搜索结果：collaboration

Large Language Models (LLMs) are increasingly used to power autonomous agents for complex, multi-step tasks. However, human-agent interaction remains pointwise and reactive: users approve or correct individual actions to mitigate immediate risks, without visibility into subsequent consequences. This forces users to mentally simulate long-term effects, a cognitively demanding and often inaccurate process. Users have control over individual steps but lack the foresight to make informed decisions. We argue that effective collaboration requires foresight, not just control. We propose simulation-in-the-loop, an interaction paradigm that enables users and agents to explore simulated future trajectories before committing to decisions. Simulation transforms intervention from reactive guesswork into informed exploration, while helping users discover latent constraints and preferences along the way. This perspective paper characterizes the limitations of current paradigms, introduces a conceptual framework for simulation-based collaboration, and illustrates its potential through concrete human-agent collaboration scenarios.

AI accessibility tools have mostly been designed for individual use, helping one person overcome a specific functional barrier. But for many people with disabilities, complex tasks are accomplished through collaboration with others who bring complementary abilities, not solitary effort. We propose a three-layer framework, Channelling, Coordinating, and Co-Creating, that rethinks AI's role in ability-diverse collaboration: establishing shared informational ground across abilities, mediating workflows between collaborators with different abilities, and contributing as a bounded partner toward shared goals. Grounded in the Ability-Diverse Collaboration framework, grounding theory, and Carlile's 3T framework, it extends the ``agents as remote collaborators'' vision by centring the collaborative, interdependent ways people with disabilities already work.

The rapid evolution of Large Language Model (LLM)-based autonomous agents is reshaping the digital landscape toward an emerging Agentic Web, where increasingly specialized agents must collaborate to accomplish complex tasks. However, existing collaboration paradigms are constrained to message passing, leaving execution environments as isolated silos. This creates a context gap: agents cannot directly manipulate files or invoke tools in a peer's environment, and must instead resort to costly, error-prone environment reconstruction. We introduce the Agent Workspace Collaboration Protocol (AWCP), which bridges this gap through temporary workspace delegation inspired by the Unix philosophy that everything is a file. AWCP decouples a lightweight control plane from pluggable transport mechanisms, allowing a Delegator to project its workspace to a remote Executor, who then operates on the shared files directly with unmodified local toolchains. We provide a fully open-source reference implementation with MCP tool integration and validate the protocol through live demonstrations of asymmetric collaboration, where agents with complementary capabilities cooperate through delegated workspaces.

The Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) will produce unprecedented volumes of heterogeneous astronomical data (images, catalogs, and alerts) that challenge traditional analysis pipelines. The LSST Dark Energy Science Collaboration (DESC) aims to derive robust constraints on dark energy and dark matter from these data, requiring methods that are statistically powerful, scalable, and operationally reliable. Artificial intelligence and machine learning (AI/ML) are already embedded across DESC science workflows, from photometric redshifts and transient classification to weak lensing inference and cosmological simulations. Yet their utility for precision cosmology hinges on trustworthy uncertainty quantification, robustness to covariate shift and model misspecification, and reproducible integration within scientific pipelines. This white paper surveys the current landscape of AI/ML across DESC's primary cosmological probes and cross-cutting analyses, revealing that the same core methodologies and fundamental challenges recur across disparate science cases. Since progress on these cross-cutting challenges would benefit multiple probes simultaneously, we ide

The COMPASS Collaboration has recently published an article "Multiplicities of positive and negative pions, kaons, and unidentified hadrons from deep-inelastic scattering of muons off a liquid hydrogen target", Phys. Rev. D 112 (2025) 012002. In contrast to earlier COMPASS publications on similar topics, the aforementioned article features an enhanced treatment of QED radiative corrections, employing the DJANGOH Monte Carlo generator. This methodological improvement led to corrections that are up to 12% larger in the low-x, high-z region compared to the previously applied ones. To ensure consistent treatment of COMPASS data sets obtained using both isoscalar and proton targets, this paper presents an updated set of isoscalar multiplicities based on DJANGOH-derived radiative corrections. The present results supersede those published in Phys. Lett. B 764 (2017) 1 and Phys. Lett. B 767 (2017) 133.

