arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.24858cs.HCcs.MA
收藏

多智能体感知系统中的上下文引导领域适应

Context-Mediated Domain Adaptation in Multi-Agent Sensemaking Systems

Aarhus University(奥胡斯大学);Maastricht University(马斯特里赫特大学);TU Wien(维也纳工业大学)

Anton Wolter, Leon Haag, Vaishali Dhanoa, Niklas Elmqvist

AI总结:

本文提出了一种上下文引导的领域适应方法,通过多智能体系统中的用户修改来隐式指定领域知识,从而改进大语言模型驱动的多代理推理行为。

摘要:

领域专家拥有无法通过显式规范轻易表达的隐性知识。当专家通过修正术语、重构论点和调整重点修改AI生成的产物时,这些修改揭示了传统基于提示的交互中潜藏的领域理解。当前系统将此类修改视为终点修正而非隐式规范,这些规范能够重塑后续推理。我们提出上下文引导的领域适应,是一种范式,其中用户对系统生成产物的修改作为隐式领域规范,从而重塑LLM驱动的多代理推理行为。通过我们的系统Seedentia,一个基于网页的多代理框架,我们展示了生成产物与系统推理之间的双向语义链接。我们的方法实现了规范引导,其中模糊的初始提示通过迭代的人机协作演变为精确的领域规范,通过反向工程用户修改实现隐式知识转移,并通过上下文学习,使代理行为根据观察到的修正模式进行适应。我们展示了与领域专家评估的结果,专家生成并修改了学术论文中的研究问题。我们的系统从用户修改中提取了46个领域知识条目,证明了通过修改模式捕捉隐性专业知识的可行性,尽管样本量有限,限制了关于系统质量改进的结论。

英文摘要:

Domain experts possess tacit knowledge that they cannot easily articulate through explicit specifications. When experts modify AI-generated artifacts by correcting terminology, restructuring arguments, and adjusting emphasis, these edits reveal domain understanding that remains latent in traditional prompt-based interactions. Current systems treat such modifications as endpoint corrections rather than as implicit specifications that could reshape subsequent reasoning. We propose context-mediated domain adaptation, a paradigm where user modifications to system-generated artifacts serve as implicit domain specification that reshapes LLM-powered multi-agent reasoning behavior. Through our system Seedentia, a web-based multi-agent framework for sense-making, we demonstrate bidirectional semantic links between generated artifacts and system reasoning. Our approach enables specification bootstrapping where vague initial prompts evolve into precise domain specifications through iterative human-AI collaboration, implicit knowledge transfer through reverse-engineered user edits, and in-context learning where agent behavior adapts based on observed correction patterns. We present results from an evaluation with domain experts who generated and modified research questions from academic papers. Our system extracted 46 domain knowledge entries from user modifications, demonstrating the feasibility of capturing implicit expertise through edit patterns, though the limited sample size constrains conclusions about systematic quality improvements.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