Autonomously improve a generated paper via GPT-5.4 xhigh review \u2192 implement fixes \u2192 recompile, for 2 rounds. Use when user says \\\"\u6539\u8bba\u6587\\\", \\\"improve paper\\\", \\\"\u8bba\u6587\u6da6\u8272\u5faa\u73af\\\", \\\"auto improve\\\", or wants to iteratively polish a generated paper.
SKILL.md
Auto Paper Improvement Loop: Review → Fix → Recompile
Autonomously improve the paper at: $ARGUMENTS
Context
This skill is designed to run after Workflow 3 (/paper-plan → /paper-figure → /paper-write → /paper-compile). It takes a compiled paper and iteratively improves it through external LLM review.
Unlike /auto-review-loop (which iterates on research — running experiments, collecting data, rewriting narrative), this skill iterates on paper writing quality — fixing theoretical inconsistencies, softening overclaims, adding missing content, and improving presentation.
Constants
MAX_ROUNDS = 2 — Two rounds of review→fix→recompile. Empirically, Round 1 catches structural issues (4→6/10), Round 2 catches remaining presentation issues (6→7/10). Diminishing returns beyond 2 rounds for writing-only improvements.
REVIEWER_MODEL = gpt-5.4 — Model used via a secondary Codex agent for paper review.
REVIEW_LOG = PAPER_IMPROVEMENT_LOG.md — Cumulative log of all rounds, stored in paper directory.
HUMAN_CHECKPOINT = false — When true, pause after each round's review and present score + weaknesses to the user. The user can approve fixes, provide custom modification instructions, skip specific fixes, or stop early. When false (default), runs fully autonomously.
💡 Override: /auto-paper-improvement-loop "paper/" — human checkpoint: true
Inputs
Compiled paper — paper/main.pdf + LaTeX source files
Installs
0
All section .tex files — concatenated for review prompt
State Persistence (Compact Recovery)
If the context window fills up mid-loop, Codex auto-compacts. To recover, this skill writes PAPER_IMPROVEMENT_STATE.json after each round:
On startup: if PAPER_IMPROVEMENT_STATE.json exists with "status": "in_progress" AND timestamp is within 24 hours, read it + PAPER_IMPROVEMENT_LOG.md to recover context, then resume from the next round. Otherwise (file absent, "status": "completed", or older than 24 hours), start fresh.
After each round: overwrite the state file. On completion: set "status": "completed".
Workflow
Step 0: Preserve Original
cp paper/main.pdf paper/main_round0_original.pdf
Step 1: Collect Paper Text
Concatenate all section files into a single text block for the review prompt:
# Collect all sections in order
for f in paper/sections/*.tex; do
echo "% === $(basename $f) ==="
cat "$f"
done > /tmp/paper_full_text.txt
Step 2: Round 1 Review
Send the full paper text to GPT-5.4 xhigh:
spawn_agent:
model: gpt-5.4
reasoning_effort: xhigh
message: |
You are reviewing a [VENUE] paper. Please provide a detailed, structured review.
## Full Paper Text:
[paste concatenated sections]
## Review Instructions
Please act as a senior ML reviewer ([VENUE] level). Provide:
1. **Overall Score** (1-10, where 6 = weak accept, 7 = accept)
2. **Summary** (2-3 sentences)
3. **Strengths** (bullet list, ranked)
4. **Weaknesses** (bullet list, ranked: CRITICAL > MAJOR > MINOR)
5. **For each CRITICAL/MAJOR weakness**: A specific, actionable fix
6. **Missing References** (if any)
7. **Verdict**: Ready for submission? Yes / Almost / No
Focus on: theoretical rigor, claims vs evidence alignment, writing clarity,
self-containedness, notation consistency.
Save the agent id for Round 2.
Step 2b: Human Checkpoint (if enabled)
Skip if HUMAN_CHECKPOINT = false.
Present the review results and wait for user input:
📋 Round 1 review complete.
Score: X/10 — [verdict]
Key weaknesses (by severity):
1. [CRITICAL] ...
2. [MAJOR] ...
3. [MINOR] ...
Reply "go" to implement all fixes, give custom instructions, "skip 2" to skip specific fixes, or "stop" to end.
Parse user response same as /auto-review-loop: approve / custom instructions / skip / stop.
Number of CRITICAL/MAJOR/MINOR issues fixed per round
Final page count
Remaining issues (if any)
Feishu Notification (if configured)
After each round's review AND at final completion, check ~/.codex/feishu.json:
After each round: Send review_scored — "Round N: X/10 — [key changes]"
After final round: Send pipeline_done — score progression table + final page count
If config absent or mode "off": skip entirely (no-op)
Output
paper/
├── main_round0_original.pdf # Original
├── main_round1.pdf # After Round 1
├── main_round2.pdf # After Round 2 (final)
├── main.pdf # = main_round2.pdf
└── PAPER_IMPROVEMENT_LOG.md # Full review log with scores
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.
Preserve all PDF versions — user needs to compare progression
Save FULL raw review text — do not summarize or truncate GPT-5.4 responses
Use send_input for Round 2 to maintain conversation context
Always recompile after fixes — verify 0 errors before proceeding
Do not fabricate experimental results — synthetic validation must describe methodology, not invent numbers
Respect the paper's claims — soften overclaims rather than adding unsupported new claims
Global consistency — when renaming notation or softening claims, check ALL files (abstract, intro, method, experiments, theory sections, conclusion, tables, figure captions)
Typical Score Progression
Based on end-to-end testing on a 9-page ICLR 2026 theory paper:
+4.5 points across 3 rounds (2 content + 1 format) is typical for a well-structured but rough first draft. Final: 8 pages main body, 0 overfull hbox, ICLR-compliant.
