arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.03549cs.AI
收藏

PARC:一种自主自反思编码代理,用于稳健执行长周期任务

PARC: An Autonomous Self-Reflective Coding Agent for Robust Execution of Long-Horizon Tasks

PARC

Yuki Orimo, Iori Kurata, Hodaka Mori, Ryuhei Okuno, Ryohto Sawada, Daisuke Okanohara

AI总结:

PARC是一种自主自反思编码代理,通过自我评估和反馈机制实现长周期任务的稳健执行,展示了AI在自主科学分析中的潜力。

摘要:

我们介绍了PARC,一种用于自主和稳健执行长周期计算任务的编码代理。PARC基于一种分层多智能体架构,整合了任务规划、执行以及一个评估其自身行动及其结果的独立上下文机制,并提供反馈,即自我评估和自我反馈。这种设计使PARC能够检测并纠正高层战略错误,并在没有人工干预的情况下维持进展。我们评估了PARC在计算科学和数据科学任务中的表现。在材料科学中,它能够自主复现关键结果,这些结果来自关于锂离子传导和合金分离的研究。特别是,它协调了数十个并行模拟任务,每个任务大约需要43小时的计算时间,负责编排、监控和错误纠正的全过程。在基于Kaggle的实验中,从最小的自然语言指令开始,PARC进行数据分析并实施搜索策略,产生与人类设计的基线相竞争的解决方案。这些结果突显了将分层多智能体系统与自我评估和自我反馈相结合的潜力,以使AI系统能够独立进行大规模的科学和分析工作。

英文摘要:

We introduce PARC, a coding agent for the autonomous and robust execution of long-horizon computational tasks. PARC is built on a hierarchical multi-agent architecture incorporating task planning, execution, and a mechanism that evaluates its own actions and their outcomes from an independent context and provides feedback, namely self-assessment and self-feedback. This design enables PARC to detect and correct high-level strategic errors and sustain progress without human intervention. We evaluate PARC across computational science and data science tasks. In materials science, it autonomously reproduces key results from studies on lithium-ion conduction and alloy segregation. In particular, it coordinates dozens of parallel simulation tasks, each requiring roughly 43 hours of computation, managing orchestration, monitoring, and error correction end-to-end. In Kaggle-based experiments, starting from minimal natural-language instructions, PARC conducts data analysis and implements search strategies, producing solutions competitive with human-engineered baselines. These results highlight the potential of integrating a hierarchical multi-agent system with self-assessment and self-feedback to enable AI systems capable of independent, large-scale scientific and analytical work.

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。

↑