Auto Review Loop

Auto Review Loop: Autonomous Research Improvement

Autonomously iterate: review → implement fixes → re-review, until the external reviewer gives a positive assessment or MAX_ROUNDS is reached.

Context: $ARGUMENTS

Constants

• MAX_ROUNDS = 4
• POSITIVE_THRESHOLD: score >= 6/10, or verdict contains "accept", "sufficient", "ready for submission"
• REVIEW_DOC: AUTO_REVIEW.md in project root (cumulative log)
• REVIEWER_MODEL = gpt-5.4 — Model used via Codex MCP. Must be an OpenAI model (e.g., gpt-5.4, o3, gpt-4o)
• HUMAN_CHECKPOINT = false — When true, pause after each round's review (Phase B) and present the score + weaknesses to the user. Wait for user input before proceeding to Phase C. The user can: approve the suggested fixes, provide custom modification instructions, skip specific fixes, or stop the loop early. When false (default), the loop runs fully autonomously.

💡 Override: /auto-review-loop "topic" — human checkpoint: true

State Persistence (Compact Recovery)

Long-running loops may hit the context window limit, triggering automatic compaction. To survive this, persist state to REVIEW_STATE.json after each round:

{
  "round": 2,
  "threadId": "019cd392-...",
  "status": "in_progress",
  "last_score": 5.0,
  "last_verdict": "not ready",
  "pending_experiments": ["screen_name_1"],
  "timestamp": "2026-03-13T21:00:00"
}

Write this file at the end of every Phase E (after documenting the round). Overwrite each time — only the latest state matters.

On completion (positive assessment or max rounds), set "status": "completed" so future invocations don't accidentally resume a finished loop.

Workflow

Initialization

1. Check for REVIEW_STATE.json in project root:
   • If it does not exist: fresh start (normal case, identical to behavior before this feature existed)
   • If it exists AND status is "completed": fresh start (previous loop finished normally)
   • If it exists AND status is "in_progress" AND timestamp is older than 24 hours: fresh start (stale state from a killed/abandoned run — delete the file and start over)
   • If it exists AND status is "in_progress" AND timestamp is within 24 hours: resume
     • Read the state file to recover round, threadId, last_score, pending_experiments
     • Read AUTO_REVIEW.md to restore full context of prior rounds
     • If pending_experiments is non-empty, check if they have completed (e.g., check screen sessions)
     • Resume from the next round (round = saved round + 1)
     • Log: "Recovered from context compaction. Resuming at Round N."
2. Read project narrative documents, memory files, and any prior review documents
3. Read recent experiment results (check output directories, logs)
4. Identify current weaknesses and open TODOs from prior reviews
5. Initialize round counter = 1 (unless recovered from state file)
6. Create/update AUTO_REVIEW.md with header and timestamp

Loop (repeat up to MAX_ROUNDS)

Phase A: Review

Send comprehensive context to the external reviewer:

mcp__codex__codex:
  config: {"model_reasoning_effort": "xhigh"}
  prompt: |
    [Round N/MAX_ROUNDS of autonomous review loop]

    [Full research context: claims, methods, results, known weaknesses]
    [Changes since last round, if any]

    Please act as a senior ML reviewer (NeurIPS/ICML level).

    REALITY CHECK (answer these first):
    A. Are the reported results from actual model inference or from an oracle/mock?
    B. Does the paper include actual simulation/real-world frames showing the system running?
    C. Is there a trained model checkpoint, or only scaffold code?
    If ANY answer is "oracle/mock/no", flag this as a CRITICAL issue that must be fixed before scoring.

    Then:
    1. Score this work 1-10 for a top venue
    2. List remaining critical weaknesses (ranked by severity)
    3. For each weakness, specify the MINIMUM fix (experiment, analysis, or reframing)
    4. State clearly: is this READY for submission? Yes/No/Almost

    Be brutally honest. If results are from oracle mode, the maximum possible score is 3/10.
    A paper with no real execution data is NOT submittable regardless of framework quality.

    SCORING CONSTRAINTS:
    - If results are from oracle/mock execution: MAX score = 3/10, regardless of framework quality.
    - If no actual simulation frames exist: MAX score = 2/10.
    - If no trained model was used: MAX score = 1/10.
    - Only real model inference on real simulation with actual rendered frames qualifies for scores above 5/10.

If this is round 2+, use mcp__codex__codex-reply with the saved threadId to maintain conversation context.

Phase B: Parse Assessment

CRITICAL: Save the FULL raw response from the external reviewer verbatim (store in a variable for Phase E). Do NOT discard or summarize — the raw text is the primary record.

