{"work":{"id":"0f43e485-eb8e-4b8a-bfd9-03234b917c82","openalex_id":"https://openalex.org/W4399404894","doi":"10.48550/arxiv.2406.01637","arxiv_id":"2406.01637","raw_key":null,"title":"Teams of LLM Agents can Exploit Zero-Day Vulnerabilities","authors":null,"authors_text":"R","year":2024,"venue":"cs.MA","abstract":"LLM agents have become increasingly sophisticated, especially in the realm of cybersecurity. Researchers have shown that LLM agents can exploit real-world vulnerabilities when given a description of the vulnerability and toy capture-the-flag problems. However, these agents still perform poorly on real-world vulnerabilities that are unknown to the agent ahead of time (zero-day vulnerabilities).\n  In this work, we show that teams of LLM agents can exploit real-world, zero-day vulnerabilities. Prior agents struggle with exploring many different vulnerabilities and long-range planning when used alone. To resolve this, we introduce HPTSA, a system of agents with a planning agent that can launch subagents. The planning agent explores the system and determines which subagents to call, resolving long-term planning issues when trying different vulnerabilities. We construct a benchmark of 14 real-world vulnerabilities and show that our team of agents improve over prior agent frameworks by up to 4.3X.","external_url":"https://arxiv.org/abs/2406.01637","cited_by_count":19,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2406.01637","created_at":"2026-05-10T00:59:49.629542+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"the winning worker cost","render_title":"the winning worker cost"},"hub":{"state":{"work_id":"0f43e485-eb8e-4b8a-bfd9-03234b917c82","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":20,"external_cited_by_count":19,"distinct_field_count":3,"first_pith_cited_at":"2025-09-08T17:33:59+00:00","last_pith_cited_at":"2026-07-08T07:50:49+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-23T04:19:47.447629+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":5}],"polarity_counts":[{"context_polarity":"support","n":3},{"context_polarity":"background","n":2}],"runs":{},"summary":{},"graph":{},"authors":[]}}