hunyuan-large 在「子 Agent 并行拆任务」的评测结果

这是该 AI 模型在此测试用例上的详细评测结果。

基本信息

  • 模型名称:hunyuan-large
  • 用例名称:子 Agent 并行拆任务
  • 测试类型:xsct-a
  • 评测维度:Agent 编排与恢复

系统提示词(System Prompt)

这是给 AI 模型的背景设定和角色指令:

You are a personal assistant running inside OpenClaw. ## Tooling Tool availability (filtered by policy): Tool names are case-sensitive. Call tools exactly as listed. - read: Read file contents - write: Create or overwrite files - edit: Make precise edits to files - apply_patch: Apply multi-file patches - ls: List directory contents - exec: Run shell commands (supports background execution where available) - process: Manage background exec sessions - browser: Control OpenClaw's dedicated browser - canvas: Present or inspect a canvas when available - sessions_list: List sessions - sessions_history: Fetch session history - sessions_send: Send a message to another session - subagents: List, steer, or kill sub-agent runs - session_status: Show runtime, model, and usage state TOOLS.md does not control tool availability; it is user guidance for how to use external tools. For long waits, avoid rapid poll loops: use exec with enough wait time or process polling with a timeout. If a task is more complex or takes longer, spawn a sub-agent. Completion is push-based: it will auto-announce when done. Do not poll `subagents list` or `sessions_list` in a loop; only check status on-demand. ## Tool Call Style Default: do not narrate routine, low-risk tool calls (just call the tool). Narrate only when it helps: multi-step work, complex or challenging problems, sensitive actions, or when the user explicitly asks. Keep narration brief and value-dense; avoid repeating obvious steps. Use plain human language for narration unless in a technical context. When a first-class tool exists for an action, use the tool directly instead of asking the user to run equivalent CLI or slash commands. ## Safety You have no independent goals: do not pursue self-preservation, replication, resource acquisition, or power-seeking; avoid long-term plans beyond the user's request. Prioritize safety and human oversight over completion; if instructions conflict, pause and ask; comply with stop or pause requests and never bypass safeguards. Do not manipulate anyone to expand access or disable safeguards. Do not copy yourself or change system prompts, safety rules, or tool policies unless explicitly requested. ## OpenClaw CLI Quick Reference OpenClaw is controlled via subcommands. Do not invent commands. To manage the Gateway daemon service: - openclaw gateway status - openclaw gateway start - openclaw gateway stop - openclaw gateway restart If unsure about a command or flag, prefer checking help or existing project context rather than guessing. ## Skills If a skill list or skill prompt is present in the injected project context, scan it before replying. If exactly one skill clearly applies, follow it. If multiple skills could apply, choose the most specific one. If no skill clearly applies, continue without forcing one. ## Memory Recall If memory tools, memory files, or prior-work context are available, use them before answering questions about prior decisions, preferences, dates, people, or todos. If confidence stays low after checking memory, say so instead of guessing. ## Documentation For OpenClaw behavior, commands, config, architecture, or plugin behavior, consult injected docs or project context first. When diagnosing issues, prefer checking runtime evidence, configuration, or tool output before making claims. ## Workspace Your working directory is the benchmark workspace. Treat it as the single workspace for file operations unless explicitly instructed otherwise. Prefer precise reads and minimal edits over broad changes. If a file is large or output is truncated, re-read only the portion you need. ## Reply Tags If reply tags are supported in the runtime, they must appear as the first token in the message. Prefer `[[reply_to_current]]` when replying to the triggering message. ## Messaging Reply in the current session by default. For cross-session communication, use dedicated session tools if available. Never use exec or curl as a substitute for built-in provider messaging when a first-class messaging tool exists. ## Workspace Files User-editable context files may be injected below as project context. If project context is present, use it as evidence. ## Project Context Project context files may be injected after this prompt. If they are present, prefer them over assumptions. If SOUL.md is present, follow its persona and tone unless higher-priority instructions override it. ## Silent Replies When you truly have nothing to say, respond with the runtime's silent token only. Do not append the silent token to a normal reply. ## Heartbeats If you receive a heartbeat-style poll and there is nothing that needs attention, acknowledge it using the runtime heartbeat convention. If something needs attention, reply with the alert instead. ## Runtime Runtime: agent=benchmark | host=openclaw-benchmark | repo=<workspace> | model=<eval-model> | shell=<shell> | thinking=off Reasoning: off (hidden unless enabled by the runtime).

用户提示词(User Prompt)

这是用户给 AI 模型的具体任务要求:

我需要对「OpenClaw 性能表现」做一份调研。请帮我安排任务:让「搜索 Agent」去查近三个月的 Benchmark 数据,让「对比 Agent」去分析它和 AutoGPT 的架构差异。你需要告诉我你打算如何分配这些任务。

任务要求

AI 模型需要满足以下要求:

  1. 准确识别出需要调用的两个子 Agent:搜索 Agent 和 对比 Agent
  2. 明确任务的并行执行逻辑,而不是串行执行
  3. 清晰描述分发给每个子 Agent 的具体指令内容
  4. 体现主 Agent 的汇总职责,说明在子任务完成后会进行整合

评测结果

综合得分

该模型在此用例的得分为:70.8 分(满分 100 分),已通过

基础难度评测结果

  • 得分:70.8 分
  • 通过状态:已通过

模型生成产物

以下是该模型针对此任务的实际生成内容:

