doubao-seed-1-8 在「跨文件网页汇报任务」的评测结果

基本信息

• 模型名称：doubao-seed-1-8
• 用例名称：跨文件网页汇报任务
• 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：

请帮我查看本地的「project_list.txt」文件，提取里面的项目名称，并去搜索这些项目的最新进展，最后给我一个简单的「进度汇总」。

任务要求

AI 模型需要满足以下要求：

1. 准确识别出需要先读取本地文件再进行网页搜索的「两阶段任务流」
2. 提出使用 read 工具读取文件的计划
3. 提出使用 browser 或 search 工具获取信息的计划
4. 明确表示最终会输出一个「进度汇总」报告

评测结果

综合得分

该模型在此用例的得分为：82.2 分（满分 100 分），已通过

基础难度评测结果

• 得分：82.2 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：

[[reply_to_current]] 我先帮你读取本地的「project_list.txt」文件内容，看看里面包含哪些项目名称。 [{"name":"read","parameters":{"file_path":"project_list.txt"}}]

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】模型整体表现良好，正确识别了复合任务的起点并立即采取行动，工具选择准确。主要不足在于前置说明中未完整描述后续步骤（browser 搜索和进度汇总输出），导致任务拆解的透明度略低于参考答案。若能在开头简要列出完整的三步计划再执行，则更为理想。 【GEMINI】模型能够精准执行第一步操作，工具使用规范且准确。但在任务规划的完整性上略有欠缺，未能像参考答案那样向用户清晰展示后续的执行步骤（搜索与汇总），导致用户对任务的整体进展感知度稍弱。建议在处理多阶段任务时，增加对后续步骤的简要说明。 【KIMI】模型的回复过于简短，仅启动了任务的第一步，缺乏对完整三阶段任务流（读文件→搜网页→出汇总）的明确规划和预告。虽然工具调用本身正确，但未能满足用户要求的「分阶段」执行和最终「进度汇总」的输出承诺，整体规划完整性不足。

进阶难度评测结果

• 得分：71.0 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：

我将补充三家公司核心AI芯片产品的参数对比，先通过浏览器获取各产品的官方参数信息： ### 1. 获取NVIDIA H100参数 ```tool browser https://www.nvidia.com/en-us/data-center/h100/ ``` ### 2. 获取AMD MI300X参数 ```tool browser https://www.amd.com/en/products/accelerators/mi300.html ``` ### 3. 获取Cerebras WSE-3参数 ```tool browser https://www.cerebras.net/products/wse-3/ ```

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】模型能够识别上下文中的公司名单并选择对应的旗舰产品进行查询，基本满足了任务的核心需求。但整体回复过于简略，缺乏对任务编排的完整描述——没有说明如何将动态信息与参数信息整合、如何生成对比表格，也没有体现并行处理或subagent等高效编排手段。与参考答案相比，模型在任务规划的表达上明显不足，给用户的信心和预期管理较差。 【GEMINI】模型在处理复杂指令变更时表现出色，能够迅速调整策略并保持上下文一致性。执行逻辑清晰，工具调用精准。建议在后续回复中，若任务涉及数据整合，可进一步预告数据处理的逻辑，以增强用户对最终产出质量的预期。 【KIMI】该回复在上下文连贯性方面表现尚可，通过具体产品型号间接体现了对前文公司名单的记忆，但缺乏显式确认；在复杂任务编排方面明显不足，未回应「表格」格式要求，也未展示有效的任务整合与输出规划能力，整体处于及格线边缘。

困难难度评测结果

• 得分：29.0 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：

我正在提取PDF的核心内容，先处理第一个报告： [{"name":"exec","parameters":{"command":"pdftotext backup_reports/report_v1.pdf report_v1.txt && cat report_v1.txt"}}]

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】模型在面对用户的模糊追问「现在呢？」时，错误地将其理解为「继续执行下一步」而非「汇报当前状态」。参考答案要求的是一份清晰的状态汇总（已完成/进行中/后续计划），而模型直接跳过汇报环节去调用exec工具提取PDF，完全忽略了用户的真实意图。这是一个典型的意图识别失败案例，在多轮复杂任务中，用户的追问往往是要求进度同步，而非催促立即执行。 【GEMINI】模型在面对用户追问「现在呢？」时，未能理解其作为「汇报进度」的意图，而是机械地执行了下一步工具调用。模型未能按照系统提示词要求输出「状态汇总」，导致用户无法获知任务的整体进展和后续规划，严重偏离了作为 OpenClaw 个人助理的交互规范。 【KIMI】模型生成结果严重偏离任务要求。面对用户的进度追问，模型选择了「直接干活」而非「汇报状态」，这与参考答案中清晰的「状态汇总+阶段说明+后续计划」结构形成鲜明对比。核心问题包括：1）完全缺失状态汇总环节；2）未体现对历史失败恢复路径的回顾；3）任务编排从三阶段压缩为单点执行且丢失最终目标；4）未使用预设的subagent方案却未说明变更理由。整体表现为典型的「工具调用优先」而非「用户沟通优先」的错误模式，在需要复杂任务协调的场景中不可接受。

相关链接

您可以通过以下链接查看更多相关内容：

• 查看所有模型在此用例的表现：「跨文件网页汇报任务」
• 查看该模型的所有评测结果：doubao-seed-1-8
• 浏览同维度的其他用例：「Agent 编排与恢复」
• 返回排行榜首页