# Brainstorming Research Ideas

> Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.

- Skill: `tianhao909/brainstorming-research-ideas` (Agent Skill)
- Install (CLI): `npx skillmds add tianhao909/brainstorming-research-ideas`
- Raw SKILL.md: https://api.skillmd.com/api/skills/tianhao909/brainstorming-research-ideas/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- License: MIT
- Author: tianhao909 (https://skillmd.com/u/tianhao909)
- Updated: 2026-08-19
- Page: https://skillmd.com/skills/tianhao909/brainstorming-research-ideas

---


# 科研想法头脑风暴 | Research Idea Brainstorming

发现下一个研究想法的结构化框架。本技能提供十个互补的创意视角，帮助研究人员从模糊的好奇心转向具体、可辩护的研究提案。每个框架针对不同的认知模式——单独使用或组合使用进行全面探索。

Structured frameworks for discovering the next research idea. This skill provides ten complementary ideation lenses that help researchers move from vague curiosity to concrete, defensible research proposals. Each framework targets a different cognitive mode—use them individually or combine them for comprehensive exploration.

## 何时使用此技能 | When to Use This Skill

- 开始新的研究方向，需要结构化探索
- 对当前项目感到困顿，想要新的角度
- 评估一个半成形的想法是否具有真正的潜力
- 为与合作者的头脑风暴会议做准备
- 在研究领域之间转换，寻求高杠杆的切入点
- 回顾一个领域，寻找未被充分探索的空白

- Starting a new research direction and need structured exploration
- Feeling stuck on a current project and want fresh angles
- Evaluating whether a half-formed idea has real potential
- Preparing for a brainstorming session with collaborators
- Transitioning between research areas and seeking high-leverage entry points
- Reviewing a field and looking for underexplored gaps

**请勿在以下情况使用此技能**：
- 你已经有一个明确的研究问题，需要执行指导
- 你需要实验设计或方法论方面的帮助（请使用领域特定技能）
- 你想要文献综述（请使用 `scientific-skills:literature-review`）

**Do NOT use this skill when**:
- You already have a well-defined research question and need execution guidance
- You need help with experimental design or methodology (use domain-specific skills)
- You want a literature review (use `scientific-skills:literature-review`)

---

## 核心创意框架 | Core Ideation Frameworks

### 1. 问题优先vs解决方案优先思维 | 1. Problem-First vs. Solution-First Thinking

研究想法来自两种不同的模式。知道自己在哪种模式可以防止常见失败：构建缺乏真正问题的解决方案，或追求没有可行方法的问题。

Research ideas originate from two distinct modes. Knowing which mode you are in prevents a common failure: building solutions that lack real problems, or chasing problems without feasible approaches.

**问题优先**（痛点→方法）：
- 从具体的失败、瓶颈或未满足的需求开始
- 自然产生有影响力的工作，因为动机是内在的
- 风险：可能收敛到增量修复而非范式转变

**Problem-First** (pain point → method):
- Start with a concrete failure, bottleneck, or unmet need
- Naturally yields impactful work because the motivation is intrinsic
- Risk: may converge on incremental fixes rather than paradigm shifts

**解决方案优先**（新能力→应用）：
- 从寻求应用的新工具、洞察或技术开始
- 通常通过解锁先前不可能的方法来推动突破
- 风险：「锤子找钉子」——解决方案可能缺乏真正的需求

**Solution-First** (new capability → application):
- Start with a new tool, insight, or technique seeking application
- Often drives breakthroughs by unlocking previously impossible approaches
- Risk: "hammer looking for a nail"—solution may lack genuine demand

**工作流**：
1. 用一句话写下你的想法
2. 分类：这是问题优先还是解决方案优先？
3. 如果问题优先 → 验证问题是否重要（谁受苦？多少？）
4. 如果解决方案优先 → 识别它至少解决的两个真正问题
5. 对于任一模式，阐明差距：今天什么不能做，而这是能 enabled 的？

**Workflow**:
1. Write down your idea in one sentence
2. Classify it: Is this problem-first or solution-first?
3. If problem-first → verify the problem matters (who suffers? how much?)
4. If solution-first → identify at least two genuine problems it addresses
5. For either mode, articulate the gap: what cannot be done today that this enables?