By observing collider neutrino interactions of different flavours, the SND@LHC and Faser experiments have shown that the LHC can make interesting contributions to neutrino physics. This document summarizes why the SND@LHC Collaboration intends to continue taking data at the High Luminosity LHC (HL-LHC). The upgraded detector will instrument the regions of both the neutrino vertex and the magnetized calorimeter with silicon microstrips. The use of this technology will allow us to continue the physics program of the current SND@LHC detector with higher statistics. It will also offer new possibilities. For instance, the magnetization of the hadron calorimeter will enable the separation between neutrinos and antineutrinos. This could lead to the first direct observation of tau antineutrinos. The use of ultrafast timing layers will enable triggers to be sent to ATLAS, potentially allowing the identification of the charm quark pair that produced the neutrino interacting in the detector. Such tagging of the neutrino source would fulfill Pontecorvo original proposal of a tagged neutrino beam. The experiment will perform unique measurements with high energy neutrinos and will also provide a

AI agents powered by large language models (LLMs) have shown strong capabilities in problem solving. Through combining many intelligent agents, multi-agent collaboration has emerged as a promising approach to tackle complex, multi-faceted problems that exceed the capabilities of single AI agents. However, designing the collaboration protocols and evaluating the effectiveness of these systems remains a significant challenge, especially for enterprise applications. This report addresses these challenges by presenting a comprehensive evaluation of coordination and routing capabilities in a novel multi-agent collaboration framework. We evaluate two key operational modes: (1) a coordination mode enabling complex task completion through parallel communication and payload referencing, and (2) a routing mode for efficient message forwarding between agents. We benchmark on a set of handcrafted scenarios from three enterprise domains, which are publicly released with the report. For coordination capabilities, we demonstrate the effectiveness of inter-agent communication and payload referencing mechanisms, achieving end-to-end goal success rates of 90%. Our analysis yields several key finding

The Advanced Wakefield Experiment, AWAKE, is a well-established international collaboration and aims to develop the proton-driven plasma wakefield acceleration of electron bunches to energies and qualities suitable for first particle physics applications, such as strong-field QED and fixed target experiments ($\sim$50-200GeV). Numerical simulations show that these energies can be reached with an average accelerating gradient of $\sim1$GeV/m in a single proton-driven plasma wakefield stage. This is enabled by the high energy per particle and per bunch of the CERN SPS 19kJ, 400GeV and LHC ($\sim$120kJ, 7TeV) proton bunches. Bunches produced by synchrotrons are long, and AWAKE takes advantage of the self-modulation process to drive wakefields with GV/m amplitude. By the end of 2025, all physics concepts related to self-modulation will have been experimentally established as part of the AWAKE ongoing program that started in 2016. Key achievements include: direct observation of self-modulation, stabilization and control by two seeding methods, acceleration of externally injected electrons from 19MeV to more than 2GeV, and sustained high wakefield amplitudes beyond self-modulation satura

Shared experiences are fundamental to social connection, yet media consumption is increasingly solitary. While AI companions offer real-time reactions and emotional regulation, existing systems either rely on single-agent designs or lack the social awareness and multi-party interaction required to replicate authentic group dynamics. We present CompanionCast, a general framework for orchestrating multiple specialized AI agents as social collaborators within a live shared context. CompanionCast integrates multimodal event detection, rolling context caching for improved grounding, and spatial audio to enhance co-presence. We validate CompanionCast through sports viewing, a domain with rich dynamics and strong social traditions. Pilot studies with soccer fans demonstrate that CompanionCast significantly improves perceived social presence and emotional sharing compared to solitary viewing. We conclude by discussing implications and open challenges for multi-agent systems as social collaborators in shared experiences.

Background: Software development teams are increasingly diverse, embedded, and cross-disciplinary. Domain experts (DEs) from different disciplines collaborate with professional software developers (SDEs), bringing complementary expertise in creating and maintaining complex production software. However, contested expectations, divergent problem-solving perspectives, and conflicting priorities lead to friction. Aims: This study aims to investigate the dynamics of emerging collaboration of cross-disciplinary software development (CDSD) by exploring the expectations held by DEs and SDEs and understanding how these frictions manifest in practice. Method: We utilize Activity Theory (AT), a well-established socio-technical framework, as an analytical lens in a grounded, empirical investigation, conducted through a mixed-method study involving 24 interviews (12 DEs and 12 SDEs) and a large-scale validation survey with 293 participants (161 DEs and 132 SDEs). Results: We conceptualize and empirically ground the CDSD dynamics. We identified eight expectations held by SDEs and six by DEs. By mapping these expectations to AT components, we revealed 21 frictions in CDSD and illustrated where an

This Chapter examines the dynamics of conflict and collaboration in human-machine systems, with a particular focus on large-scale, internet-based collaborative platforms. While these platforms represent successful examples of collective knowledge production, they are also sites of significant conflict, as diverse participants with differing intentions and perspectives interact. The analysis identifies recurring patterns of interaction, including serial attacks, reciprocal revenge, and third-party interventions. These microstructures reveal the role of experience, cultural differences, and topic sensitivity in shaping human-human, human-machine, and machine-machine interactions. The chapter further investigates the role of algorithmic agents and bots, highlighting their dual nature: they enhance collaboration by automating tasks but can also contribute to persistent conflicts with both humans and other machines. We conclude with policy recommendations that emphasize transparency, balance, cultural sensitivity, and governance to maximize the benefits of human-machine synergy while minimizing potential detriments.

