Outline Agent

Outline Agent (Step 1)

Faithful implementation of the Outline Agent from PaperOrchestra (Song et al., 2026, arXiv:2604.05018, App. F.1, pp. 40–44).

Cost: 1 LLM call.

Your task

Read four input files from the workspace and produce a single JSON object at workspace/outline.json with three top-level keys:

• plotting_plan — array of figure objects
• intro_related_work_plan — object with introduction_strategy and related_work_strategy
• section_plan — array of section objects, each with section_title and subsections[]

How to do it

1. Read the verbatim prompt at `references/prompt.md`. This is the exact Outline Agent system prompt from the paper. Use it as your system message. 2. Prepend the Anti-Leakage Prompt from ../paper-orchestra/references/anti-leakage-prompt.md. 3. Read the four input files:

• workspace/inputs/idea.md
• workspace/inputs/experimental_log.md
• workspace/inputs/template.tex
• workspace/inputs/conference_guidelines.md

4. Synthesize across all four — the global instruction in the prompt is "Do not analyze inputs in isolation. You must synthesize information across all provided documents for every step." 5. Emit a single JSON object following the schema in references/outline-schema.md. Cross-check against references/outline_schema.json (machine-readable). 6. Save to workspace/outline.json. 7. Validate:

   python skills/outline-agent/scripts/validate_outline.py workspace/outline.json

If validation fails, fix the JSON and re-validate. Do not proceed to Step 2 or Step 3 with an invalid outline — every downstream agent depends on this schema.

8. Append §1 to research_brief.md (see skills/shared/research_brief_template.md):

After outline.json passes validation, append the §1 section to workspace/research_brief.md (create the file if absent). Template:

   ## §1 · Core Claim and Narrative
   _Written by: outline-agent, Step 1_

   **Core claim:** <one-sentence contribution>
   **Narrative tension:** <gap this paper resolves>
   **Key novelty framing:** <how the contribution is framed relative to prior work>
   **Outline decisions:**
   - Plotting plan: <N> figures
   - Related Work clusters: <names>
   - Section structure: <section titles>
   **Potential weaknesses flagged at outline stage:**
   - <any claim in idea.md that may be hard to support>

This is a free-form prose append; no machine-readable schema required.

Hard rules from the prompt (do not violate)

These are excerpted from references/prompt.md. The validator enforces them.

Plotting plan (Directive 1)

• plot_type MUST be exactly one of "plot" or "diagram".
• data_source MUST be exactly one of "idea.md", "experimental_log.md",

or "both".

• aspect_ratio MUST be exactly one of:

"1:1", "1:4", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9".

• figure_id MUST be a semantically meaningful snake_case identifier

(e.g., fig_framework_overview, fig_ablation_study_parameter_sensitivity).

• figure_id MUST NOT contain the word "Figure".

Intro / Related Work strategy (Directive 2)

• Strictly separate Introduction (macro-level context, 10-20 papers,

foundational + survey + impact) from Related Work (micro-level technical baselines, 30-50 papers, divided into 2-4 methodology clusters that directly compete with or precede the proposed approach).

• For each Related Work cluster: provide methodology_cluster,

sota_investigation_mission, limitation_hypothesis, limitation_search_queries, bridge_to_our_method.

• CRITICAL TIMELINE RULE: Do not instruct searches for any papers

published after {cutoff_date}. Derive cutoff_date from conference_guidelines.md (e.g., "ICLR 2025 → cutoff October 2024", "CVPR 2025 → cutoff November 2024"). If unspecified, default to one month before today's date.

Section plan (Directive 3)

• Structural hierarchy: if Subsection X.1 is created, X.2 is mandatory.

No orphaned subsections. Omit subsections entirely if a section does not require division.

• Content specificity: each content_bullets entry must reference source

materials concretely. AVOID "Describe the model". REQUIRE "Formalize the Temporal-Aware Attention mechanism using Eq. 3 from idea.md."

• Mandatory citations: every dataset, optimizer, metric, and

foundational architecture/model mentioned in idea.md or experimental_log.md MUST have a citation hint, no matter how ubiquitous (e.g., AdamW, ResNet, ImageNet, CLIP, Transformer, LLaMA, GPT, LLaVA).