**自检**：
- [ ] 我能说出谁需要这个吗？
- [ ] 我解决的问题实际上是未解决的吗（不只是营销不足）？
- [ ] 如果是解决方案优先，解决方案是否创造了新能力，还是只是复制现有的？

**Self-Check**:
- [ ] Can I name a specific person or community who needs this?
- [ ] Is the problem I am solving actually unsolved (not just under-marketed)?
- [ ] If solution-first, does the solution create new capability or just replicate existing ones?

---

### 2. 抽象阶梯 | 2. The Abstraction Ladder

每个研究问题都处于特定的抽象层次。故意上下移动阶梯会揭示在你当前层次看不到的想法。

Every research problem sits at a particular level of abstraction. Deliberately moving up or down the ladder reveals ideas invisible at your current level.

| 方向 | 行动 | 结果 |
|-----------|--------|---------|
| **上移**（泛化） | 将具体结果转化为更广泛的原则 | 框架论文、理论贡献 |
| **下移**（实例化） | 在具体约束下测试通用范式 | 经验论文、令人惊讶的失败分析 |
| **侧移**（类比） | 将相同抽象层次应用于相邻领域 | 交叉授粉、迁移论文 |

| Direction | Action | Outcome |
|-----------|--------|---------|
| **Move Up** (generalize) | Turn a specific result into a broader principle | Framework papers, theoretical contributions |
| **Move Down** (instantiate) | Test a general paradigm under concrete constraints | Empirical papers, surprising failure analyses |
| **Move Sideways** (analogize) | Apply same abstraction level to adjacent domain | Cross-pollination, transfer papers

**工作流**：
1. 用一句话陈述你当前的研究重点
2. 上移：这背后的普遍原则是什么？这属于哪类问题？
3. 下移：最具体、受约束的实例是什么？极端情况下会发生什么？
4. 侧移：这个模式还出现在其他什么领域？
5. 对于每个新层次，问：这本身是一个可发表的吗？

**Workflow**:
1. State your current research focus in one sentence
2. Move UP: What is the general principle behind this? What class of problems does this belong to?
3. Move DOWN: What is the most specific, constrained instance of this? What happens at the extreme?
4. Move SIDEWAYS: Where else does this pattern appear in a different field?
5. For each new level, ask: Is this a publishable contribution on its own?

**示例**：
- **当前**：「提高RAG系统的检索准确率」
- **上移**：「什么使上下文选择对任何增强生成系统有效？」
- **下移**：「当文档受到对抗性干扰时检索准确率如何下降？」
- **侧移**：「数据库查询优化使用类似的相关性排序——我们可以借鉴什么？」

**Example**:
- **Current**: "Improving retrieval accuracy for RAG systems"
- **Up**: "What makes context selection effective for any augmented generation system?"
- **Down**: "How does retrieval accuracy degrade when documents are adversarially perturbed?"
- **Sideways**: "Database query optimization uses similar relevance ranking—what can we borrow?"

---

### 3. 张力与矛盾寻找 | 3. Tension and Contradiction Hunting

突破往往来自于解决广泛接受但看似冲突的目标之间的张力。这些矛盾不是bug——它们是研究机会。

Breakthroughs often come from resolving tensions between widely accepted but seemingly conflicting goals. These contradictions are not bugs—they are the research opportunity.

**常见研究张力**：

| 张力对 | 研究机会 |
|-------------|---------------------|
| 性能↔效率 | 我们能用10倍更少的计算匹配SOTA吗？ |
| 隐私↔效用 | 联邦/加密方法能缩小准确率差距吗？ |
| 通用性↔专业化 | 何时微调优于提示，为什么？ |
| 安全性↔能力 | 对齐能否改进而非拖累能力？ |
| 可解释性↔性能 | 机制性洞察能否带来更好的架构？ |
| 规模↔可访问性 | 小模型能复现涌现行为吗？

**Common Research Tensions**:

| Tension Pair | Research Opportunity |
|-------------|---------------------|
| Performance ↔ Efficiency | Can we match SOTA with 10x less compute? |
| Privacy ↔ Utility | Can federated/encrypted methods close the accuracy gap? |
| Generality ↔ Specialization | When does fine-tuning beat prompting, and why? |
| Safety ↔ Capability | Can alignment improve rather than tax capability? |
| Interpretability ↔ Performance | Do mechanistic insights enable better architectures? |
| Scale ↔ Accessibility | Can small models replicate emergent behaviors?

