Workspace learning requires AI agents to identify, reason over, exploit, and update explicit and implicit dependencies among heterogeneous files in a worker's workspace, enabling them to complete both routine and advanced tasks effectively. Despite its importance, existing relevant benchmarks largely evaluate agents on pre-specified or synthesized files with limited real-world dependencies, leaving workspace-level evaluation underexplored. To this end, we introduce Workspace-Bench, a benchmark for evaluating AI agents on Workspace Learning involving Large-Scale File Dependencies. We construct realistic workspaces with 5 worker profiles, 74 file types, 20,476 files (up to 20GB) and curate 388 tasks, each with its own file dependency graph, evaluated across 7,399 total rubrics that require cross-file retrieval, contextual reasoning, and adaptive decision-making. We further provide Workspace-Bench-Lite, a 100-task subset that preserves the benchmark distribution while reducing evaluation costs by about 70%. We evaluate 4 popular agent harnesses and 7 foundation models. Experimental results show that current agents remain far from reliable workspace learning, where the best reaches onl
Nowadays team workspaces are widely adopted for multi-user collaboration and digital resource management. To further broaden real-world applications, mainstream team workspaces platforms, such as Google Workspace and Microsoft OneDrive, allow third-party applications (referred to as add-ons) to be integrated into their workspaces, significantly extending the functionality of team workspaces. The powerful multi-user collaboration capabilities and integration of add-ons make team workspaces a central hub for managing shared resources and protecting them against unauthorized access. Due to the collaboration features of team workspaces, add-ons involved in collaborations may bypass the permission isolation enforced by the administrator, unlike in single-user permission management. This paper aims to investigate the permission management landscape of team workspaces add-ons. To this end, we perform an in-depth analysis of the enforced access control mechanism inherent in this ecosystem, considering both multi-user and cross-app features. We identify three potential security risks that can be exploited to cause permission escalation. We then systematically reveal the landscape of permiss
Mixed Reality enables hybrid workspaces where physical and virtual monitors are adaptively created and moved to suit the current environment and needs. However, in shared settings, individual users' workspaces are rarely aligned and can vary significantly in the number of monitors, available physical space, and workspace layout, creating inconsistencies between workspaces which may cause confusion and reduce collaboration. We present Desk2Desk, an optimization-based approach for remote collaboration in which the hybrid workspaces of two collaborators are fully integrated to enable immersive side-by-side collaboration. The optimization adjusts each user's workspace in layout and number of shared monitors and creates a mapping between workspaces to handle inconsistencies between workspaces due to physical constraints (e.g. physical monitors). We show in a user study how our system adaptively merges dissimilar physical workspaces to enable immersive side-by-side collaboration, and demonstrate how an optimization-based approach can effectively address dissimilar physical layouts.
This paper focuses on the optimal design of a tendon-driven continuum robot (TDCR) based on its feasible static workspace (FSW). The TDCR under consideration is a two-segment robot driven by eight tendons, with four tendon actuators per segment. Tendon forces are treated as design variables, while the feasible static workspace (FSW) serves as the optimization objective. To determine the robot's feasible static workspace, a genetic algorithm optimization approach is employed to maximize a Euclidian norm of the TDCR's tip position over the workspace. During the simulations, the robot is subjected to external loads, including torques and forces. The results demonstrate the effectiveness of the proposed method in identifying optimal tendon forces to maximize the feasible static workspace, even under the influence of external forces and torques.
Modern agents built on frontier language models often cannot adapt their weights. What, then, remains trainable? We argue it is the agent's \emph{workspace}, the structured external substrate it reads, writes, and tests; we call its evolution workspace optimization. Workspace optimization targets hard multi-turn environments where a frontier model has strong priors but cannot solve the task in a single shot, so the agent must learn through interaction. We propose a principled way to evolve the workspace, mirroring the structure of weight-space training: artifacts in place of parameters, evidence in place of data, counterexamples in place of losses, and textual feedback in place of gradients. We instantiate the idea in DreamTeam, a multi-agent harness for ARC-AGI-3 whose roles build an executable world model, plan, hypothesize, probe, strategize, and route failures. On the current 25-game ARC-AGI-3 public set under the official scoring protocol and averaged over two independent runs, DreamTeam improves the SOTA protocol-matched agent's score from 36% to 38.4%, while using 31% fewer environment actions per game.
