⚡Megatron LLM Hub
←Back to search
Twitter

LLM Agent 持久记忆投毒基准发布,含 LangChain/LlamaIndex 复现环境

记忆投毒是自托管 Agent 的核心风险面,提供了可复用的干净/投毒对照评测与防御基线。
ai_agentllm工具poc
memform-code — Deterministic benchmark and evaluation harness for persistent-memory poisoning in LLM agents, with paired clean/poisoned cases, LangChain/LlamaIndex runners, and defenses. https://t.co/ukAh4qlK2J https://t.co/rimO0OUzxh