用对抗协作机制让AI自主完成科研，防止虚假成功。
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
- 让执行模型与评审模型跨架构协作，动态验证研究过程。
- 通过三阶段验证确保结论有证据支撑，错误率下降47%。
- 适合希望自动化科研流程的研究者，尤其关注可复现性。
本文介绍ARIS（Auto-Research-in-sleep）——一个开源的自主科研框架，包含其架构、保障机制及早期部署经验。基于大语言模型的智能体系统性能不仅取决于模型权重，更依赖于其外围框架，该框架决定信息的存储、检索与呈现方式。在长周期科研任务中，主要风险并非明显崩溃，而是看似合理却缺乏支持的“虚假成功”：长期运行的智能体可能生成证据不全、误报或隐式继承执行者预设的主张。为此，我们提出以跨模型对抗协作作为默认配置的ARIS框架：由一个执行模型推进研究，同时推荐来自不同模型家族的评审模型对中间成果进行批判并要求修改。ARIS包含三层架构：执行层提供65种以上可重用的Markdown定义技能，通过MCP实现模型集成，持久化研究维基支持迭代复用，并具备确定性图表生成能力；编排层协调五类端到端工作流，支持可调节努力程度和评审模型路由配置；保障层包含三阶段验证机制，检查实验主张是否被证据支持：完整性验证、结果到主张映射、主张审计（将文稿陈述与主张账本及原始证据交叉核对），以及五轮科学编辑流程、数学证明检查和渲染后PDF视觉审查。原型自改进循环记录研究轨迹，提出框架优化建议，仅在评审批准后采纳。
原文摘要 · Abstract (English)
This report describes ARIS (Auto-Research-in-sleep), an open-source research harness for autonomous research, including its architecture, assurance mechanisms, and early deployment experience. The performance of agent systems built on LLMs depends on both the model weights and the harness around them, which governs what information to store, retrieve, and present to the model. For long-horizon research workflows, the central failure mode is not a visible breakdown but a plausible unsupported success: a long-running agent can produce claims whose evidential support is incomplete, misreported, or silently inherited from the executor's framing. Therefore, we present ARIS as a research harness that coordinates machine-learning research workflows through cross-model adversarial collaboration as a default configuration: an executor model drives forward progress while a reviewer from a different model family is recommended to critique intermediate artifacts and request revisions. ARIS has three architectural layers. The execution layer provides more than 65 reusable Markdown-defined skills, model integrations via MCP, a persistent research wiki for iterative reuse of prior findings, and deterministic figure generation. The orchestration layer coordinates five end-to-end workflows with adjustable effort settings and configurable routing to reviewer models. The assurance layer includes a three-stage process for checking whether experimental claims are supported by evidence: integrity verification, result-to-claim mapping, and claim auditing that cross-checks manuscript statements against the claim ledger and raw evidence, as well as a five-pass scientific-editing pipeline, mathematical-proof checks, and visual inspection of the rendered PDF. A prototype self-improvement loop records research traces and proposes harness improvements that are adopted only after reviewer approval.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。