research-ideation

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Research Ideation

研究构思

A goal-driven workflow for finding important research problems, designing novel solutions, and building deep field understanding through structured paper reading.

一个目标驱动的工作流，用于通过结构化论文阅读寻找重要研究问题、设计新颖解决方案并构建深度领域认知。

When to Use This Skill

何时使用此Skill

User wants to find a research direction or brainstorm research ideas
User needs to do a literature review or map a research field
User asks about evaluating whether an idea is novel or worth pursuing
User wants to read papers more effectively or build a systematic reading habit
User mentions "research ideation", "find a problem", "literature tree", "novelty check", "paper reading"

用户希望寻找研究方向或头脑风暴研究创意
用户需要进行文献综述或绘制研究领域图谱
用户询问如何评估某个创意是否新颖或值得深入研究
用户希望更高效地阅读论文或建立系统性阅读习惯
用户提及“research ideation”、“寻找研究问题”、“literature tree”、“novelty check”、“论文阅读”

Goal-Driven Research Workflow

目标驱动的研究工作流

Follow these five steps in order. Each step builds on the previous one.

按顺序遵循以下五个步骤，每个步骤都建立在前一个步骤的基础上。

Step 1: Define a Long-Term Research Goal

步骤1：定义长期研究目标

Start with a goal that has both scientific and practical value. The goal should be ambitious enough to sustain multiple papers, but concrete enough to guide daily decisions.

Ask: "What is the ultimate form of this research direction? What would the world look like if this problem were fully solved?"

从一个兼具科学价值与实用价值的目标开始。该目标需足够宏大，能够支撑多篇论文的研究，同时又足够具体，可指导日常决策。

思考：“这个研究方向的最终形态是什么？如果该问题被完全解决，世界会变成什么样？”

Step 2: Build a Literature Tree

步骤2：构建文献树

Map the field by constructing two complementary trees:

Novelty tree: Classify existing work by milestone tasks, representative pipelines, and novel modules. This reveals WHERE the field has gaps.
Challenge-insight tree: Collect technical challenges and the insights/techniques that address them. This reveals WHICH problems lack good solutions.

See references/literature-tree.md for the full construction method and four types of novelty.

通过构建两棵互补的树来绘制领域图谱：

新颖性树：按里程碑任务、代表性流程和新颖模块对现有研究进行分类。这能揭示领域中存在哪些空白。
挑战洞见树：收集技术挑战以及解决这些挑战的洞见/技术。这能揭示哪些问题缺乏优质解决方案。

完整的构建方法及四种新颖性类型，请参阅references/literature-tree.md。

Step 3: Select a Problem

步骤3：选择研究问题

Find tasks with genuine research space. The key question: "Is this problem worth solving, or has a well-established solution already claimed this territory?"

Use the well-established solution check (4 levels) to decide whether to proceed or switch problems. Actively seek new failure cases rather than improving on known benchmarks.

See references/problem-selection.md for the full selection framework.

寻找具备真实研究空间的任务。核心问题：“这个问题是否值得解决，还是已有成熟解决方案占据了该领域？”

使用成熟解决方案核查（四个层级）来决定是否继续推进或更换问题。积极寻找新的失败案例，而非在已知基准上进行改进。

完整的选择框架，请参阅references/problem-selection.md。

Step 4: Design a Solution

步骤4：设计解决方案

Novel techniques are creative combinations of existing methods, not simple concatenations. Use two design patterns:

Cross-domain transfer: Find papers in completely different domains that solve a technically similar problem, then adapt their solution.
Problem decomposition: Break the problem into sub-problems, solve each via cross-domain transfer, then combine.

See references/solution-design.md for the full design methodology and knowledge distillation pipeline.

新颖技术是现有方法的创造性组合，而非简单拼接。使用两种设计模式：

跨领域迁移：寻找完全不同领域中解决技术相似问题的论文，然后适配其解决方案。
问题分解：将问题拆分为子问题，通过跨领域迁移解决每个子问题，再进行整合。

完整的设计方法及知识蒸馏流程，请参阅references/solution-design.md。

Step 5: Validate and Iterate

步骤5：验证与迭代

Run experiments on representative data. Use results to refine your understanding. If the approach fails, return to Step 3 or Step 4 with updated knowledge from the failure.

Output artifacts: Research direction summary (problem statement, proposed approach, novelty claim, key risks) — this becomes the input to

idea-tournament

paper-planning

See the

experiment-craft

skill for systematic debugging when experiments don't work as expected.

