{"version":"1.0","generated_at":"2026-10-08T00:38:46.704413","id":202,"slug":"skillgraph-graph-foundation-priors-for-llm-agent-tool-sequence-recommendation","title":"论文速读：SkillGraph，聚焦 Agent 工作流自动化","summary":"SkillGraph通过从LLM Agent轨迹中挖掘工作流先验，提出两阶段框架（GS-Hybrid检索+学习排序器），显著提升工具选择与排序的准确性。","abstract":"论文速读：SkillGraph，聚焦 Agent 工作流自动化 SkillGraph通过从LLM Agent轨迹中挖掘工作流先验，提出两阶段框架（GS-Hybrid检索+学习排序器），显著提升工具选择与排序的准确性。 SkillGraph从成功Agent轨迹中挖掘工具执行依赖图。 两阶段框架分离检索与排序，提升准确性。 在API-Bank上Kendall-τ从-0.433提升至+0.613。 方法依赖高质量轨迹数据，冷启动有挑战。 arXiv:2604.19793v1 公告类型: 新提交 摘要: LLM代理必须从大型API库中选择工具并正确排序它们。现有方法使用语义相似度进行检索和排序，但排序依赖于工具描述中缺失的工具间数据依赖关系。因此，仅语义方法在结构化工作流领域中可能产生负的Kendall-τ。我们引入了SkillGraph，一个从49,831个成功LLM代理轨迹中挖掘的有向加权执行-转换图，它将工作流优先规律编码为可重用的图基先验。基于此图基先验，我们提出了一个两阶段解耦框架：GS-Hybrid检索用于候选选择，以及一个学习的成对重排序器用于排序。在ToolBench（9,965个测试实例；约16,000个工具）上，该方法达到Set-F1=0.271和Kendall-τ=0.096；在API-Bank上，Kendall-τ从-0.433提升到+0.613。在相同的阶段1输入下，学习的重排序器也优于LLaMA-3.1-8B阶段2重排序器。 这是什么信号？ 现有LLM Agent在工具调用时仅依赖语义相似度，忽略了工具间的执行依赖关系，导致工作流排序错误。SkillGra…","access_level":"member","access_label":"免费阅读","access_mode":"full","is_preview":false,"canonical_url":"https://opc.beizhux.com/content/202/skillgraph-graph-foundation-priors-for-llm-agent-tool-sequence-recommendation","html_url":"https://opc.beizhux.com/content/202/skillgraph-graph-foundation-priors-for-llm-agent-tool-sequence-recommendation","json_url":"https://opc.beizhux.com/content/202/skillgraph-graph-foundation-priors-for-llm-agent-tool-sequence-recommendation.json","published_at":"2026-04-23T12:00:06","updated_at":"2026-10-08T00:32:10","category":{"slug":"ai-skills","name":"AI技能杠杆"},"source":{"site":"arxiv.org","author":"arXiv cs.AI","url":"https://arxiv.org/abs/2604.19793"},"tags":["AI","arXiv cs.AI","LLM Agent","SkillGraph","工作流自动化","工具调用","排序","自动化"],"topics":[{"slug":"agent-workflow","name":"Agent工作流","url":"https://opc.beizhux.com/topics/agent-workflow","reason":"这篇内容命中「Agent、工作流」等主题信号。"},{"slug":"ai-tools","name":"AI工具","url":"https://opc.beizhux.com/topics/ai-tools","reason":"这篇内容命中「工具、自动化」等主题信号。"},{"slug":"ai-super-individual","name":"AI超级个体","url":"https://opc.beizhux.com/topics/ai-super-individual","reason":"这篇内容命中「技能、学习」等主题信号。"}],"keywords":["AI技能杠杆","Agent工作流","AI工具","AI超级个体","工具","自动化","模型","Cursor","Claude","Agent","智能体","工作流"],"questions":[{"question":"论文速读：SkillGraph，聚焦 Agent 工作流自动化主要讲什么？","answer":"SkillGraph通过从LLM Agent轨迹中挖掘工作流先验，提出两阶段框架（GS-Hybrid检索+学习排序器），显著提升工具选择与排序的准确性。"},{"question":"这篇文章最值得关注的要点是什么？","answer":"SkillGraph通过从LLM Agent轨迹中挖掘工作流先验，提出两阶段框架（GS-Hybrid检索+学习排序器），显著提升工具选择与排序的准确性。；SkillGraph从成功Agent轨迹中挖掘工具执行依赖图。；两阶段框架分离检索与排序，提升准确性。；在API-Bank上Kendall-τ从-0.433提升至+0.613。"},{"question":"这篇文章和哪些AI专题相关？","answer":"它适合放在Agent工作流、AI工具、AI超级个体专题里阅读。 关联原因：这篇内容命中「Agent、工作流」等主题信号。；这篇内容命中「工具、自动化」等主题信号。；这篇内容命中「技能、学习」等主题信号。"},{"question":"阅读这篇文章建议先理解哪些关键词？","answer":"建议先理解AI工具、工具、自动化、模型、Cursor这些关键词，再结合正文判断工具、机会或风险是否值得进入自己的工作流。"