Workspaces

Complex robotic manipulation tasks frequently require a long-term memory of past events and actions. As conditioning on full histories renders policies prone to spurious correlations and degrades performance, many approaches to policy memory involve compressing historical information through expensive VLM queries in-the-loop to process only task-salient information. In this paper, we propose an alternative approach in which computationally intensive VLM queries are made during train-time to learn a lightweight latent memory that can be efficiently queried at deployment time. Our representation, which we call the \textbf{workspace token}, is trained by (1) using a VLM to identify current and historical information necessary for completing a task, then (2) distilling these into the workspace token using a set-reconstruction decoder loss. In both simulation and hardware, we show that the workspace token can be used as a drop-in replacement for observations during deployment, enabling policies to solve memory-intensive tasks without the need for VLM reasoning in-the-loop. Interestingly, we found that workspace tokens are not only more lightweight but also lead to better policy performance.

Multimedia applications require precise music annotation-labeled positions, segments, or loops-placed by hand or algorithmically. Machine-learning algorithms are scalable and effective but need annotated training data, scarce for many tasks. TimeCues Studio is an open-source workspace where algorithm-development teams annotate a music corpus, compare detection algorithms against those annotations, and prototype new ones. Unlike existing tools built for a single track at a time, TimeCues targets teams annotating whole collections, tightly integrated with algorithm development. Annotators place several marker types-each supporting ambiguity-aware labeling-on a grid-locked timeline that visualizes many music features, including separated audio stems. The same timeline drives an algorithm-comparison engine with bundled baselines, a Python sandbox for prototyping new models, and an ambiguity-aware evaluator that honors the structured fields. The same visualization suits solo annotators on music-sync projects. TimeCues is MIT-licensed and deploys via one Docker Compose command.

Workspace analysis measures where a robot can place its end effector. For visually guided manipulation, reachability alone is insufficient: a kinematically reachable target may not be visible in the specific pose required to reach it. The robot must then redirect its sensing or move its body to acquire a view, turning a perception limitation into additional motion. Existing humanoids largely inherit this limitation when copying human form factors. We introduce the visible-reachable workspace (VRW), a design-stage measure that conditions visibility on feasible reaching configurations and extends it to concurrent visibility of spatially separated work regions. We apply VRW by building a 31-DoF humanoid with independently actuated RGB-D cameras. On the same robot, camera articulation increases visible-reachable coverage from 38% to 97%. With actuated camera layouts, a second camera raises pairwise coverage from 0.45 to 0.95, while a third changes it only to 0.97. In a controlled two-target reach-and-grasp benchmark, our dual-actuated design reduces mean completion time by 17% and mechanical energy by 19% relative to the same robot with its cameras fixed. Hardware experiments demonstrate simultaneous observation and manipulation of front/back and left/right target pairs without torso reorientation. The results suggest that reachability becomes a more informative design quantity for perception-driven humanoid manipulation when it is evaluated together with the sensing configurations that make the reachable space observable. We will open-source all software and the humanoid hardware design. Our website is https://generalroboticslab.com/DukeHumanoidv2

Agentic systems persist model-visible memory while mutating workspaces, while a runtime, registry, or approval service may hold authority state outside both. Identical final files can then require opposite safe actions. We call this the cross-substrate authority gap: decision- relevant authorization information resides outside the planner-visible workspace or memory state. Across two controlled mini-benchmark families, three experiments compare planner-observation augmentation with an execution-time authority check using real Git lineage, durably recorded agent execution attempts, deterministic oracles, and two model routes. Experiment 1 is a 128-cell controlled evidence ablation: authority-blind candidate evidence obtains 0/32 final semantic success, while raw receipts and a typed relation both obtain 32/32. The missing authority fact accounts for the gain; typed packaging provides no observed planning-accuracy gain over equal raw information. Experiment 2 uses 96 planning calls: workspace-visible evidence yields 12/16 unsafe publication decisions, and planning with the typed relation remains unreliable (15/32 first actions correct; 11/32 invalid or absent). Experiment 3 replays the same 32 fixed model-generated first-action intents with zero additional model calls; a deterministic execution guard prevents all six unsafe intents from becoming effects and permits all 12 valid authorized publish intents. These results position authority enforcement at the mutation boundary as the operational endpoint of memory governance.

