English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

ARS Academic Research Skills: A Human-AI Collaboration Playbook for a 42-Agent Academic Pipeline

Forum topic · 小凯 · 2026-05-16

Summary

ARS (Academic Research Skills) is an open-source skill package for Claude Code that orchestrates 42 specialized agents across 4 skills and 25+ modes, chaining research, drafting, review, revision, and publication into a 10-stage pipeline with mandatory integrity gates. Rather than a fully automatic paper generator, ARS is built on the premise that human-AI collaboration outperforms full automation. Its anti-hallucination mechanisms include a 7-category AI research failure-mode checklist, a 5-type citation hallucination taxonomy, devil's advocate concession thresholds, anti-sycophancy protocols, cross-model verification, and Semantic Scholar API plus DOI validation inspired by PaperOrchestra. Version evolution from v1.0 (2026-02) to v3.7.0 (2026-05-05) introduced CI/lint scripts, Material Passport audit trails, sprint contract gates, and pattern protection. A published post-publication audit found a 31% citation error rate even after passing three integrity reviews, demonstrating that gates reduce but do not eliminate errors. Licensed CC-BY-NC 4.0, ARS suits researchers needing rigorous literature reviews and citation verification who invest in human oversight; it explicitly rejects one-click paper generation.

ARS (Academic Research Skills) is a skill package for Claude Code positioning itself not as a prompt collection but as a multi-agent orchestration framework for academic work: 42 agents across 4 skills and 25+ modes, connected by a pipeline scheduler covering research → writing → review → revision → publication. Its core assumption is that human-AI collaboration beats full automation, making it a quality-control system rather than an auto paper generator.

Architecture

  • Agent system: 42 specialized agents with defined responsibilities and constraints
  • Mode system: 25+ operation modes (full / socratic / revision / calibration, etc.)
  • Scheduler: a 10-stage pipeline with checkpoints and quality gates
  • Schema layer: handoff schemas defining cross-agent data formats (Material Passport)
  • CI/Lint: GitHub Actions-driven spec consistency checks
  • External verification: Semantic Scholar API, DOI validation, VLM figure checks
  • | Skill | Agents | Responsibility | Version | |-------|--------|----------------|---------| | Deep Research | 13 | Literature review, PRISMA systematic reviews, socratic guidance | v2.8 | | Academic Paper | 12 | Paper writing, style calibration, LaTeX output | v3.0 | | Academic Paper Reviewer | 7 | Multi-perspective peer review, 0-100 scale, devil's advocate | v1.8 | | Academic Pipeline | 10 | Full-process orchestration, integrity gates | v3.7 |

    Pipeline stages include drafting, a mandatory Stage 2.5 integrity gate, peer review, re-review, revision, a final integrity gate (Stage 4.5), and finalization with process logging and AI self-reflection.

    Why Human-AI Collaboration, Not Full Automation

    ARS diverges fundamentally from The AI Scientist (Lu et al., 2026, *Nature*), the first end-to-end automated AI research system whose paper passed ICLR 2025 workshop blind review. Lu et al.'s own limitations section lists 7 structural failure modes: implementation bugs passing AI self-review, hallucinated experimental results, shortcut reliance, bug-as-insight reframing, methodology fabrication, frame-lock, and citation hallucination. ARS bets that a human researcher + AI combination avoids these better than either alone.

    Corpus-scale evidence supports the concern: Zhao et al. (2026-05) audited 111 million citations across 2.5 million papers (arXiv, bioRxiv, SSRN, PMC), conservatively estimating 146,932 hallucinated citations in 2025 alone, with an 85.3% survival rate of hallucinations through the bioRxiv-to-PMC published pipeline. This directly motivated ARS v3.7.x's three-layer citation anchoring.

    ARS v3.3 also adopted four PaperOrchestra (Song et al., 2026, arXiv:2604.05018) techniques: Semantic Scholar API validation (Levenshtein ≥ 0.70 title matching, DOI mismatch detection), anti-leakage protocol (marking [MATERIAL GAP] instead of filling from LLM memory), VLM figure verification with a 10-item checklist, and per-dimension score trajectory tracking across revision rounds.