• Citation hint format:
• If you know the exact author and title:

"Author (Exact Paper Title)"

• Otherwise: "research paper or technical report introducing '[Exact Model/Dataset/Metric Name]'"
• Do NOT guess or hallucinate authors.

Output

Exactly one file: workspace/outline.json. No prose, no code blocks, no markdown. The Section Writing Agent and Literature Review Agent will parse this JSON directly.

See references/example-output.json for a complete worked example from the paper (App. F.1, pp. 43–44).

Resources

• references/prompt.md — verbatim Outline Agent prompt from App. F.1
• references/outline-schema.md — prose explanation of the schema
• references/outline_schema.json — machine-readable JSON Schema
• references/example-output.json — example output from the paper
• references/allowed-values.md — enumerated allowed values for each enum field
• scripts/validate_outline.py — JSON Schema validator
• skills/shared/research_brief_template.md — NEW §1 schema; append after outline.json passes validation

Allowed enumerated values

Source: arXiv:2604.05018, App. F.1 Outline Agent prompt.

These are the only values the validator will accept for each enum field. Anything else will fail validate_outline.py.

plot_type

data_source

aspect_ratio

Exactly one of these 12 strings:

1:1   1:4   2:3   3:2   3:4   4:1   4:3   4:5   5:4   9:16   16:9   21:9

Common conventions:

The Plotting Agent's render_matplotlib.py translates the ratio into pixel dimensions at 300 DPI.

figure_id rules

• Snake_case: ^[a-z0-9_]+$
• Convention: prefix with fig_ (e.g., fig_main_results,

fig_ablation_temperature_sensitivity).

• MUST be semantically meaningful (no fig_1, fig_a, chart).
• MUST NOT contain the word figure as a substring after the fig_ prefix.

Citation hint format

Two acceptable forms (per the prompt):

Never guess authors. The Literature Review Agent will use these hints as search queries — wrong authors lead to wrong citations.

Outline JSON Schema (prose)

The Outline Agent emits a single JSON object with three top-level keys: plotting_plan, intro_related_work_plan, section_plan. Source: arXiv:2604.05018, App. F.1, pp. 43–44.

The machine-readable JSON Schema is in outline_schema.json and is enforced by scripts/validate_outline.py. This document is the human-readable view.

Top-level structure

{
  "plotting_plan": [ <FigureSpec>, ... ],
  "intro_related_work_plan": <IntroRelWorkPlan>,
  "section_plan": [ <SectionSpec>, ... ]
}

FigureSpec

{
  "figure_id":     "fig_framework_overview",            // snake_case, no "Figure"
  "title":         "Framework Overview",
  "plot_type":     "diagram",                           // "plot" or "diagram"
  "data_source":   "idea.md",                           // "idea.md" | "experimental_log.md" | "both"
  "objective":     "Visual summary (Block Diagram) of the proposed pipeline.",
  "aspect_ratio":  "16:9"                               // see allowed-values.md
}

If plot_type is "plot", the objective MUST name the specific chart type (e.g., "Visual summary (Radar Chart) demonstrating that our method achieves SOTA balance across 5 metrics.").

IntroRelWorkPlan

{
  "introduction_strategy": {
    "hook_hypothesis":        "Video-LLMs are currently the dominant paradigm for short clips.",
    "problem_gap_hypothesis": "Context window limits prevent scaling to >5s videos efficiently.",
    "search_directions": [
      "Find highly cited papers establishing the real-world impact of context limits in video generation",
      "Search for published 'long-context video generation' surveys",
      "Identify foundational papers establishing causal video generation"
    ]
  },
  "related_work_strategy": {
    "overview": "Investigate three specific paradigms to build a graph proving the necessity of our Sliding-Window approach.",
    "subsections": [
      {
        "subsection_title":          "2.1 Autoregressive Video Generation",
        "methodology_cluster":       "Discrete Tokenization & Transformers",
        "sota_investigation_mission": "Identify the current SOTA autoregressive models from 2024-2025. Determine their maximum stable generation length.",
        "limitation_hypothesis":     "These models suffer from 'drift' or 'error propagation' because they lack bidirectional context.",
        "limitation_search_queries": [
          "Autoregressive video generation error propagation metrics",
          "Causal masking limitations in temporal video transformers"
        ],
        "bridge_to_our_method": "Our method introduces bidirectional blocks to fix the hypothesized drift issue."
      }
    ]
  }
}

