This work introduces Mycelium, an active shared workspace that automatically connects researchers and AI agents, and describes networked intelligence as sparse conditional computation over distributed scientific contexts as sparse conditional computation over distributed scientific contexts.
Abstract
Most AI-for-science systems focus on scaling a single reasoning process by using better models, larger context windows, long-horizon agentic execution, or digital co-scientists working with one principal user. However, challenging scientific problems are rarely solved by one reasoner alone. They are solved by teams whose members carry different priors, experimental background, tacit knowledge, and domain-trained intuitions. The open problem is therefore not only how to scale models, but how to develop"networked intelligence", scaling the connections between humans and AI systems so that a result or hypothesis produced in one context reaches another person, agent, instrument or robot that can act on it. We introduce Mycelium, an active shared workspace that automatically connects researchers and AI agents. As human users and agents work, the system captures important observations and hypotheses, tracks how they relate to the team's evolving knowledge model, and routes them to the person or agent whose next decision they can inform. We evaluate Mycelium through a real-world scientific discovery use case: a biological multi-omics campaign where shared context turned a local analytical finding into a cross-expert mechanistic constraint and ultimately into an experimental design. Finally, we describe networked intelligence as sparse conditional computation over distributed scientific contexts. This framework establishes when a scaled standalone agent is sufficient, and when isolated data and specialized expertise make a networked approach essential.
This work argues that studying AI Scientists as human-agent systems (HAS) is both underexplored and undervalued, and calls for new research that adopts the HAS lens to develop mathematical frameworks for understanding and fostering human-AI synergy in scientific discovery.
P. Emami, Sameera Horawalavithana, T. Nguyễn et al.· 0 citations
Large language models and foundation models are increasingly embedded in reasoning systems that plan, invoke tools, use memory, gather evidence, and iteratively refine their outputs. The second KDD Day on AI Reasoning brings together researchers and practitioners from academia and industry to examine how these systems can be made more capable, reliable, interpretable, and efficient. The program spans scientific discovery, human-centered interaction, software engineering, time-series analysis, deep research, computer use, and inference infrastructure. Across these domains, the day highlights shared challenges: grounding decisions in evidence, designing effective feedback and verification mechanisms, evaluating open-ended behavior, managing test-time computation, and preserving meaningful human control. Through keynote and invited presentations, the event provides a forum for connecting advances in models, agents, data, systems, and applications, and for identifying research directions toward trustworthy next-generation reasoning systems.
Jun Huan, James Caverlee, Lei Li et al.· Proceedings of the 32nd ACM...· 0 citations
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
Multi-agent information retrieval is not a future prospect -- it is an operational reality. Existing frameworks for multi-agent coordination -- including comprehensive taxonomies of collaboration mechanisms and adaptive orchestration architectures for modular generative IR systems -- address the agent-only case: they configure AI components that interact with each other to serve a passive human end-user. The heterogeneous case -- teams in which humans and AI agents serve as joint cognitive participants with complementary capabilities -- remains without a principled design foundation. This perspectives paper introduces the Collaborative Information Retrieval Configurations (CIRC) framework, organized around three dimensions -- composition, coordination, and adaptation -- that provide systematic guidance for designing and evaluating human-agent teams in IR. Situated within the design science research paradigm, CIRC is prescriptive where prior taxonomies are descriptive: it specifies when collaborative configurations outperform single-agent approaches, which coordination patterns suit which task types, and how to evaluate team-level performance rather than individual agent output. We ground the framework in simulation experiments on TREC Deep Learning 2020 that demonstrate the framework's discriminative capacity: collaborative configurations produce measurably distinct quality profiles, and collaborative advantages concentrate at higher task complexity in ways that standard IR metrics fail to capture. We outline a three-dimensional evaluation framework and a concrete research agenda to advance the science of collaborative IR configurations.
Chirag Shah, L. Tamine, Mouly Dewan· International Conference on...· 0 citations
Identifying promising scientific ideas remains an important challenge in research practice. Researchers commonly rely on small-group discussions or one-to-one interactions with a single large language model, yet these approaches often expose them to only a limited range of perspectives and directions. We present AgentPanel, a multi-agent forum for human--AI collaboration in scientific exploration. Heterogeneous agents asynchronously discuss scientific questions in a forum-style environment, while researchers can submit questions, browse and organize candidate ideas, engage agents in follow-up interactions, and optionally generate post-hoc summary reports. We evaluate AgentPanel in terms of idea quality, exploration breadth, interaction effectiveness, candidate-selection efficiency, and practical utility. Offline experiments show that AgentPanel outperforms a centralized multi-agent debate baseline. A human study with 20 participants further shows that users value AgentPanel for perspective diversity and exploration support. In experience-based comparisons with commonly used LLM tools, 65\% of participants favored AgentPanel for both breadth of research directions and overall suitability for early-stage exploration. The platform is publicly available at https://agentpanel.cc/.
Zhiyao Cui, Qianyi Wang, Hao Yan et al.· 0 citations
Large language models (LLMs) and agentic AI systems are rapidly moving into user-facing applications, yet most remain fundamentally generic, optimized for population-level objectives under the assumption that one model can serve all users. This assumption is increasingly misaligned with real-world deployment, where AI systems interact continuously with individuals whose preferences, knowledge, goals, and values evolve over time. PILA'26 is motivated by the need to move beyond static general models toward personal intelligence ---AI systems that explicitly model users and dynamically adapt their reasoning, behavior, and decisions through memory, interaction, and lifelong learning. The workshop brings together researchers and practitioners from data mining, LLMs, NLP, IR, human-centered AI, and AI safety to position personalization as a central research direction for next-generation AI systems at KDD. Topics include user memory and personalized alignment, self-evolving and lifelong learning, datasets and evaluation, real-world applications, and trustworthiness in user-adaptive AI. Workshop website: https://pila26-workshop.github.io.
Xiaoyan Zhao, Yang Zhang, Moxin Li et al.· Proceedings of the 32nd ACM...· 0 citations