Research Review via a secondary Codex agent (xhigh reasoning)

Get a multi-round critical review of research work from an external LLM with maximum reasoning depth.

Constants

• REVIEWER_MODEL = gpt-5.4 — Model used via a secondary Codex agent. Must be an OpenAI model (e.g., gpt-5.4, o3, gpt-4o)
• REVIEWER_BACKEND = `codex` — Default: Codex xhigh reviewer. Use --reviewer: oracle-pro only when explicitly requested; if Oracle is unavailable, warn and fall back to Codex xhigh.

Context: $ARGUMENTS

Prerequisites

• Use spawn_agent and send_input when the user has explicitly allowed delegation or subagents.
• If delegation is not allowed, run the same review loop locally and preserve the same deliverable structure.

Workflow

Step 1: Gather Research Context

Before calling the external reviewer, compile a comprehensive briefing:

1. Read project narrative documents (e.g., STORY.md, README.md, paper drafts)
2. Read any memory/notes files for key findings and experiment history
3. Identify: core claims, methodology, key results, known weaknesses

Step 2: Initial Review (Round 1)

Send a detailed prompt with xhigh reasoning:

spawn_agent:
  reasoning_effort: xhigh
  message: |
    [Full research context + specific questions]
    Please act as a senior ML reviewer (NeurIPS/ICML level). Identify:
    1. Logical gaps or unjustified claims
    2. Missing experiments that would strengthen the story
    3. Narrative weaknesses
    4. Whether the contribution is sufficient for a top venue
    Please be brutally honest.

Step 3: Iterative Dialogue (Rounds 2-N)

Use send_input with the returned agent id to continue the conversation:

send_input:
  target: [saved reviewer id from Step 2]
  message: |
    Please continue the review using the revised materials below.

    Revised files:
    - /absolute/path/to/file1
    - /absolute/path/to/file2

    Focus on unresolved weaknesses and whether the revision actually fixed them.

For each round:

1. Respond to criticisms with evidence/counterarguments
2. Ask targeted follow-ups on the most actionable points
3. Request specific deliverables: experiment designs, paper outlines, claims matrices

Key follow-up patterns:

• "If we reframe X as Y, does that change your assessment?"
• "What's the minimum experiment to satisfy concern Z?"
• "Please design the minimal additional experiment package (highest acceptance lift per GPU week)"
• "Please write a mock NeurIPS/ICML review with scores"
• "Give me a results-to-claims matrix for possible experimental outcomes"

Step 4: Convergence

Stop iterating when:

• Both sides agree on the core claims and their evidence requirements
• A concrete experiment plan is established
• The narrative structure is settled

Step 5: Document Everything

Save the full interaction and conclusions to a review document in the project root:

• Round-by-round summary of criticisms and responses
• Final consensus on claims, narrative, and experiments
• Claims matrix (what claims are allowed under each possible outcome)
• Prioritized TODO list with estimated compute costs
• Paper outline if discussed

Update project memory/notes with key review conclusions.

Step 6: Review Tracing

Save a trace for every spawn_agent, send_input, or oracle-pro review call following ../shared-references/review-tracing.md. Record the reviewer route, saved agent id, prompt summary, raw response path, decisions, and action items. This preserves the Claude mainline Review Tracing semantics while using Codex-native reviewer calls.

Key Rules

• ALWAYS use reasoning_effort: xhigh for reviews
• Send comprehensive context in Round 1 — the external model cannot read your files
• Be honest about weaknesses — hiding them leads to worse feedback
• Push back on criticisms you disagree with, but accept valid ones
• Focus on ACTIONABLE feedback — "what experiment would fix this?"
• Document the agent id for potential future resumption
• The review document should be self-contained (readable without the conversation)

Prompt Templates

For initial review:

"I'm going to present a complete ML research project for your critical review. Please act as a senior ML reviewer (NeurIPS/ICML level)..."

For experiment design:

"Please design the minimal additional experiment package that gives the highest acceptance lift per GPU week. Our compute: [describe]. Be very specific about configurations."

For paper structure:

"Please turn this into a concrete paper outline with section-by-section claims and figure plan."

For claims matrix:

"Please give me a results-to-claims matrix: what claim is allowed under each possible outcome of experiments X and Y?"

For mock review:

"Please write a mock NeurIPS review with: Summary, Strengths, Weaknesses, Questions for Authors, Score, Confidence, and What Would Move Toward Accept."