Search agents now answer questions that take dozens of searches to settle, yet how such an agent reads a page has drawn far less attention than how it finds one. Nearly all of them use one of two document interfaces, and both tie a page to the moment it is opened. \emph{Visit-and-read} injects a reading of the page into the message history at fetch time, fixing that reading before the agent knows which fact it will need. Stateful \emph{browsing} instead extracts on demand from the page in hand, but holds one page at a time and releases it as soon as the agent opens another. Either way, a page that turns out to matter many turns later has to be fetched and rendered into context all over again. We propose \textbf{Fetch-then-Explore}, which separates page selection from evidence extraction and keeps what it selects: pages are recorded in a per-question workspace on the filesystem rather than the context window or a transient session, and evidence is pulled from them on demand later. Selection becomes almost free, extraction can wait until the agent knows what to look for and be repeated as its hypothesis sharpens, and pages are not released when the agent moves on, so evidence accumulates across the trajectory. In a unified ReAct harness with fixed search, we compare Fetch-then-Explore against snippet-only, visit-and-read, and browsing baselines on two open-web benchmarks, BrowseComp and WideSearch, across three agent backbones. It leads BrowseComp accuracy at every backbone and generally matches or exceeds the baselines on WideSearch, and a behavioral analysis traces the gains to the workspace's defining move: returning to a page after leaving it, which it does far more than any transient interface, so evidence missed on a first pass can still be recovered later.

Enterprise agents often need to integrate heterogeneous knowledge sources: documents for narrative facts, tables for computation, and dependency graphs for file relationships. Existing benchmarks typically evaluate retrieval or tool use without distinguishing whether an agent first selects the appropriate knowledge sources. We introduce WorkSurface-Bench, a benchmark for evaluating this capability as surface routing. It contains 1,151 atomic tasks derived from persona-scoped Workspace-Bench-Lite workspaces, spanning document, table, graph, and cross-surface questions. Its reference answers are auditable: table answers are reproduced through executed DuckDB queries, document answers are grounded in verified text spans, and graph answers are traced to source dependency annotations. We evaluate four model backbones across six controlled agent settings, yielding 27,624 protocol-error-free trajectories. Under gold-constrained tool access, agents achieve 98.7-99.8 Route F1, while Answer remains only 56.1-75.3 percent, showing that correct surface selection is necessary but insufficient for task completion. Matched interventions further show that surface hints improve Answer for three of four models, whereas removing irrelevant tools primarily improves routing and efficiency. In an independent three-annotator audit, all 200 sampled tasks pass all six quality criteria by majority vote, with 192 receiving unanimous judgments on every criterion. We release the dataset, construction pipeline, scoring code, and agent harness at https://github.com/haolpku/WorkSurface-Bench.

Safety inflation can cause nearby obstacles to overlap, violating the disjoint-obstacle assumptions used by many modulation-based reactive planners. We investigate Star-World workspace reshaping for three-dimensional reactive control of a Franka Emika Panda manipulator. At each update, intersecting inflated obstacles are clustered and replaced by star-shaped proxies before a dynamical-system-based end-effector controller is evaluated. A null-space artificial-potential-field term provides complementary arm-body avoidance. We compare reshaped and unreshaped obstacle representations in six PyBullet scenarios using goal attainment, path-length ratio, and computation time. In this preliminary 12-trial evaluation, reshaping reaches the goal in five of six scenarios, compared with four of six for the unreshaped baseline. It resolves the canonical overlapping-wall case and requires 0.68--8.70,ms per workspace update for scenes containing one to seven obstacles. However, it also increases path length, produces near-equilibria in two cases, and closes a navigable corridor through over-aggressive merging. These results show both the promise and the practical limitations of transferring Star-World guarantees from workspace geometry to a redundant manipulator controlled through inverse kinematics.