Then extract structured fields:

• Score (numeric 1-10)
• Verdict ("ready" / "almost" / "not ready")
• Action items (ranked list of fixes)

STOP CONDITION: If score >= 6 AND verdict contains "ready" or "almost" → stop loop, document final state.

Human Checkpoint (if enabled)

Skip this step entirely if HUMAN_CHECKPOINT = false.

When HUMAN_CHECKPOINT = true, present the review results and wait for user input:

📋 Round N/MAX_ROUNDS review complete.

Score: X/10 — [verdict]
Top weaknesses:
1. [weakness 1]
2. [weakness 2]
3. [weakness 3]

Suggested fixes:
1. [fix 1]
2. [fix 2]
3. [fix 3]

Options:
- Reply "go" or "continue" → implement all suggested fixes
- Reply with custom instructions → implement your modifications instead
- Reply "skip 2" → skip fix #2, implement the rest
- Reply "stop" → end the loop, document current state

Wait for the user's response. Parse their input:

• Approval ("go", "continue", "ok", "proceed"): proceed to Phase C with all suggested fixes
• Custom instructions (any other text): treat as additional/replacement guidance for Phase C. Merge with reviewer suggestions where appropriate
• Skip specific fixes ("skip 1,3"): remove those fixes from the action list
• Stop ("stop", "enough", "done"): terminate the loop, jump to Termination

Feishu Notification (if configured)

After parsing the score, check if ~/.claude/feishu.json exists and mode is not "off":

• Send a review_scored notification: "Round N: X/10 — [verdict]" with top 3 weaknesses
• If interactive mode and verdict is "almost": send as checkpoint, wait for user reply on whether to continue or stop
• If config absent or mode off: skip entirely (no-op)

Phase C: Implement Fixes (if not stopping)

For each action item (highest priority first):

1. Code changes: Write/modify experiment scripts, model code, analysis scripts
2. Run experiments: Deploy to GPU server via SSH + screen/tmux
3. Analysis: Run evaluation, collect results, update figures/tables
4. Documentation: Update project notes and review document

Prioritization rules:

• Skip fixes requiring excessive compute (flag for manual follow-up)
• Skip fixes requiring external data/models not available
• Prefer reframing/analysis over new experiments when both address the concern
• Always implement metric additions (cheap, high impact)

Phase D: Wait for Results

If experiments were launched:

• Monitor remote sessions for completion
• Collect results from output files and logs

Phase E: Document Round

Append to AUTO_REVIEW.md:

## Round N (timestamp)

### Assessment (Summary)
- Score: X/10
- Verdict: [ready/almost/not ready]
- Key criticisms: [bullet list]

### Reviewer Raw Response

<details>
<summary>Click to expand full reviewer response</summary>

[Paste the COMPLETE raw response from the external reviewer here — verbatim, unedited.
This is the authoritative record. Do NOT truncate or paraphrase.]

</details>

### Actions Taken
- [what was implemented/changed]

### Results
- [experiment outcomes, if any]

### Status
- [continuing to round N+1 / stopping]

Write REVIEW_STATE.json with current round, threadId, score, verdict, and any pending experiments.

Increment round counter → back to Phase A.

Termination

When loop ends (positive assessment or max rounds):

1. Update REVIEW_STATE.json with "status": "completed"
2. Write final summary to AUTO_REVIEW.md
3. Update project notes with conclusions
4. If stopped at max rounds without positive assessment:
   • List remaining blockers
   • Estimate effort needed for each
   • Suggest whether to continue manually or pivot
5. Feishu notification (if configured): Send pipeline_done with final score progression table

Key Rules

• ALWAYS use config: {"model_reasoning_effort": "xhigh"} for maximum reasoning depth
• Save threadId from first call, use mcp__codex__codex-reply for subsequent rounds
• Be honest — include negative results and failed experiments
• Do NOT hide weaknesses to game a positive score
• Implement fixes BEFORE re-reviewing (don't just promise to fix)
• If an experiment takes > 30 minutes, launch it and continue with other fixes while waiting
• Document EVERYTHING — the review log should be self-contained
• Update project notes after each round, not just at the end

Prompt Template for Round 2+

mcp__codex__codex-reply:
  threadId: [saved from round 1]
  config: {"model_reasoning_effort": "xhigh"}
  prompt: |
    [Round N update]

    Since your last review, we have:
    1. [Action 1]: [result]
    2. [Action 2]: [result]
    3. [Action 3]: [result]

    Updated results table:
    [paste metrics]

    Please re-score and re-assess. Are the remaining concerns addressed?
    Same format: Score, Verdict, Remaining Weaknesses, Minimum Fixes.