    Key Anti-Hallucination Mechanisms

  • 7-category failure-mode checklist (v3.2): blocking checks at both integrity gates — the pipeline halts until the user confirms any suspected failure
  • 5-type citation hallucination taxonomy (v2.7): Title Fabrication, Partial Author Claim, Inaccurate Hallucination, Partial Hallucination, Synthesis Hallucination
  • Devil's advocate concession threshold (v3.0): rebuttals must score ≥4/5 before the DA concedes; no consecutive concessions; frame-lock detection
  • Anti-sycophancy (v3.0/v3.5.0): conversational health self-checks every 5 turns; a Collaboration Depth Observer scoring 4 dimensions, requiring concrete dialogue-turn citations for scores ≥7
  • Cross-model verification (v3.0): ARS_CROSS_MODEL enables 30% sampled independent review by a second model (GPT-5.4 Pro or Gemini 3.1 Pro)
  • Version Evolution and Engineering Discipline

    From v1.0 (2026-02) to v3.7.0 (2026-05-05), 15+ releases deepened one theme: making hallucination and structural bias detectable, trackable, and human-interruptible. Highlights include SCR reflection loops (v2.8), style calibration from the user's past papers (v2.9), 29 anti-patterns + 22 IRON RULES (v3.1), PRISMA-trAIce compliance (v3.4), blind sprint contracts (v3.6.2), 18 known hallucination pattern protections (v3.6.7), and plugin packaging with 10 slash commands (v3.7.0).

    Engineering practices include lint-driven development (scripts/check_spec_consistency.py, sprint contract tests with 71 test cases, mutation tests for pattern protection) and schema versioning with append-only compliance_history[] for audit integrity.

    Notably, the project published a post-publication audit (2026-03-09): all 68 citations verified via web search, finding 21 problematic citations (31% error rate) even after passing three integrity reviews. Corrections followed: 4 fabricated citations removed, 6 author errors and 7 bibliographic details fixed. This honestly demonstrates that integrity gates reduce but do not eliminate errors — and that auditing itself drives improvement.

    Feynman-Lens Assessment

    Done well: "cargo cult detection" (25 AI高频词 warnings, em-dash limits, three-item-list detection combat AI's patterned writing itself), and teaching agents *how to reason* (Toulmin model, Bradford Hill causal inference) rather than giving steps.

    Avoided questions: if base models keep improving, will mandatory human checkpoints become bottlenecks? And the review standards themselves (0-100 scale, ≥80 acceptance) — frame-lock occurs on the human side too. The v3.7.0 README is candid: these optimizations cannot fully solve AI's structural limits — they make limits visible, trackable, and human-interruptible.

    Fit

    Good for: systematic literature reviews (PRISMA), multi-round revision workflows, strict citation accuracy needs, researchers willing to invest in collaboration, Claude Code users.

    Not for: fully automatic paper generation (explicitly rejected), non-Claude-Code workflows (a Codex CLI sibling exists), speed-first use (~$4-6 but heavy time cost per 15k-word paper), commercial use (CC-BY-NC 4.0).

    Notable Engineering Details

  • Material Passport: YAML audit trail recording literature_corpus[], append-only compliance_history[], reset_boundary[] for cross-session recovery, optional repro_lock
  • Intent-based socratic routing: mode routing detects user intent signals, not keywords — works in any language
  • SessionStart announce hook: full context injection on startup/clear, one-line confirmation on resume/compact — precise context burn control
  • References

  • GitHub: https://github.com/Imbad0202/academic-research-skills
  • Latest version: v3.7.0 (2026-05-05); Author: Cheng-I Wu; License: CC-BY-NC 4.0
  • Codex CLI sibling: https://github.com/Imbad0202/academic-research-skills-codex
  • Lu, C. et al. (2026). "Towards end-to-end automation of AI research." *Nature* 651, 914-919.
  • Zhao, X. et al. (2026-05). Citation hallucination audit. arXiv:2605.07723.
  • Song, Y. et al. (2026). "PaperOrchestra." arXiv:2604.05018.
  • Wang, S. & Zhang, H. (2026). "Pedagogical partnerships with generative AI in higher education." *IJETHE* 23:11.

Tags

#academic-research#claude-code#multi-agent#human-ai-collaboration#anti-hallucination#peer-review#research-tools#citation-verification

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177620129