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.
Recent years have seen considerable work on compiling sparse tensor algebra expressions. This paper addresses a shortcoming in that work, namely how to generate efficient code (in time and space) that scatters values into a sparse result tensor. We address this shortcoming through a compiler design that generates code that uses sparse intermediate tensors (sparse workspaces) as efficient adapters between compute code that scatters and result tensors that do not support random insertion. Our compiler automatically detects sparse scattering behavior in tensor expressions and inserts necessary intermediate workspace tensors. We present an algorithm template for workspace insertion that is the backbone of our code generation algorithm. Our algorithm template is modular by design, supporting sparse workspaces that span multiple user-defined implementations. Our evaluation shows that sparse workspaces can be up to 27.12$\times$ faster than the dense workspaces of prior work. On the other hand, dense workspaces can be up to 7.58$\times$ faster than the sparse workspaces generated by our compiler in other situations, which motivates our compiler design that supports both. Our compiler prod
Large language model (LLM) agents are increasingly used to assist with operations research (OR) modeling, yet existing OR-oriented benchmarks often reduce evaluation to one-shot translation from a self-contained problem statement into a mathematical formulation or solver program. Such settings abstract away two characteristics of real industrial OR workflows: persistent multi-artifact workspaces and multi-stage task lifecycles. We introduce OR-Space, a full-lifecycle workspace benchmark for evaluating industrial optimization agents across model construction, model revision, and grounded explanation. Each instance is an executable workspace containing business documents, structured data, optional code artifacts, solver outputs, and task-specific evaluators distributed across interdependent files. OR-Space defines three task modes: Build, where agents construct solver-ready optimization models from heterogeneous artifacts; Revise, where agents modify existing models under changing requirements or solver feedback while preserving valid prior logic; and Explain, where agents answer grounded questions about solutions, constraints, and business implications using evidence spread across w
The workspace limits the operational capabilities and range of motion for the systems with robotic arms. Maximizing workspace utilization has the potential to provide more optimal solutions for aerial manipulation tasks, increasing the system's flexibility and operational efficiency. In this paper, we introduce a novel planning framework for aerial grasping that maximizes workspace utilization. We formulate an optimization problem to optimize the aerial manipulator's trajectory, incorporating task constraints to achieve efficient manipulation. To address the challenge of incorporating the delta arm's non-convex workspace into optimization constraints, we leverage a Multilayer Perceptron (MLP) to map position points to feasibility probabilities.Furthermore, we employ Reversible Residual Networks (RevNet) to approximate the complex forward kinematics of the delta arm, utilizing efficient model gradients to eliminate workspace constraints. We validate our methods in simulations and real-world experiments to demonstrate their effectiveness.
Supernumerary robotic limbs (SRLs) offer substantial potential in both the rehabilitation of hemiplegic patients and the enhancement of functional capabilities for healthy individuals. Designing a general-purpose SRL device is inherently challenging, particularly when developing a unified theoretical framework that meets the diverse functional requirements of both upper and lower limbs. In this paper, we propose a multi-objective optimization (MOO) design theory that integrates grasping workspace similarity, walking workspace similarity, braced force for sit-to-stand (STS) movements, and overall mass and inertia. A geometric vector quantification method is developed using an ellipsoid to represent the workspace, aiming to reduce computational complexity and address quantification challenges. The ellipsoid envelope transforms workspace points into ellipsoid attributes, providing a parametric description of the workspace. Furthermore, the STS static braced force assesses the effectiveness of force transmission. The overall mass and inertia restricts excessive link length. To facilitate rapid and stable convergence of the model to high-dimensional irregular Pareto fronts, we introduce
We present a kinematic and transmission-aware design framework for a serial spherical mechanism with an additional translational degree of freedom for microsurgery. The first contribution is an analytical workspace formulation that provides geometric insight into reachable motion and enables rapid selection of rotation axis orientations without numerical optimization. The second contribution is a dynamics-informed methodology for mechanisms driven by self-locking transmissions, supporting evaluation of torque requirements for a prescribed workspace geometry. The framework is accompanied by an open-source software package for friction identification and inverse dynamics analysis. Experiments on a purpose-built robotic tool for vitreoretinal surgery validate the predictive capability of the models and demonstrate their practical utility for engineering design.
