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

arXiv: https://arxiv.org/abs/2605.02200 · HTML: https://mlsanity.com/paper/2605.02200/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 48 references that are in the map.
- First posted on arXiv 4 May 2026.

## Builds on (most cited first, 30 of 33)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback](https://mlsanity.com/paper/2312.00849/) (2023)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Statistical Rejection Sampling Improves Preference Optimization](https://mlsanity.com/paper/2309.06657/) (2023)
- [On The Power of Curriculum Learning in Training Deep Networks](https://mlsanity.com/paper/1904.03626/) (2019)
- [Fine-Tuning LLaMA for Multi-Stage Text Retrieval](https://mlsanity.com/paper/2310.08319/) (2023)
- [MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training](https://mlsanity.com/paper/2403.09611/) (2024)
- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [Direct Preference Optimization with an Offset](https://mlsanity.com/paper/2402.10571/) (2024)
- [IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding](https://mlsanity.com/paper/2402.18476/) (2024)
- [Curriculum Learning of Multiple Tasks](https://mlsanity.com/paper/1412.1353/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/2507.10485/) (2025)
- [Learning Statistical Texture for Semantic Segmentation](https://mlsanity.com/paper/2103.04133/) (2021)
- [NoteLLM-2: Multimodal Large Representation Models for Recommendation](https://mlsanity.com/paper/2405.16789/) (2024)
- [Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation](https://mlsanity.com/paper/2305.03944/) (2023)
- [ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations](https://mlsanity.com/paper/2406.12223/) (2024)
- [MLLM-as-a-Judge for Image Safety without Human Labeling](https://mlsanity.com/paper/2501.00192/) (2024)
- [Ultra-High Resolution Segmentation with Ultra-Rich Context: A Novel Benchmark](https://mlsanity.com/paper/2305.10899/) (2023)
- [Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understanding](https://mlsanity.com/paper/2411.08516/) (2024)
- [Guided Patch-Grouping Wavelet Transformer with Spatial Congruence for Ultra-High Resolution Segmentation](https://mlsanity.com/paper/2307.00711/) (2023)
- [Discrete Latent Perspective Learning for Segmentation and Detection](https://mlsanity.com/paper/2406.10475/) (2024)
- [Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval](https://mlsanity.com/paper/2510.02745/) (2025)
- [ToxVidLM: A Multimodal Framework for Toxicity Detection in Code-Mixed Videos](https://mlsanity.com/paper/2405.20628/) (2024)
- [Structural and Statistical Texture Knowledge Distillation and Learning for Segmentation](https://mlsanity.com/paper/2503.08043/) (2025)
- [RAVEN: Robust Advertisement Video Violation Temporal Grounding via Reinforcement Reasoning](https://mlsanity.com/paper/2510.16455/) (2025)
- [Towards Trustworthy Multimodal Moderation via Policy-Aligned Reasoning and Hierarchical Labeling](https://mlsanity.com/paper/2508.03296/) (2025)

## Abstract (arXiv)

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.