Large Language Model (LLM) agents have significantly improved coding and programming workflows. Claude Code, in particular, is one of the most powerful LLM coding agents and is capable of conducting complex coding tasks. However, several drawbacks can undermine long-term agentic workflows. (1) Irrecoverable agent teams: The Agent Teams feature is powerful, but the working state accumulated by each teammate is lost and cannot be resumed once the process stops, for example, when a terminal is closed. (2) Compaction erodes working detail: Compaction condenses the conversation into a summary, causing an agent's working details to become vague. (3) Agentic "technical debt": Over time, a user's decisions and the agents' operations become trapped in compacted old chats, making the project increasingly difficult to maintain and review. (4) Heavy prompt writing: Assigning or handing off tasks requires users to repeatedly write long prompts to achieve the expected agentic performance. We propose ATWZ (Agent Team Work Zone), a filesystem-based operations layer built around Claude Code's native Agent Teams that addresses these problems. Its central design principle is to treat each agent and teammate as a human employee and preserve their important working state in files stored in a dedicated directory called a "workstation," together with the skills, hooks, and scripts that use and maintain these files. With ATWZ, an agent team can periodically back up its working state, allowing an agent's knowledge to be recovered after compaction. After a process ends, the team can be restored with a single command. These features also substantially mitigate the agentic "technical debt" described above. Moreover, within ATWZ, agent "employees" can send documents to one another, greatly reducing the effort required to write prompts.

Coverage path planning (CPP) is a fundamental problem in robot motion planning, whose aim is to produce robot trajectories that provide complete coverage of target workspaces while minimizing task-specific objectives such as path length, overlap, number of turns, and energy consumption. CPP has widespread applications in cleaning, inspection, mapping, agriculture, manufacturing, surveillance, demining, and environmental monitoring. Although classical CPP has been extensively studied, recent advances have extended CPP beyond single-robot settings to multi-robot systems, complex 3D environments, constrained platforms, learning-based coverage planning, and visual coverage tasks. This paper presents a comprehensive survey of 125 representative works published primarily between 2015 and 2026, while presenting the evolution of recent developments in light of the classical CPP methods published before 2015. The CPP methods are organized into six main categories: single-robot CPP, multi-robot CPP, 3D CPP, constrained CPP, learning-based CPP, and visual CPP. For each category, the review summarizes the main planning formulations, representative algorithms, strengths, and limitations. In addition, the review analyzes how environmental knowledge, workspace geometry, robot constraints, sensing objectives, and coordination requirements shape the CPP problem. The survey further discusses open challenges in scalable online planning, multi-robot coordination, 3D and visual coverage, unified platform-constrained and resource-aware coverage, and learning-enhanced coverage. Thus, the survey provides a structured overview of recent CPP developments and future research directions.

Modern local and agentic workloads often need large-model capacity at low concurrency, but run on GPUs that cannot keep a frontier-scale model resident. Mixture-of-Experts (MoE) models are a natural fit because they activate only a small subset of experts per token, but their sparsity saves computation, not residency: the full expert pool still has to be stored, and any expert used by a layer must be in GPU memory when that layer runs. Static layer-level CPU offload makes such models fit, but transfers the expert layer in bulk on every forward pass, losing much of the sparsity advantage. We view low-resource MoE serving as a working-set problem on the GPU. Routed expert weights and the KV cache are two memory-demand streams competing for the same limited VRAM. We implement this view in WiSP (Working-Set Paging), a routing-aware expert pager that plugs into an unmodified serving engine and preserves byte-identical outputs. On a real 24 GiB RTX 3090, WiSP achieves up to 2.0x the decode throughput of static offload at the same memory budget when the model does not fit. A natural next step is to predict future experts and prefetch them. We find that this does not help in single-stream decode: the bottleneck is PCIe bandwidth, not prediction quality, so speculative transfers compete with demand transfers instead of hiding them. This shifts the design question from prefetching to allocation: how should one VRAM budget be divided between resident experts and the KV cache? We answer with MV-WSA (Marginal-Value Working-Set Allocation), which splits memory by marginal latency benefit per byte while enforcing a KV-admission floor. As a startup configurator, MV-WSA is the only policy we test that stays near-best on both prefill and decode; as a live controller, it resizes both pools while serving and reduces end-to-end time by up to 1.19x over a fixed offline split, without changing model outputs.

