让大模型客服按政策走完整流程，避免出错或漏步骤。
PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents
- 将政策转为流程图，在每轮对话时主动检查并引导正确路径。
- 在多个领域平均通过率从0.42提升至0.62，电信领域提升最明显。
- 适用于需严格遵循流程的客服系统，尤其适合高风险场景。
客户服务大模型在代用户操作时必须遵守组织政策。合规失败源于禁止行为（如批准不合格变更）或遗漏流程要求（如身份确认）。运行时防护可干预高风险动作，但局部检查无法指导多步流程。现有流程系统关注任务完成而非行为安全。PolicyGuide将各领域政策编译为流程图，并在用户回合边界调用主动验证器。基于持久化图状态，验证器协调未决请求，返回针对当前步骤的合规修正建议。在航空、零售、电信三个领域的τ²- bench测试中，使用GPT-5.4代理与验证器，平均通过率$ ext{Pass}^4$从0.42提升至0.62，电信领域提升最大（0.19至0.61）。相同流程可迁移至Claude Sonnet 4.6和Gemini 2.5 Pro代理。补充评估显示，在对抗性用户下攻击成功率最低，且在人工设计的流程级验证中表现出最强的程序合规性。
原文摘要 · Abstract (English)
Customer-service LLM agents must follow organizational policy when acting on a user's behalf. Compliance failures arise from either forbidden actions, such as granting an ineligible change, or omitted procedural requirements, such as identification or confirmation. Runtime safeguards can intervene on risky actions, but action-local checks do not guide an agent through a multi-step procedure. Workflow-following systems support prescribed process execution, but primarily target workflow completion rather than safeguarding agent behavior. PolicyGuide instead compiles each domain policy into a workflow graph and invokes a proactive verifier at user-turn boundaries. From persisted graph state, the verifier reconciles open requests and returns step-specific remediation along a policy-compliant path. Across the $τ^2$-bench airline, retail, and telecom domains with a GPT-5.4 agent and verifier, PolicyGuide raises mean $\mathrm{Pass}^4$ from $0.42$ to $0.62$, with the largest gain on telecom ($0.19$ to $0.61$), the most workflow-structured domain. The same workflows transfer to Claude Sonnet 4.6 and Gemini 2.5 Pro agents. Complementary evaluations find the lowest observed attack-success rate under adversarial users and the strongest procedural compliance in an author-designed workflow-level validation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。