# ORACLE: Anticipating Scams from Partial Trajectories in Streaming App Usage

arXiv: https://arxiv.org/abs/2605.16363 · HTML: https://mlsanity.com/paper/2605.16363/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 9 May 2026.

## Builds on (most cited first, 21 of 21)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models](https://mlsanity.com/paper/2601.18734/) (2026)
- [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026)
- [On-Policy Context Distillation for Language Models](https://mlsanity.com/paper/2602.12275/) (2026)
- [XSkill: Continual Learning from Experience and Skills in Multimodal Agents](https://mlsanity.com/paper/2603.12056/) (2026)
- [Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements](https://mlsanity.com/paper/2502.12904/) (2025)
- [Online Experiential Learning for Language Models](https://mlsanity.com/paper/2603.16856/) (2026)
- [Real-time Traffic Accident Risk Prediction based on Frequent Pattern Tree](https://mlsanity.com/paper/1701.05691/) (2017)
- ["It Warned Me Just at the Right Moment": Exploring LLM-based Real-time Detection of Phone Scams](https://mlsanity.com/paper/2502.03964/) (2025)
- [TeleAntiFraud-28k: An Audio-Text Slow-Thinking Dataset for Telecom Fraud Detection](https://mlsanity.com/paper/2503.24115/) (2025)
- [Context-Aware Target Apps Selection and Recommendation for Enhancing Personal Mobile Assistants](https://mlsanity.com/paper/2101.03394/) (2021)
- [Bot Wars Evolved: Orchestrating Competing LLMs in a Counterstrike Against Phone Scams](https://mlsanity.com/paper/2503.07036/) (2025)
- [A Survey on Smartphones Security: Software Vulnerabilities, Malware, and Attacks](https://mlsanity.com/paper/2001.09406/) (2020)
- [ScamGPT-J: Inside the Scammer's Mind, A Generative AI-Based Approach Toward Combating Messaging Scams](https://mlsanity.com/paper/2412.13528/) (2024)
- [An Overview of 7726 User Reports: Uncovering SMS Scams and Scammer Strategies](https://mlsanity.com/paper/2508.05276/) (2025)
- [SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning](https://mlsanity.com/paper/2601.01392/) (2026)
- [Anticipate, Simulate, Reason (ASR): A Comprehensive Generative AI Framework for Combating Messaging Scams](https://mlsanity.com/paper/2507.17543/) (2025)
- [CASE: An Agentic AI Framework for Enhancing Scam Intelligence in Digital Payments](https://mlsanity.com/paper/2508.19932/) (2025)

## Abstract (arXiv)

Smartphone scams are increasingly prevalent and typically manifest as multi-stage, cross-application processes with gradually emerging intent. Effective intervention thus requires anticipating scams before the intent becomes explicit. This is inherently challenging, as decisions must rely on partial trajectories with temporally distributed evidence. In this paper, we propose ORACLE Online Reasoning for Anticipating Cross-temporal Latent thrEats, the first agentic framework for early scam anticipation from textitstreaming app-usage trajectories. To support this setting, we curate a real-world long-horizon benchmark of streaming app-usage trajectories, covering 12 scam types, spanning extended periods (15 days on average), involving diverse applications (95 apps), and interleaving normal and scam behaviors. To address fragmented evidence, we introduce a self-evolving context manager that adaptively consolidates entity-centric interactions over time, enabling more effective reconstruction of cross-temporal evidence from partial observations. To enhance sensitivity to latent early-stage signals, we propose an on-policy self-distillation scheme in which a teacher model, conditioned on summarized anti-scam reflections and clues by skills, supervises a student model without access to such reflections. This scheme thereby distills evidence-informed knowledge and improves recognition of emerging fraud patterns from partial trajectories. Experiments show that method consistently improves early scam anticipation, yielding timely warnings while reducing false alerts in realistic streaming scenarios.