Group mood plays a crucial role in shaping workspace experiences, influencing group dynamics, team performance, and creativity. The perceived group mood depends on many, often subconscious, aspects such as individual emotional states or group life, which make it challenging to maintain a positive atmosphere. Intelligent technology could support mood regulation in physical office environments, for example, as adaptive ambient lighting for mood regulation. However, little is known about the relationship between the physical workspace and group mood dynamics. To address this knowledge gap, we conducted a qualitative user study (N=8 workgroups and overall 26 participants) to explore how the physical workspace shapes group mood experiences and investigate employees' perspectives on intelligent mood-aware technologies. Our findings reveal key factors influencing group mood, and participants' expectations for supportive technology to preserve privacy and autonomy. Our work highlights the potential of adaptive and responsive workspaces while also emphasizing the need for human-centered, technology-driven interventions that benefit group well-being.
Electromagnetic navigation systems (eMNS) enable a number of magnetically guided surgical procedures. A challenge in magnetically manipulating surgical tools is that the effective workspace of an eMNS is often severely constrained by power and thermal limits. We show that system-level control design significantly expands this workspace by reducing the currents needed to achieve a desired motion. We identified five key system approaches that enable this expansion: (i) motion-centric torque/force objectives, (ii) energy-optimal current allocation, (iii) real-time pose estimation, (iv) dynamic feedback, and (v) high-bandwidth eMNS components. As a result, we stabilize a 3D inverted pendulum on an eight-coil OctoMag eMNS with significantly lower currents (0.1-0.2 A vs. 8-14 A), by replacing a field-centric field-alignment strategy with a motion-centric torque/force-based approach. We generalize to multi-agent control by simultaneously stabilizing two inverted pendulums within a shared workspace, exploiting magnetic-field nonlinearity and coil redundancy for independent actuation. A structured analysis compares the electromagnetic workspaces of both paradigms and examines current-alloca
Robust multimodal systems must remain effective when some modalities are noisy, degraded, or unreliable. Existing multimodal fusion methods often learn modality selection jointly with representation learning, making it difficult to determine whether robustness comes from the selector itself or from full end-to-end co-adaptation. Motivated by Global Workspace Theory (GWT), we study this question using a lightweight top-down modality selector operating on top of a frozen multimodal global workspace. We evaluate our method on two multimodal datasets of increasing complexity: Simple Shapes and MM-IMDb 1.0, under structured modality corruptions. The selector improves robustness while using far fewer trainable parameters than end-to-end attention baselines, and the learned selection strategy transfers better across downstream tasks, corruption regimes, and even to a previously unseen modality. Beyond explicit corruption settings, on the MM-IMDb 1.0 benchmark, we show that the same mechanism improves the global workspace over its no-attention counterpart and yields decent benchmark performance.
