用于可靠的工具增强型大语言模型系统的自愈代理编排器
Self-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model Systems
AI总结：
提出一种自愈代理编排器，通过将可靠性视为有界运行时控制问题，映射故障信号、选择恢复动作并验证轨迹，在100任务故障注入基准上达到98.8%任务成功率，优于重试和完全重规划基线。
摘要：
工具增强型大语言模型（LLM）代理依赖于协调规划、检索、工具调用、验证、记忆和恢复的编排层。在这些系统中，故障不仅来自模型错误，还来自编排层问题，如工具超时、参数格式错误、过时上下文、矛盾证据、重试循环和未验证的中间输出。本文提出一种自愈代理编排器，将可靠性视为有界运行时控制问题。该编排器将可观察的故障信号映射到推断的故障类别，在显式预算下选择目标恢复动作，验证恢复轨迹，并记录可观察性痕迹。我们在一个100任务的受控故障注入基准上，将本方法与静态工作流、仅重试、ReAct风格和完全重规划基线进行比较。自愈方法实现了98.8%的任务成功率，而仅重试为94.5%，完全重规划为93.8%。匹配的恢复预算扫描显示，在每个测试预算下，自愈方法均优于仅重试和完全重规划，在单次恢复尝试下差距最大：分别为94.0%对比85.3%和88.2%。在受控的语义静默故障设置下，验证器引导的自愈将静默故障降至0.0%，而非验证基线更频繁地返回错误但看似合理的输出。紧凑的模型在环验证表明，当实时工具调用模型在本地故障注入工具上执行工具选择、参数生成和答案合成时，相同的恢复机制可以运行。这些结果提供了受控证据，表明故障感知、有预算和验证引导的编排提高了工具增强型LLM系统的可靠性和可诊断性。
英文摘要：
Tool-augmented large language model (LLM) agents rely on orchestration layers that coordinate planning, retrieval, tool invocation, validation, memory, and recovery. In these systems, failures arise not only from model errors, but also from orchestration-level issues such as tool timeouts, malformed arguments, stale context, contradictory evidence, retry loops, and unverified intermediate outputs. This paper presents a self-healing agentic orchestrator that treats reliability as a bounded runtime control problem. The orchestrator maps observable failure signals to inferred failure classes, selects targeted recovery actions under explicit budgets, verifies recovered trajectories, and records observability traces. We evaluate the approach on a 100-task controlled fault-injection benchmark against static workflow, retry-only, ReAct-style, and full-replanning baselines. Self-healing achieves 98.8\% task success, compared with 94.5\% for retry-only and 93.8\% for full replanning. A matched recovery-budget sweep shows that self-healing outperforms retry-only and full replanning at every tested budget, with the largest gap under a single recovery attempt: 94.0\% versus 85.3\% and 88.2\%, respectively. Under a controlled semantic silent-failure setting, verifier-guided self-healing reduces silent failures to 0.0\%, while non-verifying baselines return wrong-but-plausible outputs more often. A compact model-in-the-loop validation shows that the same recovery mechanism can operate when a live tool-calling model performs tool selection, argument generation, and answer synthesis over local fault-injected tools. These results provide controlled evidence that failure-aware, budgeted, and verification-guided orchestration improves reliability and diagnosability in tool-augmented LLM systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