Agentic search over large corpora relies on retriever-mediated interfaces (e.g., BM25 or ColBERT) for scalable candidate discovery. While effective at ranking relevant documents, these interfaces expose evidence only as ranked results or bounded document views, limiting agents' ability to reorganize material and verify constraints across documents. Direct Corpus Interaction (DCI) addresses this limitation by exposing shell-executable corpus operations for flexible search, filtering, comparison, and verification. However, full-corpus terminal commands become slow and unstable as the corpus grows, degrading performance and efficiency. We introduce DR-DCI, a retriever-steered DCI framework that treats retrieval as an agent-callable action for expanding a local workspace. Rather than operating directly over the full corpus, the agent dynamically pulls relevant documents into an evolving workspace and conducts DCI operations within it. This design combines retriever-level recall with DCI-style precision: retrieval keeps exploration scalable, while DCI preserves the local operations needed for effective evidence resolution. Experiments show that DR-DCI is both effective and efficient across scales. On Browsecomp-Plus, DR-DCI reaches 71.2% accuracy, improving over raw DCI and ablated variants by up to 8.3 points while reducing tool usage, wall time, and estimated cost. With workspace-preserving context reset, accuracy further improves to 73.3%. In corpus-scaling experiments, DR-DCI remains effective from 100K to 10M documents, whereas raw DCI becomes unstable and BM25 performs substantially worse. DR-DCI also scales to a 20M-scale file-per-document Wiki-18 QA setting, achieving an average score of 63.0 across six benchmarks and outperforming retrieval-based and trained search-agent baselines. Ablation analysis further shows that ranked previews and inter-document DCI are key to performance.

For a humanoid robot to be deployed in the real world, the choice of command space (i.e., the interface between task planning and whole-body control) is crucial. Existing whole-body controllers typically demand dense kinematic or spatial references that planners struggle to synthesize from task semantics. We instead propose a compact, explicit interface that is intuitive, general, modular, and expressive enough for diverse loco-manipulation skills. To this end, we introduce HANDOFF, a single humanoid whole-body controller that follows this interface and is distilled via multi-teacher KL distillation under a context-conditioned gating scheme into a mixture-of-experts student from three complementary specialists: whole-body motion tracking with safety-filtered data, locomotion, and fall-recovery. On the Unitree G1, HANDOFF matches state-of-the-art velocity tracking and offers one of the largest robust manipulation workspaces. We further demonstrate hardware feasibility through multiple natural-language-driven task roll-outs, powered by a VLM-driven agentic planner with no task-specific data or controller fine-tuning.

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.

Computer-use agents increasingly operate inside live personal workspaces, where their actions can modify files, applications, GUI state, credentials, and authenticated sessions. This creates a tension between safety and quality: agents need isolation and rollback to avoid damaging user state, but also need fast branching to support speculative execution and parallel search. Existing VMs, containers, and checkpoint/restore systems can isolate or recover workloads, but they do not provide low-latency versioning of a full interactive workspace. We present TClone, a forkable personal workspace system for computer-use agents. TClone enables a live GUI workspace to be snapshotted, forked into isolated branches, rolled back, and selectively committed or merged. Its design separates fast branch creation from durable checkpointing, using sibling containers, copy-on-write memory sharing, filesystem versioning, GUI-local execution, and asynchronous checkpointing. In our end-to-end agent-loop measurement, TClone reduces total task latency by 1.9x and 1.5x over KVM and CRIU. By making workspace versioning a first-class systems primitive, TClone supports safer and higher-quality agent execution over real personal computing environments.

This paper proposes a cell decomposition algorithm for binary occupancy grids that ensures mutual complete visibility from each cell to at least one adjacent cell. This decomposition establishes a simplified framework for verifying path feasibility that can be easily embedded in optimization problems. To illustrate its utility, we formulate both second-order cone programs (SOCP) and their mixed-integer variant (MISOCP) within the proposed framework. Furthermore, we propose the KSP-SOCP method, which combines Yen's k-shortest path algorithm with the SOCP, achieving improved solutions compared to a standard SOCP approach while avoiding the computational burden of MISOCP. The cell decomposition algorithm, KSP-SOCP, and MISOCP approaches were evaluated in 9 city-like workspaces. The decomposition efficiently partitioned each map, enabling both optimization methods to compute feasible paths. The proposed KSP-SOCP achieved time performance comparable to the MISOCP while requiring less memory, making it highly suitable for large-scale problems.

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.

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 only about 60%, substantially below the human result of 80.7%, and the average performance across agents is only 43.3%.