This study investigates the effectiveness of Google Workspace in fostering collaboration within academic settings, specifically at the University of Makati. The aim is to evaluate its role in enhancing blended learning practices and identify areas for improvement among faculty, staff, and students. A survey was conducted with 50 participants, including academic staff, faculty, and students at the University of Makati who regularly use Google Workspace for academic and collaborative activities. Participants were selected through purposive sampling to ensure familiarity with the platform. The study employed a quantitative research design using structured surveys to assess user experiences with key features such as real-time document editing, communication tools, etc. The study found that Google Workspace and rated as "Very Effective" (mean score of 4.61) in promoting teamwork. Key advantages included improved collaboration, enhanced communication, and efficient management of group projects. However, several challenges were also noted, including low user adoption rates, limited Google Drive storage capacity, the need for better technical support, and limited offline functionality. Goo
A fundamental challenge in multi-robot motion planning is achieving sufficient coordination to avoid inter-robot conflicts without incurring the large computational expense of searching the joint configuration space of the robot group. In this work, we present a method for multiple mobile robot motion planning that achieves an improvement in planning time up to an order of magnitude by leveraging the insight that we can use discrete search over a workspace decomposition to provide coordination between robots during planning. While prior work uses workspace topology to inform when coordination between robots is needed and then composes robots into their joint configuration space, we take a step further by iteratively refining our workspace representation to allow our planner to search smaller, decoupled configuration spaces.
To enhance workspace awareness for mixed-presence meetings with large displays, previous work propose digital cues to share gestures, gaze, or entire postures. While such cues were demonstrated useful in horizontal or smaller workspaces, efforts have focused on isolated elements in controlled settings. It is unknown what needs would emerge with a more realistic setting and how they could be addressed with workspace awareness cues. In this paper, we report on the results of a focus group, centred around users' perceptions while testing a mixed-presence scenario on wall-sized displays. We analyse the gathered comments using Gutwin and Greenberg's workspace awareness framework to identify the most relevant needs. Our results lead to a refinement of the original framework for wall-sized displays and in particular to a categorization into three types of workspace awareness components (i) the Environment, (ii) Actions and (iii) Attention.
This article presents a method for computing the largest singularity-free sphere (SFS) of a 6-6 Stewart-Gough platform manipulator (SGPM) over a specified orientation workspace. For a fixed orientation of the moving platform, the SFS is computed analytically. This process is repeated over a set of samples generated within the orientation workspace, and the smallest among them is designated as the desired SFS for the given orientation workspace. Numerical experiments are performed on four distinct architectures of the SGPM to understand their relative performances w.r.t. SFS volumes over the same orientation workspace. This study demonstrates the potential utility of the proposed computational method both in analysis and design of SGPMs.
Large Language Models (LLMs) have been widely applied in summarization due to their speedy and high-quality text generation. Summarization for sensemaking involves information compression and insight extraction. Human guidance in sensemaking tasks can prioritize and cluster relevant information for LLMs. However, users must translate their cognitive thinking into natural language to communicate with LLMs. Can we use more readable and operable visual representations to guide the summarization process for sensemaking? Therefore, we propose introducing an intermediate step--a schematic visual workspace for human sensemaking--before the LLM generation to steer and refine the summarization process. We conduct a series of proof-of-concept experiments to investigate the potential for enhancing the summarization by GPT-4 through visual workspaces. Leveraging a textual sensemaking dataset with a ground truth summary, we evaluate the impact of a human-generated visual workspace on LLM-generated summarization of the dataset and assess the effectiveness of space-steered summarization. We categorize several types of extractable information from typical human workspaces that can be injected into
We present a model inspired by the Global Workspace Theory that integrates specialized modules to perform a sequential reasoning task. A controller selectively routes information between modules through the workspace using a gating mechanism. This approach allows the model to chain operations by iteratively broadcasting information between specialized domains, mimicking System-2 reasoning. We evaluate the model's performance on a simple addition task, where two addends must be summed. The task can be solved by routing information sequentially through an Input module, an Increment module (multiple times), and finally an Output module. We consider two implementations of this system with increasing complexity. First, using hand-designed modules operating on one-hot digit representations, the controller (a LSTM recurrent network) learns to select the appropriate modules (input, increment, output) in the appropriate sequence. Second, we replace the hand-designed modules with learned representation modules for MNIST images and an increment module trained on the task objectives; here again, the controller learns the appropriate sequential module selection to solve the task. Finally, we sh