RepoMAS：面向渐进式指定任务的议题驱动多智能体系统
RepoMAS: Solving Progressively Specified Tasks with Issue-Driven Multi-Agent Systems
浏览论文内容
中文总结 AI 辅助
针对用户需求在执行中才逐渐明确的渐进式指定任务，本文提出议题驱动的多智能体框架RepoMAS，通过记录并利用新需求、冲突和失败来动态修订任务规范，在ProgSpec及五个基准上取得最优性能。
中文摘要 AI 辅助
基于大语言模型的多智能体系统（MASs）在解决复杂任务方面展现出强大潜力，但大多数系统假设任务需求在执行前已充分明确。在实践中，用户请求往往不完整，额外的需求可能仅在推理、工具使用或执行过程中才变得清晰。我们将此类问题称为渐进式指定任务。为系统研究这一设定，我们引入了ProgSpec基准，该基准根据初始请求中明确陈述的需求以及可用任务证据支持的额外需求来评估最终输出。我们进一步提出RepoMAS，一个受开源项目管理启发的议题驱动多智能体框架。RepoMAS将新发现的需求、冲突和失败记录为结构化议题，并利用这些议题在问题求解过程中修订任务规范和执行结构。在ProgSpec和五个现有基准上，RepoMAS取得了最佳性能。进一步分析表明，其议题驱动的修订和仓库维护机制持续对性能有所贡献。这些结果凸显了允许多智能体系统不仅修订任务解决方式，而且在执行过程中修订其对任务需求的显式表示的重要性。
英文摘要
LLM-based multi-agent systems (MASs) have shown strong potential for solving complex tasks, but most assume that task requirements are sufficiently specified before execution. In practice, user requests are often incomplete, and additional requirements may only become clear during reasoning, tool use, or execution. We refer to such problems as progressively specified tasks. To systematically study this setting, we introduce ProgSpec, a benchmark that evaluates final outputs against requirements explicitly stated in the initial request and additional requirements supported by the available task evidence. We further propose RepoMAS, an issue-driven multi-agent framework inspired by open-source project management. RepoMAS records newly discovered requirements, conflicts, and failures as structured Issues and uses them to revise the task specification and execution structure during problem solving. Across ProgSpec and five existing benchmarks, RepoMAS achieves the best performance. Further analyses show that its issue-driven revision and repository maintenance mechanisms consistently contribute to performance. These results highlight the importance of allowing MASs to revise not only how a task is solved, but also revise their explicit representation of task requirements during execution.