**工作流**：
1. 选择你的研究领域
2. 列出前3-5个愿望清单（每个人都想要的东西）
3. 识别通常被视为权衡的对
4. 对于每对，问：这个权衡是根本性的还是当前方法的产物？
5. 如果是产物 → 和解本身就是你的研究贡献
6. 如果是根本性的 → 表征帕累托前沿本身就有价值

**Workflow**:
1. Pick your research area
2. List the top 3-5 desiderata (things everyone wants)
3. Identify pairs that are commonly treated as trade-offs
4. For each pair, ask: Is this trade-off fundamental or an artifact of current methods?
5. If artifact → the reconciliation IS your research contribution
6. If fundamental → characterizing the Pareto frontier is itself valuable

**自检**：
- [ ] 我确认这个张力是真实的（而不只是假设）？
- [ ] 我能指出分别优化每边的论文吗？
- [ ] 我提出的和解在技术上是合理的，而不只是雄心勃勃的？

**Self-Check**:
- [ ] Have I confirmed this tension is real (not just assumed)?
- [ ] Can I point to papers that optimize for each side independently?
- [ ] Is my proposed reconciliation technically plausible, not just aspirational?

---

### 4. 交叉授粉（类比迁移）| 4. Cross-Pollination (Analogy Transfer)

从其他学科借用结构性想法是最具生成性的研究启发式之一。许多基础技术就是这样产生的——注意力机制借鉴认知科学，遗传算法借鉴生物学，对抗训练借鉴博弈论。

Borrowing structural ideas from other disciplines is one of the most generative research heuristics. Many foundational techniques emerged this way—attention mechanisms draw from cognitive science, genetic algorithms from biology, adversarial training from game theory.

**有效类比的要求**：
- **结构性保真**：映射必须在底层机制层面保持，而不仅仅是表面相似性
- **非显而易见连接**：如果联系广为人知，新颖性就消失了
- **可验证预测**：类比应该产生具体假设

**Requirements for a Valid Analogy**:
- **Structural fidelity**: The mapping must hold at the level of underlying mechanisms, not just surface similarity
- **Non-obvious connection**: If the link is well-known, the novelty is gone
- **Testable predictions**: The analogy should generate concrete hypotheses

**机器学习研究的高收益源领域**：

| 源领域 | 可迁移概念 |
|-------------|----------------------|
| 神经科学 | 注意力、记忆整合、分层处理 |
| 物理学 | 基于能量的模型、相变、重整化 |
| 经济学 | 机制设计、拍卖理论、激励对齐 |
| 生态学 | 种群动态、生态位竞争、协同进化 |
| 语言学 | 组合性、语用学、语法归纳 |
| 控制理论 | 反馈回路、稳定性、自适应调节 |

**High-Yield Source Fields for ML Research**:

| Source Field | Transferable Concepts |
|-------------|----------------------|
| Neuroscience | Attention, memory consolidation, hierarchical processing |
| Physics | Energy-based models, phase transitions, renormalization |
| Economics | Mechanism design, auction theory, incentive alignment |
| Ecology | Population dynamics, niche competition, co-evolution |
| Linguistics | Compositionality, pragmatics, grammatical induction |
| Control Theory | Feedback loops, stability, adaptive regulation

**工作流**：
1. 用领域无关的语言描述你的问题（去除术语）
2. 问：什么其他领域解决结构相似的问题？
3. 在机制层面研究该领域的解决方案
4. 将解决方案映射回你的领域，保持结构性关系
5. 从类比生成可验证的预测
6. 验证：借用的想法实际上改善了结果吗？

**Workflow**:
1. Describe your problem in domain-agnostic language (strip the jargon)
2. Ask: What other field solves a structurally similar problem?
3. Study that field's solution at the mechanism level
4. Map the solution back to your domain, preserving structural relationships
5. Generate testable predictions from the analogy
6. Validate: Does the borrowed idea actually improve outcomes?

---

### 5. 「什么变了？」原则 | 5. The "What Changed?" Principle

好想法往往来自在新条件下重新审视旧问题。硬件、规模、数据可用性或法规的进步可以使先前的假设失效，并使先前不切实际的方法变得可行。

Strong ideas often come from revisiting old problems under new conditions. Advances in hardware, scale, data availability, or regulations can invalidate prior assumptions and make previously impractical approaches viable.