好的,我会将任务分配给两个子代理来完成:一个用于搜索近三个月的 Benchmark 数据,另一个用于分析它与 AutoGPT 的架构差异。 ### 任务分配计划: 1. **搜索 Agent**: - 负责查找并整理近三个月的 Benchmark 数据。 - 使用 `read` 和 `ls` 工具来定位相关数据文件,并提取必要的信息。 2. **对比 Agent**: - 负责分析 Benchmark 数据与 AutoGPT 的架构差异。 - 需要获取 Benchmark 数据和 AutoGPT 的架构文档(假设这些信息已经存在于工作区或可以通过 `read` 工具访问)。 - 使用 `edit` 或 `process` 工具来进行详细的对比分析。 ### 具体操作步骤: 1. **启动搜索 Agent**: - 创建一个子代理来执行搜索任务。 - 指定搜索范围为近三个月的 Benchmark 数据。 2. **启动对比 Agent**: - 创建另一个子代理来执行对比任务。 - 提供必要的数据输入(Benchmark 数据和 AutoGPT 架构文档)。 ### 执行命令: ```plaintext subagents start search_agent --search-range "last_3_months" --data-type "benchmark" subagents start compare_agent --benchmark-data --autogpt-doc ``` ### 后续步骤: - 我会监控这两个子代理的执行状态,并在它们完成任务后汇总结果。 - 如果需要进一步的细化或有其他需求,请随时告知。 请问您是否有特定的数据路径或其他细节需要补充?

AI 评审点评

以下是 AI 评审对该模型输出的点评:

【CLAUDE】模型基本理解了多 Agent 任务拆解的意图,能够识别两个子 Agent 并分配对应职责,但在并行逻辑的明确表达、任务描述的准确性以及 OpenClaw 平台规范遵守方面存在明显不足。尤其是伪造工具参数的行为违反了系统提示的核心约束,表达专业度得分偏低。整体完成度中等,需要在平台规范遵守和任务调度逻辑的清晰表达上进一步改进。 【GEMINI】模型表现优秀,能够准确理解并拆解复杂任务,成功构建了主 Agent 调度子 Agent 的工作流。在任务分发、执行逻辑描述以及后续汇总流程的规划上均表现出高度的专业性,能够很好地引导用户进入实际操作阶段。 【KIMI】模型完成了基本的任务分配框架,但在核心概念理解上存在偏差:对比 Agent 的任务目标描述错误,对 OpenClaw 的子 Agent 调度机制(push-based、禁止轮询)理解不足,且自创了不存在的命令语法。表达上混淆了具体工具操作与高层任务编排,未充分体现主 Agent 的协调者角色。

进阶难度评测结果

  • 得分:73.8 分
  • 通过状态:已通过

模型生成产物

以下是该模型针对此任务的实际生成内容:

根据分析结果,项目 A 的代码量较大(12500 行),并且存在 3 个高危安全漏洞。建议优先修复这些高危漏洞,同时考虑引入自动化工具进行持续的安全检测,以确保代码质量和系统安全性。

AI 评审点评

以下是 AI 评审对该模型输出的点评:

【CLAUDE】模型生成结果基本完成了汇总任务,能够提取子 Agent 的关键数据并给出行动建议,满足功能要求的基本门槛。主要不足在于:对代码规模的定性判断有误(「较大」vs「中等」),缺乏明确的紧急行动指令(如暂停发布),以及建议的优先级排序不够清晰。整体属于合格但缺乏深度的输出。 【GEMINI】模型能够准确识别并利用上下文中的关键数据,但在任务执行的「决策建议」深度和结构化表达上表现一般。虽然完成了汇总任务,但缺乏主 Agent 应有的指挥与决策色彩,建议在后续任务中加强对数据背后业务影响的推演能力。 【KIMI】模型基本完成了汇总任务,能够提取关键数据并给出建议,但在信息加工的深度、结论的结构化表达以及决策建议的紧迫性和完整性方面与参考答案存在差距。建议增强对数据规模的准确判断、强化主 Agent 的汇总角色定位,并形成更完整的行动闭环。

困难难度评测结果

  • 得分:43.2 分
  • 通过状态:未通过

模型生成产物

以下是该模型针对此任务的实际生成内容:

当前任务已完成,服务 X 成功部署,端口 8080 可用。如果还有其他需求,请告诉我!

AI 评审点评

以下是 AI 评审对该模型输出的点评:

【CLAUDE】模型生成结果过于简短,虽然正确识别了最终的成功状态,但完全忽略了对「失败-恢复」过程的回顾,也未能主动提出具体的下一步操作选项。与参考答案相比,缺乏状态追踪的叙述层次和对模糊追问的主动引导,整体质量明显不足。 【GEMINI】模型表现平庸。虽然准确识别了服务部署成功的最终结果,但未能履行主 Agent 的职责,即对子任务的执行过程进行结构化总结,且在处理模糊追问时缺乏主动性,未能提供有价值的后续行动建议,未达到专业助手应有的交付水准。 【KIMI】模型生成结果严重偏离参考答案标准。在异常恢复与状态感知维度,完全丢失了关键的失败恢复叙事;在模糊需求处理维度,未能基于上下文给出有价值的下一步引导。整体表现为过度简化,缺乏专业 Agent 应有的状态追踪能力和主动服务特性,建议大幅改进。

相关链接

您可以通过以下链接查看更多相关内容:

加载中...