ARIS：基於對抗式多智能體協作的自主研究系統
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
May 4, 2026
作者: Ruofeng Yang, Yongcan Li, Shuai Li
cs.AI
摘要
本報告介紹了開源自主研究框架ARIS（Auto-Research-in-sleep），涵蓋其架構設計、保障機制及早期部署經驗。基於大型語言模型的智能體系統效能，既取決於模型權重，也受其外圍框架的調控——該框架決定何種資訊需被儲存、檢索並呈現給模型。針對長週期研究流程，核心失效模式並非顯性中斷，而是看似合理卻缺乏實證支持的成果：長期運行的智能體可能產出證據不完整、誤報或默認繼承執行者預設框架的主張。因此，我們提出ARIS研究框架，其預設透過跨模型對抗性協作來協調機器學習研究流程：由執行模型推動研究進展，同時建議採用不同模型家族的審核者來批判中間產物並要求修訂。
ARIS包含三層架構：執行層提供65+個可複用的Markdown定義技能、透過MCP實現的模型集成、用於迭代重用既往發現的持久化研究維基，以及確定性圖表生成功能；編排層協調五種端到端工作流，具備可調節工作量設置與可配置的審核模型路由機制；保障層則包含三階段實驗主張驗證流程（完整性驗證、結果與主張映射、通過交叉核對手稿陳述與主張分類帳及原始證據的審計），以及五輪科學編輯流水線、數學證明檢查和渲染PDF視覺化校驗。其原型自我改進迴路會記錄研究軌跡，並提出僅在通過審核後才被採納的框架優化方案。
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.