Inspired by search and recommender systems, this work builds Find, Attempt, and Recommend (FAR), a literature-to-review cascade that automates the search for suitable problems and focuses human attention on artifacts that have passed several stages of filtering.
Abstract
AI systems are increasingly capable of contributing to mathematical research. In research practice, frontier-model reasoning is a limited resource, and expert mathematical review is even more sharply constrained. Allocating these scarce resources well is therefore central to making AI-assisted mathematical discovery efficient. In most current AI-for-math workflows, human effort is concentrated at the beginning and end, in selecting suitable research problems and later reviewing the resulting artifacts. These two stages are becoming bottlenecks for research-level mathematics. We address them by proposing a new human-AI discovery paradigm. The human input is no longer a single problem selected in advance, but a research direction in which the experts have interest and expertise. The system then searches a broad literature corpus for candidate problems in that direction. Inspired by search and recommender systems, we build Find, Attempt, and Recommend (FAR), a literature-to-review cascade that automates the search for suitable problems and focuses human attention on artifacts that have passed several stages of filtering. In a combinatorics pilot, the pipeline starts from 5,245 combinatorics papers, recovers 6,453 candidate conjectures or open problems, and filters them to 4,717 apparently well-posed and still-open conjectures. Subsequent reasoning and automated triage stages surface 598 potential resolutions and select 77 items for author-team review. Among them, we identify many interesting discoveries, including results on conjectures and questions of Davies--Jenssen--Perkins--Roberts, Erd\H{o}s--Straus, Ikenmeyer--Pak--Panova, and Lund--Saraf--Wolf. These results demonstrate the effectiveness of this new mode of human-AI collaboration for mathematical discovery.
This article examines the emerging paradigm of agentic AI for scientific discovery, traces the conceptual shift from tools to agents, lays out a six-stage workflow spanning literature synthesis to manuscript generation, and reviews practical systems in chemistry, equation discovery, materials science, and general machine learning research.
Alexander Taktakidze· Longevity Horizon· 0 citations
AI co-scientists that generate hypotheses, retrieve related work, design experiments, execute code, and draft full papers are beginning to change how research is carried out. Despite this rapid progress, state-of-the-art systems remain researcher-agnostic: given a research goal, they optimize novelty, validity, or reviewer score while ignoring the individual scientist who will use the output. This overlooks a fundamental fact about research, namely, that what counts as novel, valuable, or feasible depends on the researcher, including their prior work, methodological repertoire, and the collaborators and communities in which they are embedded. In this work, we introduce the problem of personalized auto-research, which conditions every stage of the research process on a representation of the individual researcher. We argue that personalization is not a convenience layer, but rather the fundamental property that allows an AI system to serve as a genuine co-scientist rather than a generic instrument. To address this problem, we propose a general and flexible framework that threads a graph-grounded researcher context through retrieval, hypothesis search, experimentation, writing, and review. The framework consists of three fundamental components: (i) graph-grounded researcher representations, (ii) personalization across the full research pipeline, and (iii) evaluation grounded in the individual. Notably, we highlight a one-size-fits-all failure mode where distinct researchers issuing the same goal receive essentially the same research, erasing the tacit knowledge through which novel ideas arise. Finally, we discuss fundamental open problems and challenges.
B. Ni, Franck Dernoncourt, Hongjie Chen et al.· 0 citations
The development of intelligence has brought about major changes to knowledge discovery systems, which now deliver exceptional data analysis capabilities. Artificial intelligence (AI) has changed the way we discover things. The current research looks at intelligence-based knowledge discovery systems by studying their different application areas and their operating methods and existing obstacles. This study looks at how AI is used in different areas such as scientific research, healthcare, education, and finance, and explores knowledge graphs, explainable AI, manufacturing operations, and human-AI interface design. These areas together give us a view of the research area of AI. The review looks at existing research to find trends, gaps, and future directions. It gives researchers and practitioners a framework to work with. The study chooses and looks at research works in a comprehensive way so it includes both theoretical knowledge and practical knowledge. The results of the research show that AI-based systems improve decision-making and innovative work. AI-based systems also improve decision-making and innovative work. In the field, AI is used to create treatment plans. Healthcare facilities use intelligence to enhance patient diagnosis with personalised medical solutions. Educational applications use intelligence for adaptive learning. Financial systems use intelligence for fraud detection and risk assessment. The development of knowledge graphs and explainable AI is essential for logical processes. Manufacturing systems use intelligence technology for predictive maintenance. AI interaction is important for usability and trust. The study ends with a summary of opportunities and existing problems that require scientific fields to work together. The review provides materials that researchers will use to conduct studies about AI-based methods for discovering knowledge. AI is used in different areas and it is changing the way we do things. The study of intelligence-based knowledge discovery systems is important for the future of research. AI will continue to change the way we discover things and it will be used in many areas.
A. Sinhababu· International Journal of Inf...· 0 citations
As AI agents and tools increasingly carry out everyday tasks on behalf of users, the digital ecosystem is rapidly filling with agents that offer overlapping or complementary functionalities, raising a fundamental challenge: how can users, developers, and orchestrating systems effectively identify, compare, and select the most appropriate agents or tools for a given task? While rooted in traditional information retrieval (IR), agent search introduces new challenges because the retrieved entities are executable systems rather than static information artifacts, and their suitability depends on capabilities, behaviors, constraints, uncertainty, and task-dependent performance. We argue that the IR community is well-positioned to advance this emerging problem setting, which we refer to as AgentSearch, by developing principled methods for representing, indexing, retrieving, and ranking AI agents and tools under multi-dimensional relevance criteria. The AgentSearch Workshop aims to bring together researchers and practitioners from academia and industry to explore the challenges and opportunities of agent and tool search, including agent discovery, capability representation, retrieval and ranking models, evaluation methodologies, and issues related to safety, fairness, personalization, and explainability. To support concrete progress, the workshop will also host an exploratory AgentSearch Challenge that provides a shared experimental setting for ranking agents given a task. The workshop will adopt an interactive format featuring breakout discussions, poster and spotlight sessions, invited talks, and collaborative activities, fostering active engagement and cross-disciplinary exchange beyond a traditional mini-conference structure.
Bin Wu, To Eun Kim, Yue Feng et al.· Annual International ACM SIG...· 0 citations
Bridging Literature, Agents, and Zero-gap Experimentation (BLAZE), a paradigm of socialized scientific intelligence, makes discovery more traceable, reproducible, and cumulative while preserving human creativity, judgment, and responsibility.
Xinjie Yao, Xingxin Xu, Xiyuan Gao et al.· 0 citations
Scientists at European XFEL conduct experiments that generate very large and complex datasets. The subsequent data analysis is challenging as scientists must combine their domain expertise with facility- and software-specific knowledge scattered across documentation, tools, and support channels. To address this problem, we designed and evaluated an agentic AI system tailored to the scientists'needs and integrated with the high-performance computing environment of European XFEL. Using a design science research approach, we conducted a rapid literature review, a systematic evaluation of 16 AI tools, multiple interviews, a focus group, and a user study with experts at European XFEL to develop and evaluate two prototypes. Our study identifies key knowledge challenges in scientific data analysis, derives requirements for an AI agent that supports knowledge retrieval and source code generation, and proposes design recommendations for a specialized system adaptable to the evolving AI tool landscape. These findings provide guidance for developing maintainable AI support in highly specialized scientific environments.
Tim Fuchs, Luca Gelisio, S. Hauf et al.· 0 citations