LLM agents are expected to complete end-to-end units of work across software tools, business services, and local workspaces. Yet many agent benchmarks freeze a curated task set at release time and grade mainly the final response, making it difficult to evaluate agents against evolving workflow demand or verify whether a task was executed. We introduce Claw-Eval-Live, a live benchmark for workflow agents that separates a refreshable signal layer, updated across releases from public workflow-demand signals, from a reproducible, time-stamped release snapshot. Each release is constructed from public workflow-demand signals, with ClawHub Top-500 skills used in the current release, and materialized as controlled tasks with fixed fixtures, services, workspaces, and graders. For grading, Claw-Eval-Live records execution traces, audit logs, service state, and post-run workspace artifacts, using deterministic checks when evidence is sufficient and structured LLM judging only for semantic dimensions. The release contains 105 tasks spanning controlled business services and local workspace repair, and evaluates 13 frontier models under a shared public pass rule. Experiments reveal that reliable workflow automation remains far from solved: the leading model passes only 66.7% of tasks and no model reaches 70%. Failures are structured by task family and execution surface, with HR, management, and multi-system business workflows as persistent bottlenecks and local workspace repair comparatively easier but unsaturated. Leaderboard rank alone is insufficient because models with similar pass rates can diverge in overall completion, and task-level discrimination concentrates in a middle band of tasks. Claw-Eval-Live suggests that workflow-agent evaluation should be grounded twice, in fresh external demand and in verifiable agent action.

Evaluating the pinch capability of a robotic hand is important for understanding its functional dexterity. However, many existing grasp evaluation methods rely on object geometry or contact force models, which limits their applicability during the early stages of robotic hand design. This study proposes a kinematic evaluation method for analyzing pinch configurations of robotic hands based on interactions between fingertip workspaces. First, the reachable workspace of each fingertip is computed from the joint configurations of the fingers. Then, feasible pinch configurations are detected by evaluating the relationships between fingertip pairs. Since the proposed method does not require information about object geometry or contact force models, the pinch capability of a robotic hand can be evaluated solely based on its kinematic structure. In addition, analyses are performed on four different kinematic structures of the hand to investigate their impact on the pinch configurations. The proposed evaluation framework can serve as a useful tool for comparing different robotic hand designs and analyzing pinch capability during the design stage.

Developing Visual Analytics (VA) applications requires integrating complex machine learning models with expressive interactive interfaces. Developers face a stark trade-off: building tightly-coupled monoliths plagued by fragile interdependencies, or relying on restrictive, simplistic frameworks. Meanwhile, unconstrained, single-shot AI code generation promises speed but yields unstructured, unauditable chaos. The core challenge is combining the control and expressiveness of custom development with the efficiency of AI generation under strict constraints. To address this, we introduce BONSAI, a mixed-initiative workspace for the multi-agent co-development of VA applications. BONSAI utilizes a modular four-layer architecture (hardware, services, orchestration, application) that allows human and AI developers to independently contribute reusable components. The workspace incorporates this architecture into a structured four-phase development process (plan, design, monitor, and review), ensuring distributed agency and full provenance, where all human and AI contributions are structurally bounded and tracked. We evaluate BONSAI through case studies demonstrating the efficient creation of novel tools and the rapid reconstruction of complex VA applications directly from research paper descriptions. Ultimately, this paper contributes a conceptual workflow, a scalable architecture, and an integrated system that successfully balances AI's generative speed with the structural rigor required for complex VA development.

Generalizable grasping with high-degree-of-freedom (DoF) dexterous hands remains challenging in tiered workspaces, where occlusion, narrow clearances, and height-dependent constraints are substantially stronger than in open tabletop scenes. Most existing methods are evaluated in relatively unoccluded settings and typically do not explicitly model the distinct control requirements of arm navigation and hand articulation under spatial constraints. We present SpaceDex, a hierarchical framework for dexterous manipulation in constrained 3D environments. At the high level, a Vision-Language Model (VLM) planner parses user intent, reasons about occlusion and height relations across multiple camera views, and generates target bounding boxes for zero-shot segmentation and mask tracking. This stage provides structured spatial guidance for downstream control instead of relying on single-view target selection. At the low level, we introduce an arm-hand Feature Separation Network that decouples global trajectory control for the arm from geometry-aware grasp mode selection for the hand, reducing feature interference between reaching and grasping objectives. The controller further integrates multi-view perception, fingertip tactile sensing, and a small set of recovery demonstrations to improve robustness to partial observability and off-nominal contacts. In 100 real-world trials involving over 30 unseen objects across four categories, SpaceDex achieves a 63.0% success rate, compared with 39.0% for a strong tabletop baseline. These results indicate that combining hierarchical spatial planning with arm-hand representation decoupling improves dexterous grasping performance in spatially constrained environments.