在代表性数据上开展实验。利用实验结果深化认知。如果方法失败，结合失败带来的新认知返回步骤3或步骤4。

产出物：研究方向摘要（问题陈述、拟议方法、新颖性声明、关键风险）—— 这将作为

idea-tournament

或

paper-planning

的输入。

当实验未达到预期效果时，请使用

experiment-craft

Skill进行系统性调试。

Counterintuitive Ideation Rules

反常识的构思规则

Prioritize these rules before regular ideation:

Problem selection matters more than solution design: Choosing WHAT to solve has more impact than HOW you solve it. A great solution to an unimportant problem is still unimportant.
Pursue new failure cases, not incremental improvements: Don't improve a technique on its original setting. Find new settings where it breaks — new failure cases on new data are contributions even if the technique itself isn't novel.
If a well-established solution exists, switch problems: Solving an already-solved problem wastes time regardless of your angle. Improvement space is too small.
Technology is creative combination, not concatenation: Novel techniques combine existing methods in non-obvious ways. Simple A-to-B pipelines are not contributions — if direct concatenation worked, the problem would have no technical challenge.
When a breakthrough tool appears, apply it to YOUR roadmap: Don't improve the tool itself on its original benchmarks. Use it to solve YOUR milestone tasks — this produces high-impact work because you combine the tool's power with your domain expertise.
A paper without real contribution wastes your time: Even if accepted, it doesn't advance the field or earn respect. Do work that genuinely moves the needle.

在常规构思前，请优先遵循以下规则：

问题选择比解决方案设计更重要：选择“解决什么”比“如何解决”的影响更大。针对不重要问题的优秀解决方案依然没有价值。
追求新的失败案例，而非增量改进：不要在技术的原始场景上进行改进。寻找该技术失效的新场景——即使技术本身不新颖，新数据上的新失败案例也属于研究贡献。
若已有成熟解决方案，更换问题：解决已被解决的问题只会浪费时间，无论你的切入角度如何。改进空间极小。
技术是创造性组合，而非简单拼接：新颖技术以非显而易见的方式组合现有方法。简单的A到B流程不属于研究贡献——如果直接拼接就能奏效，该问题就不存在技术挑战。
当突破性工具出现时，将其应用到你的研究路线图中：不要在该工具的原始基准上改进工具本身。用它来解决你的里程碑任务——这会产出高影响力的研究，因为你将工具的能力与你的领域专业知识相结合。
无真实贡献的论文只会浪费你的时间：即使论文被录用，也无法推动领域发展或赢得认可。请做真正能推动领域进步的工作。

Structured Paper Reading

结构化论文阅读

Turn reading into structured Q&A using a paper parsing tree. Three levels of depth:

Level	Goal	What You Can Do After
1. Technical	Understand all details and terminology	Reproduce the method; explain each component
2. Analytical	Know what problem it solves and why this approach	Explain the paper's motivation and design choices
3. Contextual	Know its position in the literature tree	Update your field map; generate new research questions

Write a structured summary for every paper you read. Use the template at assets/paper-summary-template.md.

See references/paper-reading.md for the full reading methodology and habit-building guidance.

利用论文解析树将阅读转化为结构化问答。三个深度层级：

层级	目标	完成后可开展的工作
1. 技术层	理解所有细节与术语	复现该方法；解释每个组件
2. 分析层	了解论文解决的问题及该方法的设计原因	解释论文的动机与设计选择
3. 语境层	了解论文在文献树中的位置	更新你的领域图谱；生成新的研究问题

为每篇阅读的论文撰写结构化摘要。请使用assets/paper-summary-template.md中的模板。

完整的阅读方法及习惯养成指导，请参阅references/paper-reading.md。

Handoff to Idea Tournament or Planning

转交至Idea Tournament或论文规划

When you have a research direction but want to explore multiple concrete approaches, pass to

idea-tournament

for tree-structured generation and Elo ranking before planning.

When ideation is complete — you have a problem, a proposed solution approach, and supporting literature — pass these artifacts to

paper-planning

Artifact	Source Step	Used By
Research goal and scope	Step 1	Story design (task definition)
Literature tree (novelty + challenge-insight)	Step 2	Related work mapping, novelty claims
Problem statement and motivation	Step 3	Introduction motivation paragraphs
Solution sketch and design rationale	Step 4	Method section planning
Key failure cases to address	Step 3	Experiment planning (stress tests)
Relevant prior work and their limitations	Step 2	Baseline selection, comparison design

当你已有研究方向但希望探索多种具体方法时，可将其转交至

idea-tournament

进行树状生成和Elo排名，之后再进行规划。

当构思完成后——你已确定问题、拟议解决方案及相关文献——将这些产出物转交至

paper-planning

：

产出物	来源步骤	使用方
研究目标与范围	步骤1	故事设计（任务定义）
文献树（新颖性+挑战洞见）	步骤2	相关工作图谱、新颖性声明
问题陈述与动机	步骤3	引言动机段落
解决方案草图与设计依据	步骤4	方法部分规划
需要解决的关键失败案例	步骤3	实验规划（压力测试）
相关前人工作及其局限性	步骤2	基线选择、对比设计

Reference Navigation

参考资料导航

Topic	Reference File	When to Use
Literature tree construction	literature-tree.md	Mapping a research field
Problem selection	problem-selection.md	Evaluating whether a problem is worth solving
Solution design	solution-design.md	Designing a novel approach
Paper reading methodology	paper-reading.md	Reading papers effectively
Paper summary template	paper-summary-template.md	Writing structured paper notes

主题	参考文件	适用场景
文献树构建	literature-tree.md	绘制研究领域图谱
研究问题选择	problem-selection.md	评估问题是否值得解决
解决方案设计	solution-design.md	设计新颖方法
论文阅读方法	paper-reading.md	高效阅读论文
论文摘要模板	paper-summary-template.md	撰写结构化论文笔记