⚡Megatron LLM Hub
←Back to search
Twitter

研究者让多个 Agent 实时共享进度并互相改进,用于漏洞发现

多 Agent 协作已落到漏洞挖掘与代码审查,改变攻防效率基线。
ai_agentllm漏洞挖掘
Spent last few weeks trying to coordinate swarms in a way that agents not only can interact with each other but share progress in real time and help improve each other, this has been v promising results in multiple areas, including research, vuln discovery, finding optimal solution, code review etc.