Kaer 框架为多智能体系统的动态重规划加上安全防护
Kaer: Security-Aware Replanning for Multi-Agent Systems
写多智能体系统的值得看这篇:恶意 agent 能通过反馈劫持 orchestrator 的重规划,这是很多框架都忽略的攻击面。Kaer 用抽象模板加确定性修复算子来堵住它,比 ControlValve 更稳、比裸跑的 Magentic-One 安全得多,做 agent 安全评估还能直接用它的 Cintra 基准。
arXiv 论文 2611.24839 提出 Kaer,一个面向多智能体系统的安全重规划框架。问题在于 orchestrator 依赖 agent 反馈来动态修订计划,恶意 agent 可以在反馈中嵌入指令劫持重规划过程,而现有防御只覆盖工具级访问控制或静态的预执行策略,重规划阶段处于不设防状态。
Kaer 的做法是让 planner 不直接接触不可信的 agent 反馈:失败诊断只通过抽象模板传递给重规划流程,计划修订被限制在一组确定性的 repair operators 内,且所有修改后的计划必须满足预设策略。作者还构建了 Cintra 基准,包含需要重规划的模拟用户任务以及针对重规划阶段的对抗性目标,同时评估任务完成率和系统被恶意 agent 利用重规划漏洞的脆弱性。
在 Cintra 上与 Magentic-One(无防御 MAS)和 ControlValve(当时的 SOTA 防御)对比,Kaer 的鲁棒性高于两者,任务效用与 ControlValve 相当。抽象失败模板在部分任务上会轻微约束效用,但换来的是不向 orchestrator 暴露不可信反馈的安全动态重规划能力。
Kaer: Security-Aware Replanning for Multi-Agent Systems
One popular architecture for multi-agent systems (MAS) relies on an orchestrator that generates an initial plan, coordinates its execution, and dynamically revises the plan based on agent feedback when tasks cannot be fully specified in advance. This dynamic replanning introduces a critical vulnerability: malicious agents can embed instructions within their feedback to hijack the replanning process. Existing defenses focus exclusively on per-tool access control or static, pre-execution policy enforcement, leaving the replanning phase unsecured. We introduce Kaer, a multi-agent framework featuring security-aware replanning. Kaer shields the planner from untrusted agent feedback by conveying diagnostics to the replanning procedure strictly through abstract templates. Plan revisions are restricted to a set of deterministic repair operators, and all modified plans must satisfy preset policies. We create Cintra, a benchmark of simulated user tasks requiring replanning paired with adversarial objectives targeting the replanning phase. Using Cintra, we evaluate both task completion rates and system vulnerability to replanning exploits by malicious agents. Evaluating Kaer on Cintra against Magentic-One (an undefended MAS) and ControlValve (the state-of-the-art defense) demonstrates that Kaer achieves higher robustness than both systems while maintaining comparable utility to ControlValve. Although abstract failure templates slightly constrain utility on select tasks, Kaer enables MAS to perform secure, dynamic plan revisions without exposing the orchestrator to untrusted agent feedback.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include multi-agent systems, Kaer, Magentic-One, AI safety.
Source attribution: curated from arXiv cs.LG (@Tushin Mallick, Evan Rose, Matthew Laws, Alina Oprea, Cristina Nita-Rotaru).