**需要监测的变化类别**：

| 变化类型 | 示例 | 研究含义 |
|------------|---------|---------------------|
| **计算** | GPU快10倍 | 因太贵而被忽略的方法变得可行 |
| **规模** | 万亿token数据集 | 小规模失败的统计论点现在可能成立 |
| **法规** | 欧盟AI法案、GDPR | 创造对合规替代方案的需求 |
| **工具** | 新框架、API | 降低复杂方法的实现门槛 |
| **失败** | 高调系统失败 | 暴露现有方法的空白 |
| **文化** | 新用户行为 | 改变什么问题是重要的 |

**Categories of Change to Monitor**:

| Change Type | Example | Research Implication |
|------------|---------|---------------------|
| **Compute** | GPUs 10x faster | Methods dismissed as too expensive become feasible |
| **Scale** | Trillion-token datasets | Statistical arguments that failed at small scale may now hold |
| **Regulation** | EU AI Act, GDPR | Creates demand for compliant alternatives |
| **Tooling** | New frameworks, APIs | Reduces implementation barrier for complex methods |
| **Failure** | High-profile system failures | Exposes gaps in existing approaches |
| **Cultural** | New user behaviors | Shifts what problems matter most

**工作流**：
1. 选择一个著名的负面结果或被放弃的方法（3-10年历史）
2. 列出导致其被拒绝的假设
3. 对于每个假设，问：这今天仍然成立吗？
4. 如果任何假设已被否定 → 在新条件下重新运行这个想法
5. 阐述贡献：「X之前不切实际是因为Y，但Z已经改变」

**Workflow**:
1. Pick a well-known negative result or abandoned approach (3-10 years old)
2. List the assumptions that led to its rejection
3. For each assumption, ask: Is this still true today?
4. If any assumption has been invalidated → re-run the idea under new conditions
5. Frame the contribution: "X was previously impractical because Y, but Z has changed"

---

### 6. 失败分析与边界探测 | 6. Failure Analysis and Boundary Probing

理解方法在哪里失效通常与展示它在哪里有效一样有价值。边界探测系统性地揭示公认技术失效的条件。

Understanding where a method breaks is often as valuable as showing where it works. Boundary probing systematically exposes the conditions under which accepted techniques fail.

**需要探测的边界类型**：
- **分布**：输入分布外会发生什么？
- **规模**：方法在10倍或0.1倍典型规模下会退化吗？
- **对抗**：方法可以被故意破坏吗？
- **组合**：结合多个能力时性能是否保持？
- **时间**：方法会随时间退化吗（概念漂移）？

**Types of Boundaries to Probe**:
- **Distributional**: What happens with out-of-distribution inputs?
- **Scale**: Does the method degrade at 10x or 0.1x the typical scale?
- **Adversarial**: Can the method be deliberately broken?
- **Compositional**: Does performance hold when combining multiple capabilities?
- **Temporal**: Does the method degrade over time (concept drift)?

**工作流**：
1. 选择一个被广泛使用、报告结果强劲的方法
2. 识别其评估中的隐含假设（数据集、规模、领域）
3. 系统性地违反每个假设
4. 记录方法在哪里以及如何失效
5. 诊断每个失败的根本原因
6. 提出修复或解释为什么失败是根本性的

**Workflow**:
1. Select a widely-used method with strong reported results
2. Identify the implicit assumptions in its evaluation (dataset, scale, domain)
3. Systematically violate each assumption
4. Document where and how the method breaks
5. Diagnose the root cause of each failure
6. Propose a fix or explain why the failure is fundamental

**自检**：
- [ ] 我是在探测真正的边界，而不仅仅是确认已知的限制？
- [ ] 我能解释为什么方法失效，而不只是说它失效？
- [ ] 我的分析是否指明了一条建设性的前进道路？

**Self-Check**:
- [ ] Am I probing genuine boundaries, not just confirming known limitations?
- [ ] Can I explain WHY the method fails, not just THAT it fails?
- [ ] Does my analysis suggest a constructive path forward?

---

### 7. 简单性测试 | 7. The Simplicity Test

在接受复杂性之前，问一个更简单的方法是否就足够了。领域有时会过度关注复杂方案，而精简的基线其实也很有竞争力。

Before accepting complexity, ask whether a simpler approach suffices. Fields sometimes over-index on elaborate solutions when a streamlined baseline performs competitively.

