Mathmodel Pipeline

Full Research Pipeline: Idea → Experiments → Submission

End-to-end autonomous research workflow for: $ARGUMENTS

Constants

• AUTO_PROCEED = true — When true, Gate 1 auto-selects the top-ranked idea (highest pilot signal + novelty confirmed) and continues to implementation. When false, always waits for explicit user confirmation before proceeding.
• ARXIV_DOWNLOAD = false — When true, /problem-analysis downloads the top relevant 数模论文库 PDFs during literature survey. When false (default), only fetches metadata via 数模论文库 API. Passed through to /modeling-discovery → /problem-analysis.
• HUMAN_CHECKPOINT = false — When true, the auto-review loops (Stage 4) pause after each round's review to let you see the score and provide custom modification instructions before fixes are implemented. When false (default), loops run fully autonomously. Passed through to /auto-optimize-loop.

💡 Override via argument, e.g., /mathmodel-pipeline "topic" — AUTO_PROCEED: false, human checkpoint: true.

Overview

This skill chains the entire research lifecycle into a single pipeline:

/modeling-discovery → implement → /run-solver → /auto-optimize-loop → 可提交
├── Workflow 1 ──┤            ├────────── Workflow 2 ──────────────┤

It orchestrates two major workflows plus the implementation bridge between them.

Pipeline

Stage 1: Idea Discovery (Workflow 1)

If PROBLEM_BRIEF.md exists in the project root, it will be automatically loaded as detailed context (replaces one-line prompt). See templates/RESEARCH_BRIEF_TEMPLATE.md.

Invoke the idea discovery pipeline:

/modeling-discovery "$ARGUMENTS"

This internally runs: /problem-analysis → /model-creator → /feasibility-check → /model-review

Output: MODEL_REPORT.md with ranked, validated, pilot-tested ideas.

🚦 Gate 1 — Human Checkpoint:

After MODEL_REPORT.md is generated, pause and present the top ideas to the user:

📋 Idea Discovery complete. Top ideas:

1. [Idea 1 title] — Pilot: POSITIVE (+X%), Novelty: CONFIRMED
2. [Idea 2 title] — Pilot: WEAK POSITIVE (+Y%), Novelty: CONFIRMED
3. [Idea 3 title] — Pilot: NEGATIVE, eliminated

Recommended: Idea 1. Shall I proceed with implementation?

If AUTO_PROCEED=false: Wait for user confirmation before continuing. The user may:

• Approve an idea → proceed to Stage 2.
• Pick a different idea → proceed with their choice.
• Request changes (e.g., "combine Idea 1 and 3", "focus more on X") → update the idea prompt with user feedback, re-run /modeling-discovery with refined constraints, and present again.
• Reject all ideas → collect feedback on what's missing, re-run Stage 1 with adjusted research direction. Repeat until the user commits to an idea.
• Stop here → save current state to MODEL_REPORT.md for future reference.

If AUTO_PROCEED=true: Present the top ideas, wait 10 seconds for user input. If no response, auto-select the #1 ranked idea (highest pilot signal + novelty confirmed) and proceed to Stage 2. Log: "AUTO_PROCEED: selected Idea 1 — [title]".

⚠️ This gate waits for user confirmation when AUTO_PROCEED=false. When true, it auto-selects the top idea after presenting results. The rest of the pipeline (Stages 2-4) is expensive (GPU time + multiple review rounds), so set AUTO_PROCEED=false if you want to manually choose which idea to pursue.

Stage 2: Implementation

Once the user confirms which idea to pursue:

1. Read the idea details from MODEL_REPORT.md (hypothesis, experimental design, pilot code)

2. Implement the full experiment:

   • Extend pilot code to full scale (multi-seed, full dataset, proper baselines)
   • Add proper evaluation metrics and logging (wandb if configured)
   • Write clean, reproducible experiment scripts
   • Follow existing codebase conventions

3. Code review: Before deploying, do a self-review:

   • Are all hyperparameters configurable via argparse?
   • Is the random seed fixed and controllable?
   • Are results saved to JSON/CSV for later analysis?
   • Is there proper logging for debugging?

Stage 3: Deploy Experiments (Workflow 2 — Part 1)

Deploy the full-scale experiments:

/run-solver [experiment command]

What this does:

• Check GPU availability on configured servers
• Sync code to remote server
• Launch experiments in screen sessions with proper CUDA_VISIBLE_DEVICES
• Verify experiments started successfully

Monitor progress:

/monitor-solver [server]

Wait for experiments to complete. Collect results.

Stage 4: Auto Review Loop (Workflow 2 — Part 2)

Once initial results are in, start the autonomous improvement loop:

/auto-optimize-loop "$ARGUMENTS — [chosen idea title]"

What this does (up to 4 rounds):

1. GPT-5.4 xhigh reviews the work (score, weaknesses, minimum fixes)
2. Claude Code implements fixes (code changes, new experiments, reframing)
3. Deploy fixes, collect new results
4. Re-review → repeat until score ≥ 6/10 or 4 rounds reached

Output: AUTO_REVIEW.md with full review history and final assessment.

Stage 5: Final Summary

After the auto-review loop completes, write a final status report:

# Research Pipeline Report

**Direction**: $ARGUMENTS
**Chosen Idea**: [title]
**Date**: [start] → [end]
**Pipeline**: modeling-discovery → implement → run-solver → auto-optimize-loop

## Journey Summary
- Ideas generated: X → filtered to Y → piloted Z → chose 1
- Implementation: [brief description of what was built]
- Experiments: [number of GPU experiments, total compute time]
- Review rounds: N/4, final score: X/10

## Final Status
- [ ] Ready for submission / [ ] Needs manual follow-up

## Remaining TODOs (if any)
- [items flagged by reviewer that weren't addressed]

## Files Changed
- [list of key files created/modified]

Key Rules

• Large file handling: If the Write tool fails due to file size, immediately retry using Bash (cat << 'EOF' > file) to write in chunks. Do NOT ask the user for permission — just do it silently.

• Human checkpoint after Stage 1 is controlled by AUTO_PROCEED. When false, do not proceed without user confirmation. When true, auto-select the top idea after presenting results.

• Stages 2-4 can run autonomously once the user confirms the idea. This is the "sleep and wake up to results" part.

• If Stage 4 ends at round 4 without positive assessment, stop and report remaining issues. Do not loop forever.

• Budget awareness: Track total compute-minutes across the pipeline. Flag if approaching user-defined limits.

• Documentation: Every stage updates its own output file. The full history should be self-contained.

• Fail gracefully: If any stage fails (no good ideas, experiments crash, review loop stuck), report clearly and suggest alternatives rather than forcing forward.

Typical Timeline

Sweet spot: Run Stage 1-2 in the evening, launch Stage 3-4 before bed, wake up to a reviewed paper.