SectionSpec

{
  "section_title": "3. Methodology",
  "subsections": [
    {
      "subsection_title": "3.1 Temporal-Aware Attention Mechanism",
      "content_bullets": [
        "Define the query-key matching logic",
        "Explain the masking strategy"
      ],
      "citation_hints": [
        "Vaswani et al. (Attention Is All You Need)",
        "research paper or technical report introducing 'FlashAttention-2'"
      ]
    },
    {
      "subsection_title": "3.2 Optimization Objective",
      "content_bullets": [
        "Detail the loss function",
        "Discuss regularization terms"
      ],
      "citation_hints": []
    }
  ]
}

Validation rules (enforced by validate_outline.py)

1. The top-level object MUST contain exactly the keys plotting_plan, intro_related_work_plan, section_plan (extras allowed but reported). 2. plotting_plan is a non-empty array. 3. Each FigureSpec has all six fields with correct enum values. 4. figure_id matches ^[a-z0-9_]+$ and does not contain figure as a substring after fig_. 5. intro_related_work_plan.introduction_strategy and .related_work_strategy both present. 6. related_work_strategy.subsections has 2–4 entries (the paper's "2-4 distinct methodology clusters" rule). 7. section_plan is a non-empty array. Each SectionSpec has section_title and subsections. 8. Hierarchy rule: if a section has any subsection, it must have ≥2 (no orphans). The validator emits a WARNING for sections with exactly 1 subsection. 9. citation_hints is always an array (may be empty).

Outline Agent — verbatim prompt

Source: arXiv:2604.05018, Appendix F.1, pages 40–44 (verbatim).

This is the exact system prompt used by the Outline Agent in the paper. Reproduce it as your system message. Substitute {cutoff_date} with the research cutoff derived from conference_guidelines.md.

---

You are a senior AI researcher drafting a paper for a top-tier conference
(e.g., NeurIPS, ICML, CVPR, ICLR). Your task is to convert the provided
methodology and experimental logs into a detailed, venue-compliant paper
outline. You must output a single JSON object.

Your inputs are:
  1. idea.md: A detailed summary of the methodology, core contributions, and
     theoretical framework.
  2. experimental_log.md: A summary of experimental results, including raw
     data points, ablation studies, and performance metrics.
  3. template.tex: The template structure. You must use the section commands
     (e.g., \section{...}) found here as your primary skeleton.
  4. conference_guidelines.md: Formatting rules, specific page limits (for
     word count calculation), and mandatory sections.

Processing Directives

Global Instruction: Do not analyze inputs in isolation. You must synthesize
information across all provided documents for every step.

Directive 1: Plotting & Visualization Plan

Synthesize experimental_log.md and idea.md to identify the most compelling
evidence.

  - Determine which figures are essential to visually prove the hypothesis
    (e.g., convergence rates, qualitative visual comparisons).
  - The plot_type MUST be exactly "plot" or "diagram". If it is a plot,
    specify the specific chart type (e.g., Radar Chart) inside the objective.
  - The data_source MUST be exactly "idea.md", "experimental_log.md", or
    "both".
  - Determine the ideal aspect_ratio for each figure. The aspect_ratio MUST
    be exactly one of: "1:1", "1:4", "2:3", "3:2", "3:4", "4:1", "4:3",
    "4:5", "5:4", "9:16", "16:9", "21:9".
  - The figure_id MUST be a semantically meaningful string identifier
    summarizing the plot contents, like "fig_framework_overview" or
    "fig_ablation_study_parameter_sensitivity". It MUST NOT contain the word
    "Figure".
  - Output Focus: Create an array of objects for the plotting_plan key.

Directive 2: Research Graph & Investigation Strategy (Intro & Related Work)

Provide search instructions for a downstream literature review agent to build
a Research Graph. Do not write the actual paper content.

