arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.15425cs.SEcs.AI
收藏

运行时结构化任务分解用于代理编码系统

Runtime-Structured Task Decomposition for Agentic Coding Systems

IBM Research(IBM研究院)

Shubhi Asthana, Bing Zhang, Chad DeLuca, Hima Patel, Ruchi Mahindru

AI总结:

本文提出运行时结构化任务分解方法,通过可执行控制逻辑管理任务分解与执行流程,降低重试成本,提升代理编码系统的效率和可靠性。

摘要:

代理编码系统越来越多地使用大型语言模型(LLMs)进行软件工程任务,如调试、根本原因分析和代码审查。然而,许多现有系统在单个提示中编码任务逻辑、执行流程和输出生成,这种设计导致行为脆弱、调试困难和高重试成本,因为失败往往需要重新运行整个工作流。我们提出运行时结构化任务分解,一种架构方法,通过可执行控制逻辑管理任务分解和执行流程,而不是仅依赖提示结构。LLMs仅用于专注判断任务,输出在下游执行前会根据预定义的模式进行验证。我们在两个软件工程工作负载上评估了这种方法,使用三种配置:单体执行、静态分解(固定子任务和无运行时分支)和运行时结构化分解。每种配置在10次运行中进行评估。我们的结果表明,分解本身并不一定减少重试成本。在Kubernetes根本原因分析工作负载中,静态分解基线的重试成本为1,632±145个标记,而单体基线为904±17个标记,因为失败迫使重新运行下游子任务。在多文件调试工作负载中,类似模式出现,静态基线消耗933个标记,而单体系统为703个标记。运行时结构化方法仅重新运行失败的子任务,将重试成本降低到436±132个标记(根本原因分析)和460个标记(调试)。总体而言,该方法比单体系统减少了51.7%的重试成本,比静态分解基线减少了73.2%的重试成本,提高了代理编码系统的效率、调试能力和操作可靠性。

英文摘要:

Agentic coding systems increasingly use large language models (LLMs) for software engineering tasks such as debugging, root cause analysis, and code review. However, many existing systems encode task logic, execution flow, and output generation inside monolithic prompts. This design creates brittle behavior, limited debuggability, and high retry costs because failures often require rerunning the full workflow. We present runtime-structured task decomposition, an architectural approach in which task partitioning and execution flow are managed through executable control logic rather than prompt structure alone. LLMs are used only for focused judgment tasks, and outputs are validated against predefined schemas before downstream execution. We evaluate this approach on two software engineering workloads using three configurations: monolithic execution, static decomposition with fixed subtasks and no runtime branching, and runtime-structured decomposition. Each configuration was evaluated across 10 runs. Our results show that decomposition alone does not necessarily reduce retry cost. In the Kubernetes root cause analysis workload, the static decomposition baseline produced a retry cost of 1,632 +/- 145 tokens versus 904 +/- 17 tokens for the monolithic baseline because failures forced reruns of downstream subtasks. A similar pattern appeared in the multi-file debugging workload, where the static baseline consumed 933 tokens compared to 703 tokens for the monolithic system. The runtime-structured approach reran only failed subtasks, reducing retry costs to 436 +/- 132 tokens for root cause analysis and 460 tokens for debugging. Overall, the approach achieved up to 51.7% lower retry cost than monolithic systems and 73.2% lower retry cost than static decomposition baselines, improving efficiency, debuggability, and operational reliability in agentic coding 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。

↑