**不必要复杂性的警告信号**：
- 方法有很多超参数，最优范围很窄
- 消融显示大多数组件贡献很小
- 一个简单的基线从未被适当调整或评估
- 与基线相比改进在大多数基准上在噪声范围内

**Warning Signs of Unnecessary Complexity**:
- The method has many hyperparameters with narrow optimal ranges
- Ablations show most components contribute marginally
- A simple baseline was never properly tuned or evaluated
- The improvement over baselines is within noise on most benchmarks

**工作流**：
1. 识别你问题的当前SOTA方法
2. 将其剥离到最简单的核心（什么是这一个关键想法？）
3. 仔细工程构建那个最小版本
4. 公平比较：相同计算预算、相同调优 effort
5. 如果差距小 → 贡献就是简单性本身
6. 如果差距大 → 你现在理解了复杂性带来了什么

**Workflow**:
1. Identify the current SOTA method for your problem
2. Strip it to its simplest possible core (what is the one key idea?)
3. Build that minimal version with careful engineering
4. Compare fairly: same compute budget, same tuning effort
5. If the gap is small → the contribution is the simplicity itself
6. If the gap is large → you now understand what the complexity buys

**贡献阐述**：
- 「我们展示[简单方法]加[一个修改]匹配[复杂SOTA]」
- 「我们识别[特定组件]是关键驱动因素，而非[其他组件]」

**Contribution Framing**:
- "We show that [simple method] with [one modification] matches [complex SOTA]"
- "We identify [specific component] as the critical driver, not [other components]"

---

### 8. 利益相关者轮换 | 8. Stakeholder Rotation

从多个视角看待一个系统会揭示不同类别的研究问题。每个利益相关者看到不同的摩擦、风险和机会。

Viewing a system from multiple perspectives reveals distinct classes of research questions. Each stakeholder sees different friction, risk, and opportunity.

**利益相关者视角**：

| 利益相关者 | 关键问题 |
|-------------|---------------|
| **终端用户** | 这个可用吗？什么错误是不可接受的？延迟容限是多少？ |
| **开发者** | 这个可调试吗？维护负担是什么？它如何组合？ |
| **理论家** | 为什么这有效？有什么正式保证？差距在哪里？ |
| **对手** | 这如何被利用？攻击面是什么？ |
| **伦理学家** | 谁受伤害？嵌入什么偏见？谁被排除？ |
| **监管者** | 这可审计吗？决策能解释吗？有问责制吗？ |
| **运营者** | 成本是多少？如何扩展？失败模式是什么？ |

**Stakeholder Perspectives**:

| Stakeholder | Key Questions |
|-------------|---------------|
| **End User** | Is this usable? What errors are unacceptable? What is the latency tolerance? |
| **Developer** | Is this debuggable? What is the maintenance burden? How does it compose? |
| **Theorist** | Why does this work? What are the formal guarantees? Where are the gaps? |
| **Adversary** | How can this be exploited? What are the attack surfaces? |
| **Ethicist** | Who is harmed? What biases are embedded? Who is excluded? |
| **Regulator** | Is this auditable? Can decisions be explained? Is there accountability? |
| **Operator** | What is the cost? How does it scale? What is the failure mode?

**工作流**：
1. 用一段话描述你的系统或方法
2. 轮流假设每个利益相关者视角（每个角色5分钟）
3. 对于每个视角，列出前3个关切或问题
4. 识别哪些关切是现有工作未解决的
5. 具有最广泛影响的未解决关切就是你的研究问题

**Workflow**:
1. Describe your system or method in one paragraph
2. Assume each stakeholder perspective in turn (spend 5 minutes per role)
3. For each perspective, list the top 3 concerns or questions
4. Identify which concerns are unaddressed by existing work
5. The unaddressed concern with the broadest impact is your research question

---

### 9. 组合与分解 | 9. Composition and Decomposition

新颖性往往来自重组或模块化。创新 frequently lies not in new primitives, but in how components are arranged or separated.