Prevent Citation Overlap: Strictly separate the scope of the Introduction
from Related Work to ensure the agent searches for different tiers of
literature.

  - Introduction: Focuses on macro-level context (foundational papers,
    surveys).
  - Related Work: Focuses on micro-level technical comparisons (recent SOTA
    baselines, benchmarks).

Introduction Strategy (Macro-Level Context, 10-20 papers):

  - Hypotheses: Define the "Hook" (broad context) and "Problem Gap" to be
    verified. CRITICAL: Strictly scope the problem gap and claims to match
    the specific datasets and evaluations present in experimental_log.md.
    Do not over-claim generalization.
  - Search Directions: Provide 3-5 specific queries to find:
    1. Papers establishing the real-world impact or urgency of the problem
       gap.
    2. Good survey or review papers on the topic.
    3. 3-5 Foundational papers that established the sub-field.

Related Work Strategy (Micro-Level Technical Baselines, 30-50 papers):

  - Divide the field into 2-4 distinct methodology clusters that directly
    compete with or precede our approach.
  - For each cluster, define:
    1. Methodology Cluster Name: The technical category.
    2. SOTA Investigation: Instructions to find recent papers for conceptual
       context. CRITICAL TIMELINE RULE: Do not instruct searches for any
       papers published after {cutoff_date}. Furthermore, do NOT instruct
       the search for new "competitors" to beat if they are not exclusively
       in experimental_log.md.
    3. Limitation Hypothesis: The suspected failure point of these
       competing methods, based on idea.md.
    4. Limitation Search Queries: Highly specific, narrow queries to find
       papers documenting these exact limitations.
    5. The Bridge: How our proposed method resolves this specific limitation.

Output Focus: Populate the intro_related_work_plan key.

Directive 3: Section Writing Plan & Sizing Constraints

Outline the remaining sections (Abstract, Methodology, Experiments,
Conclusion, Appendix) into a detailed structural plan.

  - Structural Hierarchy: If Subsection X.1 is created, X.2 is mandatory.
    Do not create orphaned subsections. Omit subsections entirely if a
    section does not require division.
  - Content Specificity: Explicitly reference source materials.
    - Avoid: "Describe the model."
    - Require: "Formalize the Temporal-Aware Attention mechanism using
      Eq. 3 from idea.md."
  - Mandatory Citations (citation_hints): You must provide targeted citation
    hints for all external dependencies. Every hint must point to a single,
    unambiguous canonical paper.
    - Required Coverage (EXHAUSTIVE): You MUST explicitly create a targeted
      citation_hints query for EVERY SINGLE dataset, optimizer, metric, and
      foundational architecture/model you mention, no matter how ubiquitous
      or obvious it seems (e.g., AdamW, ResNet, ImageNet, CLIP, Transformer,
      LLaMA, GPT, LLaVA). If it is in the experimental_log.md or idea.md,
      it MUST have a citation hint.
      1. All baseline methods compared against.
      2. All datasets evaluated on.
      3. All standard metrics utilized.
      4. All foundational algorithms (e.g., ResNet, Transformer, Diffusion
         models), foundational models (e.g., LLMs, VLMs), optimizers
         (e.g., AdamW), or frameworks built upon.
    - Format Constraint & Anti-Hallucination Rule: If you know the exact
      author and title, use "Author (Exact Paper Title)". DO NOT guess or
      hallucinate authors. If you do not know the exact author, use this
      format: "research paper or technical report introducing '[Exact
      Model/Dataset/Metric Name]'".
  - Output Focus: Populate the section_plan key.

Guidelines on Scientific Depth & Mathematical Rigor:

  - Grounded Formalization: Propose explicit subsections for rigorous
    mathematical formulations (e.g., loss functions, core algorithms,
    theoretical proofs). You must base these strictly on idea.md and
    experimental_log.md; do not instruct the writing agent to include
    hallucinated variables or unsupported math.

Strict Output Format (JSON)

You must output a single, valid JSON object with the following three
top-level keys: "plotting_plan", "intro_related_work_plan", and
"section_plan".

The full example output JSON from the paper (App. F.1, pp. 43–44) is at example-output.json.