content-refinement-agent
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules, deterministic 0-100 decision bands (Accept/Minor/Major/Reject) that drive a target-met early stop, and a Devil's Advocate concession-threshold guard that blocks acceptance on unresolved critical findings. Maintains a worklog and snapshots each iteration so revert is real, not symbolic. TRIGGER when the orchestrator delegates Step 5 or when the user asks to "refine the draft", "iterate on the paper", or "ru
npx skills add Ar9av/PaperOrchestra --skill content-refinement-agent --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Content Refinement Agent (Step 5) Faithful implementation of the Content Refinement Agent from PaperOrchestra (Song et al., 2026, arXiv:2604.05018, §4 Step 5, App. F.1 pp. 49–51). **Cost: ~5–7 LLM calls** (App. B), typically ~3 refinement iterations, each consisting of one reviewer call and one revision call. The paper highlights this step as one of the largest contributors to overall quality: refinement alone accounts for +19% (CVPR) and +22% (ICLR) absolute acceptance-rate improvement (Fig. 4). Get this step right. ## Inputs - `workspace/drafts/paper.tex` — output of Step 4 - `workspace/inputs/conference_guidelines.md` - `workspace/inputs/experimental_log.md` — used as ground truth for the hallucination check - `workspace/citation_pool.json` / `workspace/refs.bib` — the allowed bibliography ## Outputs - `workspace/refinement/iter1/`, `iter2/`, `iter3/` — per-iteration snapshots containing `paper.tex`, `paper.pdf`, `review.json`, `score.json` - `workspace/refinement/worklog.json` — append-only history of decisions - `workspace/final/paper.tex` and `workspace/final/paper.pdf` — copy of the best accepted snapshot ## The refinement loop ``` prev_score = score(paper.tex) # baseline
- Inputs
- Outputs
- The refinement loop
- Step-by-step
- 0. Pre-refinement integrity gate
- 0b. Snapshot the initial draft
- 1. Simulate peer review
- 2. Score the draft
- 3. Apply revision
- 4. Compile and re-score
- 5. Apply the accept/revert decision
- 6. Halt rules
- 7. Promote the best snapshot
- Critical safety constraints (App. F.1 page 50–51)
python skills/paper-orchestra/scripts/claim_evidence_gate.py \ python skills/content-refinement-agent/scripts/snapshot.py \ cd workspace/refinement/iter0/ && latexmk -pdf -interaction=nonstopmode paper.tex python skills/content-refinement-agent/scripts/update_critique_memory.py \ python skills/content-refinement-agent/scripts/concession_guard.py \ exit 0 = clear; exit 1 = standing CRITICAL → force REVERT this iteration; exit 2 = a concession was rejected (caving/consecutive) → DA must restate; exit 3 = schema error. cd workspace/refinement/iter<N>/ && latexmk -pdf -interaction=nonstopmode paper.tex python skills/content-refinement-agent/scripts/score_delta.py \
What does the content-refinement-agent skill do?
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules, deterministic 0-100 decision bands (Accept/Minor/Major/Reject) that drive a target-met early stop, and a Devil's Advocate concession-threshold guard that blocks acceptance on unresolved critical findings. Maintains a worklog and snapshots each iteration so revert is real, not symbolic. TRIGGER when the orchestrator delegates Step 5 or when the user asks to "refine the draft", "iterate on the paper", or "ru
How do I install it?
Run `npx skills add Ar9av/PaperOrchestra --skill content-refinement-agent --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From Ar9av/PaperOrchestra, a repository with 627 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.