**组合**（组合现有技术）：
- 识别两种解决互补子问题的方法
- 问：组合它们会产生什么新出现的能力？
- 示例：RAG + 思维链 → 检索增强推理

**分解**（分解整体系统）：
- 识别具有纠缠组件的复杂系统
- 问：哪个组件是真正的瓶颈？
- 示例：将「微调」分解为数据选择、优化和正则化，表明数据选择往往最重要

Novelty often emerges from recombination or modularization. Innovation frequently lies not in new primitives, but in how components are arranged or separated.

**Composition** (combining existing techniques):
- Identify two methods that solve complementary subproblems
- Ask: What emergent capability arises from combining them?
- Example: RAG + Chain-of-Thought → retrieval-augmented reasoning

**Decomposition** (breaking apart monolithic systems):
- Identify a complex system with entangled components
- Ask: Which component is the actual bottleneck?
- Example: Decomposing "fine-tuning" into data selection, optimization, and regularization reveals that data selection often matters most

**工作流**：
1. 列出你领域的5-10个关键组件或技术
2. **组合**：选择配对，问组合它们会发生什么
3. **分解**：选择一个复杂方法，隔离每个组件的贡献
4. 对于组合：组合是否产生了新出现的能力？
5. 对于分解：隔离是否揭示了主导或冗余组件？

**Workflow**:
1. List the 5-10 key components or techniques in your area
2. **Compose**: Pick pairs and ask what happens when you combine them
3. **Decompose**: Pick a complex method and isolate each component's contribution
4. For compositions: Does the combination create emergent capabilities?
5. For decompositions: Does isolation reveal a dominant or redundant component?

---

### 10. 「解释给某人听」测试 | 10. The "Explain It to Someone" Test

一个强有力的研究想法应该能向聪明的非专业人士用两句话来辩护。这个测试强制明确目的并锐化价值主张。

A strong research idea should be defensible in two sentences to a smart non-expert. This test enforces clarity of purpose and sharpens the value proposition.

**两句话模板**：
> **第1句话**（问题）：「[领域]目前因[具体问题]而困扰，这很重要因为[具体后果]。」
> **第2句话**（洞察）：「我们通过[关键机制]来[方法]，这之所以有效是因为[原因]。」

**The Two-Sentence Template**:
> **Sentence 1** (Problem): "[Domain] currently struggles with [specific problem], which matters because [concrete consequence]."
> **Sentence 2** (Insight): "We [approach] by [key mechanism], which works because [reason]."

**如果你无法填写这个模板**：
- 问题可能尚未明确定义 → 返回框架1
- 洞察可能尚不清楚 → 返回框架7（简化）
- 重要性可能尚未确立 → 返回框架3（寻找张力）

**If You Cannot Fill This Template**:
- The problem may not be well-defined yet → return to Framework 1
- The insight may not be clear yet → return to Framework 7 (simplify)
- The significance may not be established → return to Framework 3 (find the tension)

**校准问题**：
- 你子领域之外的聪明同事能理解为什么这重要吗？
- 解释能否不用术语就站得住脚？
- 你能预测怀疑者的第一个反对是什么吗？

**Calibration Questions**:
- Would a smart colleague outside your subfield understand why this matters?
- Does the explanation stand without jargon?
- Can you predict what a skeptic's first objection would be?

---

## 集成头脑风暴工作流 | Integrated Brainstorming Workflow

使用这个端到端工作流从空白页面到排序的研究想法。

Use this end-to-end workflow to go from blank page to ranked research ideas.

### 阶段1：发散（生成候选）| Phase 1: Diverge (Generate Candidates)

**目标**：不经过滤产生10-20个候选想法。

1. **寻找张力**（框架3）：列出你领域的5个权衡
2. **检查什么变了**（框架5）：列出3个近期变化（计算、数据、法规）
3. **探测边界**（框架6）：选择2个流行方法并找出它们在哪里失效
4. **交叉授粉**（框架4）：从相邻领域选择1个想法
5. **组合/分解**（框架9）：组合2个现有技术或拆分1个
6. **攀登抽象阶梯**（框架2）：对于每个候选，生成上/下/侧变体

### Phase 1: Diverge (Generate Candidates)

**Goal**: Produce 10-20 candidate ideas without filtering.

1. **Scan for tensions** (Framework 3): List 5 trade-offs in your field
2. **Check what changed** (Framework 5): List 3 recent shifts (compute, data, regulation)
3. **Probe boundaries** (Framework 6): Pick 2 popular methods and find where they break
4. **Cross-pollinate** (Framework 4): Pick 1 idea from an adjacent field
5. **Compose/decompose** (Framework 9): Combine 2 existing techniques or split 1 apart
6. **Climb the abstraction ladder** (Framework 2): For each candidate, generate up/down/sideways variants

