DenoiseFlow：面向可靠LLM代理工作流的不确定性感知去噪
DenoiseFlow: Uncertainty-Aware Denoising for Reliable LLM Agentic Workflows
AI总结：
DenoiseFlow通过闭环框架实现多步推理的不确定性感知去噪，提升LLM代理工作流的可靠性与效率。
摘要：
自主代理正越来越多地被委托执行复杂的、长周期的任务，从数学推理到软件生成。虽然代理工作流通过将任务分解为多步推理链来促进这些任务，但随着序列长度的增加，可靠性显著下降。具体而言，自然语言指令中的微小解释错误往往会静默地在步骤中累积。我们将这种失败模式称为累积语义模糊性。现有方法缓解这种问题往往缺乏运行时适应性，依赖于静态探索预算、反应性错误恢复或单路径执行，完全忽略不确定性。我们正式将多步推理过程建模为一个噪声马尔可夫决策过程，并提出DenoiseFlow，一个闭环框架，通过三个协调阶段逐步去噪：（1）估计每一步的语义不确定性；（2）调节适应性地分配计算，通过在快速单路径执行和基于估计风险的并行探索之间路由；（3）纠正通过基于影响的根因定位进行针对性恢复。在线自我校准持续将决策边界与验证器反馈对齐，无需真实标签。在六个涵盖数学推理、代码生成和多跳问答的基准测试中，DenoiseFlow在每个基准上均达到最高准确性（83.3%平均，比最强基线高1.3%），同时通过自适应分支减少成本40-56%。详细的消融研究进一步证实了框架层面的鲁棒性和通用性。代码可在https://anonymous.4open.science/r/DenoiseFlow-21D3/上获取。
英文摘要：
Autonomous agents are increasingly entrusted with complex, long-horizon tasks, ranging from mathematical reasoning to software generation. While agentic workflows facilitate these tasks by decomposing them into multi-step reasoning chains, reliability degrades significantly as the sequence lengthens. Specifically, minor interpretation errors in natural-language instructions tend to compound silently across steps. We term this failure mode accumulated semantic ambiguity. Existing approaches to mitigate this often lack runtime adaptivity, relying instead on static exploration budgets, reactive error recovery, or single-path execution that ignores uncertainty entirely. We formalize the multi-step reasoning process as a Noisy MDP and propose DenoiseFlow, a closed-loop framework that performs progressive denoising through three coordinated stages: (1)Sensing estimates per-step semantic uncertainty; (2)Regulating adaptively allocates computation by routing between fast single-path execution and parallel exploration based on estimated risk; and (3)Correcting performs targeted recovery via influence-based root-cause localization. Online self-calibration continuously aligns decision boundaries with verifier feedback, requiring no ground-truth labels. Experiments on six benchmarks spanning mathematical reasoning, code generation, and multi-hop QA show that DenoiseFlow achieves the highest accuracy on every benchmark (83.3% average, +1.3% over the strongest baseline) while reducing cost by 40--56% through adaptive branching. Detailed ablation studies further confirm framework-level's robustness and generality. Code is available at https://anonymous.4open.science/r/DenoiseFlow-21D3/.
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。