In healthcare intelligence, the ability to fuse heterogeneous, multi-intent information from diverse clinical sources is fundamental to building reliable decision-making systems. Large Language Model (LLM)-driven information interaction systems currently showing potential promise in the healthcare domain. Nevertheless, they often suffer from information redundancy and coupling when dealing with complex medical intents, leading to severe hallucinations and performance bottlenecks. To this end, we propose MedAide, an LLM-based medical multi-agent collaboration framework designed to enable intent-aware information fusion and coordinated reasoning across specialized healthcare domains. Specifically, we introduce a regularization-guided module that combines syntactic constraints with retrieval augmented generation to decompose complex queries into structured representations, facilitating fine-grained clinical information fusion and intent resolution. Additionally, a dynamic intent prototype matching module is proposed to utilize dynamic prototype representation with a semantic similarity matching mechanism to achieve adaptive recognition and updating of the agent's intent in multi-round

The incidence of extramural collaboration in academic research activities is increasing as a result of various factors. These factors include policy measures aimed at fostering partnership and networking among the various components of the research system, policies which are in turn justified by the idea that knowledge sharing could increase the effectiveness of the system. Over the last two decades, the scientific community has also stepped up activities to assess the actual impact of collaboration intensity on the performance of research systems. This study draws on a number of empirical analyses, with the intention of measuring the effects of extramural collaboration on research performance and, indirectly, verifying the legitimacy of policies that support this type of collaboration. The analysis focuses on the Italian academic research system. The aim of the work is to assess the level of correlation, at institutional level, between scientific productivity and collaboration intensity as a whole, both internationally and with private organizations. This will be carried out using a bibliometric type of approach, which equates collaboration with the co-authorship of scientific pub

We give a brief report on the basic properties and cutoff scale of our new configuration set (HAL-Conf-2023). We generated 8,000 trajectories of the gauge configurations on $96^4$ lattices with the same lattice parameters as the PACS collaboration \cite{Ishikawa:2018jee, PACS:2019ofv}. The topological distribution, the PCAC masses, and decay constants for pseudo-scalar mesons are studied. As for the scale setting, we utilize the $Ω$ baryon mass as a reference scale and carefully investigate the operator dependence of the correlation function. As a result, we obtain $a^{-1}=2338.8(1.5)^{+0.2}_{-3.3} \ [{\rm MeV}]$ as a lattice cutoff. Our hadron spectra in the physical unit reproduce well the experimental results.

Data from High Energy Physics (HEP) experiments are collected with significant financial and human effort and are mostly unique. An inter-experimental study group on HEP data preservation and long-term analysis was convened as a panel of the International Committee for Future Accelerators (ICFA). The group was formed by large collider-based experiments and investigated the technical and organizational aspects of HEP data preservation. An intermediate report was released in November 2009 addressing the general issues of data preservation in HEP and an extended blueprint paper was published in 2012. In July 2014 the DPHEP collaboration was formed as a result of the signature of the Collaboration Agreement by seven large funding agencies (others have since joined or are in the process of acquisition) and in June 2015 the first DPHEP Collaboration Workshop and Collaboration Board meeting took place. This status report of the DPHEP collaboration details the progress during the period from 2013 to 2015 inclusive.

The new field of gravitational wave astrophysics requires a growing pool of students and researchers with unique, interdisciplinary skill sets. It also offers an opportunity to build a diverse, inclusive astronomy community from the ground up. We describe the efforts used by the North American Nanohertz Observatory for Gravitational Waves (NANOGrav) NSF Physics Frontiers Center to foster such growth by involving students at all levels in low-frequency gravitational wave astrophysics with pulsar timing arrays (PTAs) and establishing collaboration policies that ensure broad participation by diverse groups. We describe and illustrate the impact of these techniques on our collaboration as a case study for other distributed collaborations.

Human-AI collaboration (HAIC) in decision-making aims to create synergistic teaming between human decision-makers and AI systems. Learning to defer (L2D) has been presented as a promising framework to determine who among humans and AI should make which decisions in order to optimize the performance and fairness of the combined system. Nevertheless, L2D entails several often unfeasible requirements, such as the availability of predictions from humans for every instance or ground-truth labels that are independent from said humans. Furthermore, neither L2D nor alternative approaches tackle fundamental issues of deploying HAIC systems in real-world settings, such as capacity management or dealing with dynamic environments. In this paper, we aim to identify and review these and other limitations, pointing to where opportunities for future research in HAIC may lie.