### 阶段2：收敛（过滤和排序）| Phase 2: Converge (Filter and Rank)

**目标**：缩小到3-5个最强的想法。

对这些候选应用以下过滤器：

| 过滤器 | 问题 | 淘汰标准 |
|--------|----------|----------------|
| **解释它测试**（F10） | 我能用两句话陈述这个吗？ | 如果不能 → 想法尚不清晰 |
| **问题优先检查**（F1） | 问题是否真实且重要？ | 如果没人受苦 → 放弃 |
| **简单性测试**（F7） | 复杂性是否合理？ | 如果更简单的方法有效 → 简化或放弃 |
| **利益相关者检查**（F8） | 谁受益？谁可能反对？ | 如果没有明确受益者 → 放弃 |
| **可行性** | 我能用可用资源执行吗？ | 如果明显不可行 → 先搁置 |

### Phase 2: Converge (Filter and Rank)

**Goal**: Narrow to 3-5 strongest ideas.

Apply these filters to each candidate:

| Filter | Question | Kill Criterion |
|--------|----------|----------------|
| **Explain-It Test** (F10) | Can I state this in two sentences? | If no → idea is not yet clear |
| **Problem-First Check** (F1) | Is the problem genuine and important? | If no one suffers from this → drop it |
| **Simplicity Test** (F7) | Is the complexity justified? | If a simpler approach works → simplify or drop |
| **Stakeholder Check** (F8) | Who benefits? Who might object? | If no clear beneficiary → drop it |
| **Feasibility** | Can I execute this with available resources? | If clearly infeasible → park it for later

### 阶段3：优化（锐化获胜者）| Phase 3: Refine (Sharpen the Winner)

**目标**：将最佳想法转化为具体研究计划。

1. 写两句话宣传（框架10）
2. 识别正在解决的核心张力（框架3）
3. 指定抽象层次（框架2）
4. 列出3个验证想法的具体实验
5. 预判最强反对并准备回应
6. 定义2周试点以提供可行性信号

### Phase 3: Refine (Sharpen the Winner)

**Goal**: Turn the top idea into a concrete research plan.

1. Write the two-sentence pitch (Framework 10)
2. Identify the core tension being resolved (Framework 3)
3. Specify the abstraction level (Framework 2)
4. List 3 concrete experiments that would validate the idea
5. Anticipate the strongest objection and prepare a response
6. Define a 2-week pilot that would provide signal on feasibility

**完成检查清单**：
- [ ] 两句话宣传清晰有力
- [ ] 问题真实（通过问题优先检查）
- [ ] 方法合理（通过简单性测试）
- [ ] 至少有一个利益相关者明确受益
- [ ] 核心实验已指定
- [ ] 可行性试点已定义
- [ ] 最强反对有回应

**Completion Checklist**:
- [ ] Two-sentence pitch is clear and compelling
- [ ] Problem is genuine (problem-first check passed)
- [ ] Approach is justified (simplicity test passed)
- [ ] At least one stakeholder clearly benefits
- [ ] Core experiments are specified
- [ ] Feasibility pilot is defined
- [ ] Strongest objection has a response

---

## 框架选择指南 | Framework Selection Guide

不确定从哪个框架开始？使用此决策指南：

| 你的情况 | 从哪里开始 |
|---------------|------------|
| 「我不知道要做什么领域」 | 张力寻找（F3）→ 什么变了（F5） |
| 「我有一个模糊的领域但没有具体想法」 | 抽象阶梯（F2）→ 失败分析（F6） |
| 「我有一个想法但不确定它是否好」 | 解释它测试（F10）→ 简单性测试（F7） |
| 「我有一个好想法但需要新角度」 | 交叉授粉（F4）→ 利益相关者轮换（F8） |
| 「我想把现有工作组合成新东西」 | 组合/分解（F9） |
| 「我发现了一个很酷的技术想应用它」 | 问题优先检查（F1）→ 利益相关者轮换（F8） |
| 「我想挑战传统智慧」 | 失败分析（F6）→ 简单性测试（F7） |

