---
title: "An LLM-based Chain-of-Response Counter-Scam System"
authors:
  - "Heedou Kim"
  - "Mogan Gim"
  - "Donghee Choi"
  - "Soonil Bae"
  - "Hoonick Lee"
  - "Mi-Young Kim"
  - "Jaewoo Kang"
doi: "10.24963/ijcai.2026/808"
url: "https://ijcai.org/proceedings/2026/808"
pdf: "https://ijcai.org/proceedings/2026/0808.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "7266-7274"
track: "AI and Social Good"
keywords:
  - "Natural Language Processing: Natural Language Processing"
  - "AI Ethics, Trust, Fairness: AI Ethics, Trust, Fairness"
  - "Agent-based and Multi-agent Systems: Agent-based and Multi-agent Systems"
  - "Multidisciplinary Topics and Applications: Multidisciplinary Topics and Applications"
---

# An LLM-based Chain-of-Response Counter-Scam System

Heedou Kim, Mogan Gim, Donghee Choi, Soonil Bae, Hoonick Lee, Mi-Young Kim, Jaewoo Kang

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 7266-7274. DOI: [10.24963/ijcai.2026/808](https://doi.org/10.24963/ijcai.2026/808)

## Abstract

The rapid evolution of online scams, driven by transnational networks and mass-produced social engineering scenarios, has exposed the speed limitations of conventional detection, necessitating tighter inter-agency coordination. While LLMs show promise in scam identification, their role in accelerating integrated response frameworks remains underexplored. We propose Counter-Scam, a unified LLM-based multi-agent framework that orchestrates end-to-end response from initial detection to crime investigation. The framework first proposes safe data guidelines, emphasizing non-public scam data and secure dataset construction via scam-specific NER. Developed with insights from 37 stakeholders to reduce delays and improve analytical efficiency, the system integrates CSRA (multi-agent mitigation), CSRT (nine role-aligned NLP tasks), and CSRD (a corpus of 185,300 scam cases and 38,587 knowledge entries). Experiments show that fine-tuned sLLMs surpass commercial models with over 10% in all CSRT tasks and a 0.24 F1 improvement in scam-specific NER. This proves the framework's capability for enabling rapid, collaborative mitigation of online scam.