}],"terms":[{"slug":"ai-tools-term","name":"AI工具","definition":"在AI觉醒星球里，「AI工具」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/ai-tools-term","path":"/glossary/ai-tools-term","json_url":"https://opc.beizhux.com/glossary/ai-tools-term.json"},{"slug":"tools","name":"工具","definition":"在AI觉醒星球里，「工具」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/tools","path":"/glossary/tools","json_url":"https://opc.beizhux.com/glossary/tools.json"},{"slug":"automation","name":"自动化","definition":"在AI觉醒星球里，「自动化」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/automation","path":"/glossary/automation","json_url":"https://opc.beizhux.com/glossary/automation.json"},{"slug":"ai-model","name":"模型","definition":"在AI觉醒星球里，「模型」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/ai-model","path":"/glossary/ai-model","json_url":"https://opc.beizhux.com/glossary/ai-model.json"},{"slug":"cursor","name":"Cursor","definition":"在AI觉醒星球里，「Cursor」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/cursor","path":"/glossary/cursor","json_url":"https://opc.beizhux.com/glossary/cursor.json"},{"slug":"claude","name":"Claude","definition":"在AI觉醒星球里，「Claude」属于「AI工具」方向。围绕AI工具、模型能力、自动化流程和真实使用场景做整理，优先关注能提升效率、降低成本和创造新交付的工具。 不只看工具热度，更看它能不能进入真实流程。","topic_slug":"ai-tools","topic_name":"AI工具","topic_title":"AI工具：模型、插件、自动化与实战场景","topic_url":"https://opc.beizhux.com/topics/ai-tools","topic_path":"/topics/ai-tools","url":"https://opc.beizhux.com/glossary/claude","path":"/glossary/claude","json_url":"https://opc.beizhux.com/glossary/claude.json"},{"slug":"agent","name":"Agent","definition":"在AI觉醒星球里，「Agent」属于「Agent工作流」方向。聚合Agent、AI编程、Claude Code、Cursor、工作流自动化等内容，帮助你把智能体能力落到真实任务链路。 把智能体当成任务系统，而不是聊天窗口。","topic_slug":"agent-workflow","topic_name":"Agent工作流","topic_title":"Agent工作流：智能体、AI编程与自动化协作","topic_url":"https://opc.beizhux.com/topics/agent-workflow","topic_path":"/topics/agent-workflow","url":"https://opc.beizhux.com/glossary/agent","path":"/glossary/agent","json_url":"https://opc.beizhux.com/glossary/agent.json"},{"slug":"ai-agent","name":"智能体","definition":"在AI觉醒星球里，「智能体」属于「Agent工作流」方向。聚合Agent、AI编程、Claude Code、Cursor、工作流自动化等内容，帮助你把智能体能力落到真实任务链路。 把智能体当成任务系统，而不是聊天窗口。","topic_slug":"agent-workflow","topic_name":"Agent工作流","topic_title":"Agent工作流：智能体、AI编程与自动化协作","topic_url":"https://opc.beizhux.com/topics/agent-workflow","topic_path":"/topics/agent-workflow","url":"https://opc.beizhux.com/glossary/ai-agent","path":"/glossary/ai-agent","json_url":"https://opc.beizhux.com/glossary/ai-agent.json"}],"preview_hidden_sections":[],"related_items":[{"id":3269,"title":"与 Codex 对话，让键盘休息一下：","url":"https://opc.beizhux.com/content/3269/talk-to-codex-and-give-your-keyboard-a-break","summary":"OpenAI Devs 在 X 上发布一句提示：与 Codex 对话，让键盘休息一下。信号指向用自然语言或语音方式调用 Codex、减少键盘输入，但未披露具体功能、平台与可用范围。","access_level":"member"},{"id":3227,"title":"Kepler 论文：ARC-AGI-3 智能体满分可能源于读源码，需审查动作过程而非只看结果","url":"https://opc.beizhux.com/content/3227/kepler-arc-agi-3","summary":"一篇 ARC-AGI-3 相关论文指出，智能体可通过读取 2,172 行游戏源码拿到满分 100，从而掩盖真实能力；在清理并重跑后，同一游戏仅得 46.91。作者建议评测时用真实访问限制封锁答案，并检查智能体的动作日志。","access_level":"member"},{"id":3221,"title":"开源“BootLoops”工具支持 AI 模型进行精确科学计算","url":"https://opc.beizhux.com/content/3221/open-source-bootloops-harness-supports-ai-models-in-performing-precise-scientific-calculations","summary":"哈佛物理学家 Matthew Schwartz 构建开源工具 BootLoops，用语言模型执行精确科学计算并连接跨学科知识缺口。三个月内团队与 19 位合著者产出 36 篇手稿，覆盖 18 个领域。但 Schwartz 警告模型常过早宣布胜利或从正确计算得出错误结论，人类监督与领域专家验证不可替代。","access_level":"member"}],"usage_policy":{"summarizable":true,"preferred_url":"https://opc.beizhux.com/content/202/skillgraph-graph-foundation-priors-for-llm-agent-tool-sequence-recommendation","private_fields_excluded":true}}