This paper introduces the Quest Graph, a formal framework for analyzing the capabilities of agentic systems with finite context. We define abstractions that model common reasoning techniques and establish their computational power: the base Quest Graph is equivalent to an unrestricted Turing machine; the forward-only Finite Quest Decision Process (FQDP), despite its wide use, is only equivalent to a pushdown automaton (context-free); and the Reference-Augmented QDP (RQDP) regains Turing completeness only when stateful queries are allowed.
Since computability affects efficiency, we then analyze the theoretical efficiency of each model by simulating task dependencies in computation graphs. We show that this computational hierarchy translates to concrete performance trade-offs: reference-augmented (Turing-complete) systems can be exponentially more efficient at simulating complex graphs than their non-augmented (context-free) counterparts. This work provides a formal methodology for classifying and understanding the fundamental capabilities of agentic systems.
Dept. of Statistics UC Berkeley(加州大学伯克利分校统计系);Dept. of EECS UC Berkeley(加州大学伯克利分校电子工程与计算机科学系);Microsoft Research(微软研究院);Center for Computational Biology UC Berkeley(加州大学伯克利分校计算生物学中心)
Question's Gambit: The First Move Matters in Agentic Deep Search
University of Toronto(多伦多大学);Mila – Quebec AI Institute(米拉-魁北克人工智能研究所);University of Waterloo(滑铁卢大学);University of California, Berkeley(加州大学伯克利分校);McGill University(麦吉尔大学)
KnowCoder-A1: Incentivizing Agentic Reasoning Capability with Outcome Supervision for KBQA
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);State Key Laboratory of AI Safety(人工智能安全国家重点实验室);School of Computer Science, University of Chinese Academy of Sciences(中国科学院大学计算机科学学院)
Can Agentic AI Match the Performance of Human Data Scientists?
School of Statistics, University of Minnesota(统计学系,明尼苏达大学);Department of Electrical and Computer Engineering, University of Minnesota(电气与计算机工程系,明尼苏达大学);Data Science Institute, University of Chicago(数据科学研究所,芝加哥大学);Carlson School of Management, University of Minnesota(卡尔森管理学院,明尼苏达大学);Cisco Research, San Jose, CA, USA(Cisco研究,加州圣何塞)
TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives
École nationale des chartes – PSL(国立文献学校(巴黎文理研究大学));EPITA(EPITA 工程师学院);EPITA Research Laboratory(EPITA 研究实验室);Geneva Graduate Institute(日内瓦高等国际关系及发展学院)
AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning
SKL-MAIS, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所SKL-MAIS实验室);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences(中国科学院大学交叉学科学院);Meituan(美团)
V-Math: An Agentic Approach to the Vietnamese National High School Graduation Mathematics Exams
CIRTech Institute, HUTECH University, Ho Chi Minh City, Viet Nam(CIRTech研究院,HUTECH大学,胡志明市,越南);Faculty of Information Technology, HUTECH University, Ho Chi Minh City, Vietnam(信息科技学院,HUTECH大学,胡志明市,越南);Nguyen Thai Hoc High School, Gia Lai Province, Vietnam(Nguyen Thai Hoc高中,嘉莱省,越南);Office of Scientific Research, Technology Management and International Cooperation, Tien Giang University, Vietnam(科研办公室,技术管理与国际合作办公室,Tien Giang大学,越南)
本文提出自主智能体框架 V-Math,集成问题生成、求解解释与个性化导师三个 AI 智能体,支持越南高中生备考及教师辅助出题,初步评估显示其能高准确率生成合规考题并提供连贯解释。