-aware RAG framework that leverages structured knowledge from knowledge graphs (KGs) to guide three core stages of the RAG process, including retrieval, generation, and filtering.<n> Experiments on multiple open-domain QA benchmarks demonstrate that Know3-RAG consistently outperforms strong baselines, significantly reducing hallucinations and enhancing answer reliability.
  arXiv  Detail & Related papers  (2025-05-19T03:25:18Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• Rule-Guided Reinforcement Learning Policy Evaluation and Improvement [9.077163856137505]
  LEGIBLE is a novel approach to improving deep reinforcement learning policies.<n>It starts by mining rules from a deep RL policy, constituting a partially symbolic representation.<n>In the second step, we generalize the mined rules using domain knowledge expressed as metamorphic relations.<n>The third step is evaluating generalized rules to determine which generalizations improve performance when enforced.
  arXiv  Detail & Related papers  (2025-03-12T11:13:08Z)
• Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL [57.202733701029594]
  We propose Decision Mamba, a novel multi-grained state space model (SSM) with a self-evolving policy learning strategy.<n>To address these challenges, we propose Decision Mamba, a novel multi-grained state space model (SSM) with a self-evolving policy learning strategy.<n>To mitigate the overfitting issue on noisy trajectories, a self-evolving policy is proposed by using progressive regularization.
  arXiv  Detail & Related papers  (2024-06-08T10:12:00Z)
• Entity-enhanced Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding [214.8003571700285]
  Weakly supervised Referring Expression Grounding (REG) aims to ground a particular target in an image described by a language expression. We design an entity-enhanced adaptive reconstruction network (EARN) EARN includes three modules: entity enhancement, adaptive grounding, and collaborative reconstruction.
  arXiv  Detail & Related papers  (2022-07-18T05:30:45Z)
• Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients [54.98496284653234]
  We consider the task of training a policy that maximizes reward while minimizing disclosure of certain sensitive state variables through the actions. We solve this problem by introducing a regularizer based on the mutual information between the sensitive state and the actions. We develop a model-based estimator for optimization of privacy-constrained policies.
  arXiv  Detail & Related papers  (2020-12-30T03:22:35Z)

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.