Skip to content
Building Effective LLM Agents | AI Cyber Challenge
theori.io | research | #ai-security | #patching | #vulnerability-detection | #darpa | #cyber-reasoning-system | #aixcc | #llm-agents
Summary
Lessons from building LLM agents for DARPA’s AI Cyber Challenge: decomposing tasks, curating toolsets and adapting to models, applied to vulnerability detection, PoV generation and patching.
- Published
- Collected