Not sure which framework to start with? Use this decision guide:

| Your Situation | Start With |
|---------------|------------|
| "I don't know what area to work in" | Tension Hunting (F3) → What Changed (F5) |
| "I have a vague area but no specific idea" | Abstraction Ladder (F2) → Failure Analysis (F6) |
| "I have an idea but I'm not sure it's good" | Explain-It Test (F10) → Simplicity Test (F7) |
| "I have a good idea but need a fresh angle" | Cross-Pollination (F4) → Stakeholder Rotation (F8) |
| "I want to combine existing work into something new" | Composition/Decomposition (F9) |
| "I found a cool technique and want to apply it" | Problem-First Check (F1) → Stakeholder Rotation (F8) |
| "I want to challenge conventional wisdom" | Failure Analysis (F6) → Simplicity Test (F7) |

---

## 研究构思中的常见陷阱 | Common Pitfalls in Research Ideation

| 陷阱 | 症状 | 修复 |
|---------|---------|-----|
| **没有影响力的新颖性** | 「没人做过X」但没人需要X | 应用问题优先检查（F1） |
| **默认渐进主义** | 想法是在基准X上+2% | 攀登抽象阶梯（F2） |
| **复杂性崇拜** | 方法有8个组件，每个都略有帮助 | 应用简单性测试（F7） |
| **回声室** | 所有想法都来自读同样的10篇论文 | 使用交叉授粉（F4） |
| **过时假设** | 「这试过但不行」（5年前） | 应用什么变了（F5） |
| **单一视角偏见** | 只考虑ML工程师的视角 | 使用利益相关者轮换（F8） |
| **过早收敛** | 在探索替代方案之前就承诺第一个想法 | 运行完整发散阶段 |

| Pitfall | Symptom | Fix |
|---------|---------|-----|
| **Novelty without impact** | "No one has done X" but no one needs X | Apply Problem-First Check (F1) |
| **Incremental by default** | Idea is +2% on a benchmark | Climb the Abstraction Ladder (F2) |
| **Complexity worship** | Method has 8 components, each helping marginally | Apply Simplicity Test (F7) |
| **Echo chamber** | All ideas come from reading the same 10 papers | Use Cross-Pollination (F4) |
| **Stale assumptions** | "This was tried and didn't work" (5 years ago) | Apply What Changed (F5) |
| **Single-perspective bias** | Only considering the ML engineer's view | Use Stakeholder Rotation (F8) |
| **Premature convergence** | Committed to first idea without exploring alternatives | Run full Diverge phase |

---

## 代理使用说明 | Usage Instructions for Agents

当研究人员请求帮助头脑风暴研究想法时：

1. **识别他们的起点**：他们是在探索新领域、受困于当前项目，还是评估现有想法？
2. **选择适当的框架**：使用框架选择指南选择2-3个相关视角
3. **交互式引导完成框架**：逐步应用每个框架，要求研究人员提供领域特定输入
4. **生成候选**：目标是跨框架产生10-20个原始想法
5. **过滤和排序**：应用收敛阶段过滤器缩小到前3-5个
6. **优化获胜者**：帮助阐明两句话宣传并定义具体下一步

**关键原则**：
- 推动具体性——模糊的想法（「提高效率」）不可操作
- 挑战假设——至少问三次「为什么？」
- 维护所有候选的书面列表，即使被拒绝的也是（它们可能稍后重新组合）
- 研究人员对追求哪些想法做最终决定；代理促进结构化思维

When a researcher asks for help brainstorming research ideas:

1. **Identify their starting point**: Are they exploring a new area, stuck on a current project, or evaluating an existing idea?
2. **Select appropriate frameworks**: Use the Framework Selection Guide to pick 2-3 relevant lenses
3. **Walk through frameworks interactively**: Apply each framework step-by-step, asking the researcher for domain-specific inputs
4. **Generate candidates**: Aim for 10-20 raw ideas across frameworks
5. **Filter and rank**: Apply the Converge phase filters to narrow to top 3-5
6. **Refine the winner**: Help articulate the two-sentence pitch and define concrete next steps

**Key Principles**:
- Push for specificity—vague ideas ("improve efficiency") are not actionable
- Challenge assumptions—ask "why?" at least three times
- Maintain a written list of all candidates, even rejected ones (they may recombine later)
- The researcher makes the final call on which ideas to pursue; the agent facilitates structured thinking