Nardine Basta, Robin Carpentier, Benjamin Zhao, Dali Kaafar · 2026 · Lecture notes in computer science
DOI: 10.1007/978-3-032-37682-4_23 · cited by 0 works (OpenAlex) · open-access PDF
Las estafas telefónicas imponen costes sustanciales y crecientes a los individuos y a los sistemas financieros en todo el mundo, sin embargo, las contramedidas existentes no imponen costes de recursos a los perpetradores. El fraude estratégico, en el que los agentes automatizados involucran a los estafadores para agotar su capacidad operativa, ofrece una alternativa proactiva pero requiere una adaptación estratégica dinámica que los sistemas estáticos no pueden proporcionar. Introducimos un marco teórico del juego que permite a los LLM aprender estrategias eficaces de contrarreloj a través de la experiencia en el contexto sin ajustar adecuadamente.
Machine translation (Meta M2M100); the English original follows.
Phone scams impose substantial and growing costs on individuals and financial systems worldwide, yet existing countermeasures impose no resource cost on perpetrators. Strategic scam-baiting, in which automated agents engage scammers to deplete their operational capacity, offers a proactive alternative but requires dynamic strategy adaptation that static systems cannot provide. We introduce a game-theoretic framework enabling LLMs to learn effective counter-strategies through in-context experience without fine-tuning. The framework models scammer-baiter interactions as a two-player game with em
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Nash equilibrium, Game theory, Benchmark (surveying), Phone, Computer security
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26781, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange