让AI研究失败经验变共享知识，提升科研效率与成功率。
Negative Knowledge as Failure-aware Shared Memory for AutoResearch
- 将失败实验转化为结构化记录，供后续研究者参考或拒绝。
- 在非线性方程研究中，新任务解决率超基线，且节省15%以上token。
- 失败知识可跨任务迁移，适合需要持续积累的AI科研团队使用。
AI辅助科研系统会产生大量失败尝试，但这些失败极少成为持久共享的知识资产。本文提出负向知识记忆层：由校准代理将每次失败转化为有界、类型化的记录存入共享数据库，下游研究代理在提出下一步实验前显式采纳或拒绝这些记录。我们在两个场景下评估该机制：在ScienceAgentBench上进行同任务重试，以及在两个非线性数学物理偏微分方程（PDE）问题上的跨任务科研。结果表明，引入负向知识层的智能体在性能上优于基线模型，同时消耗更少的token；具备该知识库的代理能解决所有基线均失败的新任务。此外，先前的负向知识库可迁移并增强不同PDE问题上的AutoResearch表现。这些结果表明，结构化的负向知识应被视为科学科研中的核心知识资产，而不仅是记忆压缩或调试工具，它应与正向发现共同构成集体科研记忆的基础架构。代码已开源：https://github.com/hch-wang/Negative_Knowledge。
原文摘要 · Abstract (English)
AI-assisted research systems generate many failed attempts, but those failures rarely become a durable, shared knowledge asset. We propose a negative knowledge memory layer: a curator agent converts each failed attempt into a bounded, typed record in a shared bank, and a downstream research agent explicitly adopts or rejects those records before proposing its next experiment. We evaluate this layer in two settings: same-task retry on ScienceAgentBench and cross-task scientific research on two nonlinear math-physics PDE problems. The negative knowledge layer outperforms vanilla AutoResearch baselines while using fewer tokens; agents with the negative knowledge bank solve new tasks that all baselines fail to solve in PDE systems research. We also show that the previous negative knowledge bank can transfer and enhance AutoResearch on different PDE problems. These results suggest that structured negative knowledge is a knowledge asset that should be explicitly maintained in broader AI-engaged scientific research beyond a memory-compression or debugging aid, alongside positive findings, as a collective infrastructure for scientific memory. Code is available at https://github.com/hch-wang/Negative_Knowledge.
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。