超越流畅性：迈向可靠的代理信息检索轨迹
Beyond Fluency: Toward Reliable Trajectories in Agentic IR
AI总结：
本文探讨了代理信息检索中轨迹完整性与因果归因的重要性，提出通过验证门和系统性回避策略来减少累积误差和欺骗性流畅性，强调过程正确性而非终点准确性。
摘要：
信息检索正从被动文档排序转向自主代理工作流，这些工作流在多步骤的推理-行动-观察循环中运行。在长周期轨迹中，早期的小错误可能引发连锁反应，导致内部推理与外部工具执行之间出现功能不一致，尽管语言流畅性持续存在。本文通过总结工业代理系统中观察到的故障模式，将错误分类为规划、检索、推理和执行方面。我们主张安全部署需要超越终点准确性，转向轨迹完整性和因果归因。为解决累积误差和欺骗性流畅性问题，我们提出在每个交互单元设置验证门，并倡导在校准的不确定性下进行系统性回避。可靠的代理信息检索系统必须优先考虑过程正确性和基于现实的执行，而非可能但未经验证的完成。
英文摘要：
Information Retrieval is shifting from passive document ranking toward autonomous agentic workflows that operate in multi-step Reason-Act-Observe loops. In such long-horizon trajectories, minor early errors can cascade, leading to functional misalignment between internal reasoning and external tool execution despite continued linguistic fluency. This position paper synthesizes failure modes observed in industrial agentic systems, categorizing errors across planning, retrieval, reasoning, and execution. We argue that safe deployment requires moving beyond endpoint accuracy toward trajectory integrity and causal attribution. To address compounding error and deceptive fluency, we propose verification gates at each interaction unit and advocate systematic abstention under calibrated uncertainty. Reliable Agentic IR systems must prioritize process correctness and grounded execution over plausible but unverified completion.
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。
