Networked Intelligence: Active Shared Context Graphs for Human-AI Team Science

• URL: http://arxiv.org/abs/2607.13220v2
• Date: Thu, 16 Jul 2026 17:32:26 GMT
• Title: Networked Intelligence: Active Shared Context Graphs for Human-AI Team Science
• Abstract summary: We introduce Mycelium, an active shared workspace that automatically connects researchers and AI agents.<n>As human users and agents work, the system captures important observations and hypotheses, tracks how they relate to the team's evolving knowledge model.<n>We describe networked intelligence as sparse conditional computation over distributed scientific contexts.
• Score: 0.8754288080101668
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Benchmarking AI Agents for Addressing Scientific Challenges Across Scales [118.2204632627895]
  SciAgentArena is a systematic benchmark for evaluating AI agents in real-world scientific research scenarios.<n>It comprises approximately 200 tasks with stepwise verification and an interactive, agent-agnostic environment for assessing diverse AI agents.<n>We find that current agents can contribute effectively to well-specified data-analysis, particularly when the task structure and evaluation criteria are clear.
  arXiv  Detail & Related papers  (2026-06-10T22:55:30Z)
• Characterizing initial human-AI proof formalization workflows [66.06866890889131]
  Advances in AI systems' ability to generate code and engage in increasingly high-level mathematical reasoning promise to transform people's ability to formalize and thereby verify proofs.<n>We conduct a mixed-methods analysis into the initial impact of AI on people's formalization.<n>A qualitative survey shows that people's preferences are diverse, but with a general desire for AI assistance in formalization.
  arXiv  Detail & Related papers  (2026-06-02T22:58:19Z)
• Intentmaking and Sensemaking: Human Interaction with AI-Guided Mathematical Discovery [72.49593499512092]
  We identify and characterize a distinct workflow we term intentmaking.<n>We frame this as a natural extension to sensemaking.<n>Our documentation of these themes suggests an approach to designing AI tools for scientific discovery.
  arXiv  Detail & Related papers  (2026-05-07T09:30:25Z)
• Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agents [44.28040661008415]
  As large language model agents scale to populations of millions, a key question arises: Does collective intelligence emerge spontaneously from scale?<n>We present the first empirical evaluation of this question in a large-scale autonomous agent society.<n>Our experiments reveal a stark absence of collective intelligence. The society fails to outperform individual frontier models on complex reasoning tasks, rarely synthesizes distributed information, and often fails even trivial coordination tasks.
  arXiv  Detail & Related papers  (2026-04-24T11:11:36Z)
• CoGrid & the Multi-User Gymnasium: A Framework for Multi-Agent Experimentation [0.17188280334580197]
  CoGrid is a multi-agent grid-based simulation library with dual NumPy and JAX backends.<n>Multi-User Gymnasium translates such simulation environments directly into interactive web-based experiments.<n> MUG supports interactions with arbitrary numbers of humans and AI, utilizing either server-authoritative or peer-to-peer networking with rollback netcode to account for latency.
  arXiv  Detail & Related papers  (2026-04-16T14:10:38Z)
• AI Phenomenology for Understanding Human-AI Experiences Across Eras [8.54750896635797]
  We argue for AI phenomenology: a research stance that asks "How did it feel?" when interacting with AI systems.<n>We motivate AI phenomenology as a framework that captures how alignment is experienced, negotiated, and updated between users and AI systems.
  arXiv  Detail & Related papers  (2026-03-09T23:26:46Z)
• Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents [14.448267395835721]
  We propose a unified taxonomy that breaks agents into Perception, Brain, Planning, Action, Tool Use, and Collaboration.<n>We also group the environments in which these agents operate, including digital operating systems, embodied robotics, and other specialized domains.
  arXiv  Detail & Related papers  (2026-01-18T19:51:16Z)
• Can Agentic AI Match the Performance of Human Data Scientists? [27.236034079837044]
  Large language models (LLMs) have significantly automated data science.<n>Can these agentic AI systems truly match the performance of human data scientists?<n>We show that agentic AI that relies on generic analytics workflow falls short of methods that use domain-specific insights.
  arXiv  Detail & Related papers  (2025-12-24T05:31:42Z)
• AI4X Roadmap: Artificial Intelligence for the advancement of scientific pursuit and its future directions [65.44445343399126]
  We look at AI-enabled science across biology, chemistry, climate science, mathematics, materials science, physics, self-driving laboratories and unconventional computing.<n>Several shared themes emerge: the need for diverse and trustworthy data, transferable electronic-structure and interatomic models, AI systems integrated into end-to-end scientific synthesis.<n>Across domains, we highlight how large foundation models, active learning and self-driving laboratories can close loops between prediction and validation.
  arXiv  Detail & Related papers  (2025-11-26T02:10:28Z)
• What Work is AI Actually Doing? Uncovering the Drivers of Generative AI Adoption [1.4977849232424492]
  This study investigates which intrinsic task characteristics drive users' decisions to delegate work to AI systems.<n>This research provides the first systematic evidence linking real-world generative AI usage to a comprehensive, multi-dimensional framework of intrinsic task characteristics.
  arXiv  Detail & Related papers  (2025-10-26T19:13:37Z)
• HugAgent: Benchmarking LLMs for Simulation of Individualized Human Reasoning [27.80877165363182]
  We introduce HugAgent, which rethinks human reasoning simulation along three dimensions.<n>The benchmark is open-sourced as HugAgent and TraceYourThinking.
  arXiv  Detail & Related papers  (2025-10-16T21:03:54Z)
• Scaling Large Language Model-based Multi-Agent Collaboration [72.8998796426346]
  Recent breakthroughs in large language model-driven autonomous agents have revealed that multi-agent collaboration often surpasses each individual through collective reasoning.<n>This study explores whether the continuous addition of collaborative agents can yield similar benefits.
  arXiv  Detail & Related papers  (2024-06-11T11:02:04Z)
• Human-Modeling in Sequential Decision-Making: An Analysis through the Lens of Human-Aware AI [20.21053807133341]
  We try to provide an account of what constitutes a human-aware AI system. We see that human-aware AI is a design oriented paradigm, one that focuses on the need for modeling the humans it may interact with.
  arXiv  Detail & Related papers  (2024-05-13T14:17:52Z)
• Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning [50.47568731994238]
  Key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL) This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies.
  arXiv  Detail & Related papers  (2023-12-22T17:57:57Z)
• Neural Amortized Inference for Nested Multi-agent Reasoning [54.39127942041582]
  We propose a novel approach to bridge the gap between human-like inference capabilities and computational limitations. We evaluate our method in two challenging multi-agent interaction domains.
  arXiv  Detail & Related papers  (2023-08-21T22:40:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.