PulseAugur
中
实时 09:20:26
English(EN) ProgAgent: Learning Tool Orchestration through Programmatic Training

ProgAgent框架通过程序化训练增强LLM工具编排

研究人员推出了一种名为ProgAgent的新训练框架,旨在改进大型语言模型(LLM)在复杂、长周期任务中编排工具的能力。与可能遭受上下文衰减的传统直接工具调用(DTC)方法不同,ProgAgent通过可执行代码调用工具并在运行时变量中管理中间结果,从而利用程序化工具调用(PTC)。该方法在合成任务集上进行训练,与基线模型相比,已显示出更高的成功率,特别是在LOCA-bench上取得了30.7%的通过率,而其他模型得分为零。 AI

影响 这项研究可能带来更强大的LLM代理,能够更可靠地处理复杂的、多步骤的任务。

排序理由 该集群描述了一篇详细介绍LLM新训练框架的新研究论文。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

ProgAgent框架通过程序化训练增强LLM工具编排

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群描述了一篇详细介绍LLM新训练框架的新研究论文。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
5 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Hao Li, Keqing He, Longtao Zheng, Junlong Li, Weihao Zeng, Qian Liu, Yuzhen Huang ·

    ProgAgent:通过程序化训练学习工具编排

    arXiv:2610.14774v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly expected to orchestrate diverse tools over long-horizon tasks. Existing agents typically use Direct Tool Calling (DTC), where the model invokes tools sequentially, and tool responses acc…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    ProgAgent:通过程序化训练学习工具编排

    Large language models (LLMs) are increasingly expected to orchestrate diverse tools over long-horizon tasks. Existing agents typically use Direct Tool Calling (DTC), where the model invokes tools sequentially, and tool responses accumulate in the model context, which can lead to …