已审阅并标注「长任务」的研究与资产。
条目依据已审阅标签归类，同一主题不表示资源之间存在依赖关系。日期保留来源精度，注释保留原语言。
WildAWM synthesizes resettable GUI/MCP/CLI environments and cross-interface tasks, using execution-based checks of solvability, difficulty and verifier consistency before supervised and reinforcement learning.
ECHOES learns recursive textual task memory through privileged screenshot-history distillation and GRPO, then predicts GUI actions from the current screenshot and memory.
Introduces CarryOn, which maintains evidence-linked task objects and remaining-work context across history compression, with evaluations on desktop tasks and web research.
Synthesizes resettable workspaces with files, application observations and skills; repairs environment incompatibilities and trains long-task agents using verifier-linked turn credit.
Groups GUI trajectories by subgoal and combines action-level and group-level assessments into intermediate rewards for training agents with sparse task outcomes.
Introduces AgentHorizon, a benchmark for judging long computer-use trajectories using closely related instructions paired with recorded actions and screenshots. It tests whether judges can detect constraint violations and distinguish successful tasks from similar but incompatible requests.
Introduces AMBER, an append-only memory framework in which a web agent learns to reason, act, and retain evidence using outcome-reward reinforcement learning. It studies whether preserving entries avoids the loss of facts and corrective feedback seen with rewritten memory.
Presents PrecogUI, which retrieves prior anomaly and success patterns and predicts symbolic UI transitions before choosing actions. It also introduces InterfereBench, generated for evaluating long GUI workflows with disruptive events and recovery requirements.
LongPuzzleBench evaluates coherent long-horizon planning on persistent visual puzzle boards through native GUI actions. It compares GUI-only and code-assisted agents and uses controlled hints and memory diagnostics to examine decisions that preserve or eliminate future solutions.
KNOWS benchmarks browser workflows that retrieve and synthesize information into documents, presentations and spreadsheets. Task-specific evaluators combine deterministic checks with model judgments, distinguishing partial progress from usable end-to-end artifact completion.
EvoSkill-GUI revises reusable skill files from execution feedback through an executor–critic loop. It studies how training-free updates to localization, recovery and procedure information help subsequent mobile and desktop tasks.
CADWorld evaluates screenshot-and-GUI agents on long FreeCAD workflows, from modeling and assembly to manufacturing and simulation. Executable checks inspect saved engineering artifacts for geometry, constraints, construction structure and downstream state.
JarvisGUI composes typed input-output task transformations into dynamic workflows spanning Android, Windows and Ubuntu devices. Its virtual-environment benchmark tests transfer of intermediate results, shared state and cross-device dependencies.
Introduces GUI-CC, a benchmark for assessing GUI world models as multi-step agent environments. Separate reference-action and agent-loop tracks test whether generated screens preserve context, plausible transitions, and task progress throughout interaction.
Introduces CausalCache, which selects archived screenshots to restore alongside text summaries under a fixed visual-memory budget. A history-gated adapter processes restored images, with evaluation distinguishing standard step limits from longer-horizon and mobile-transfer settings.
Combines a browser execution framework, recovery-oriented supervision, and online reinforcement learning, with a bilingual live-web task benchmark.
Combines environment-grounded training with demonstration-conditioned workflows, and introduces OSWorkerBench for extended office-task evaluation.
DSAgentBench evaluates end-to-end data-science workflows spanning analysis, modeling and visualization inside a real desktop environment. Task evaluators check produced analytical and visual artifacts, while the released interface supports screenshot or accessibility observations and GUI actions.
Qwen-CUA operates through screenshots and keyboard/mouse events while compressing older visual history into reusable context blocks. Its report combines verifiable task generation, trajectory-based training and separate browser and Bash-augmented studies.
Describes a foundation GUI agent with combined GUI and command-line actions, large-scale interaction infrastructure, and iterative environment and task generation.
Introduces StateAct, a code-first computer-use harness that manipulates program state directly and delegates screenshot-and-click subgoals to a GUI agent. An independent completion gate checks saved outputs, while fresh subagents handle subgoals to limit accumulated context.
Introduces SEE, which first explores mobile interfaces to build a screen-and-element transition graph, then composes task trajectories through graph planning and controlled sampling. It studies coverage, loop avoidance, and transfer after training agents on the generated sequences.
Introduces Sidekick, a communication interface that uses ambient status cues, multimodal action summaries, and visual and verbal explanations of reasoning to help people monitor computer-use agents. A user study examines progress awareness, error traceability, and multitasking across background and foreground interaction.
Introduces ParaGUIBench, with tasks and efficiency measurements for coordinated GUI agents operating separate desktop instances over a shared file system. Its ParaGUI planner-worker system decomposes tasks and dispatches concurrent subtasks for comparison with serial execution.
StructAgent maintains compact task state and regulates long-horizon execution through verified transitions and progress checkpoints. Its workflow supports evidence-based completion and targeted recovery, with desktop computer-use evaluation and a separate Minecraft extension.
The Entry–Propagation–Recovery framework traces where conflicting memory first changes an agent action, how the effect propagates and whether recovery occurs. WebArena and the controlled MemTrapBench separate memory-consumption failures across these stages.
EvoCUA-1.5 trains multi-turn desktop agents through online reinforcement learning in executable sandboxes. It combines step-level policy optimization, task filtering and calibration, an adaptive curriculum, and asynchronous rollout handling with staleness control.
Introduces extended computer-use workflows with realistic artifacts, changing information, hidden state, and partial-progress and safety assessments.
ENVS branches over GUI actions in live desktop VMs, verifies successful leaves, and converts them into balanced step-level training supervision. It also introduces OSWorld-Noisy to test recovery from dynamic interruptions while retaining the underlying tasks.
ChainWorld composes compatible atomic OSWorld tasks into multi-objective desktop chains while preserving their evaluators. It compares giving the full sequence at once with revealing goals turn by turn, exposing different state and session-management failures.
MemGUI-Agent makes context management an action chosen by the same policy that controls the mobile UI. Structured history, UI-state and recent-step fields are trained from annotated trajectories to retain cross-app facts while limiting context growth.
VISUALSKILL organizes application-specific text and figures into hierarchical skills retrieved on demand through an MCP tool. Skills combine authored documentation with live UI exploration, and matched multimodal/text-only comparisons test their utility for interface identification and workflow-state verification.
LabOSBench evaluates GUI agents on browser-based scientific instrument simulators with configurable tasks and execution-based checks. Its subtask and end-to-end tests examine feedback-driven adjustment and long workflows without controlling physical instruments.
HiViG combines a compact history of completed actions with a visually grounded critic that checks proposed coordinates before execution. Its evaluations separate history-related planning failures from errors caused by targeting the wrong screen element.
Workflow-GYM evaluates long GUI workflows in professional software rather than isolated interface actions. Its analysis examines failures such as omitted stages, accumulated errors and goal drift during specialized end-to-end work.
WeaveBench requires agents to combine GUI, command-line and code operations within long tasks on an Ubuntu desktop. A trajectory-aware judge checks deliverables and interaction evidence, including shortcut behavior that outcome-only grading can miss.
Proposes Signal-Driven Observation: a separate call selects relevant DOM elements and selectors, and a detector requests new observations only after meaningful browser events or failures. The paper frames observation timing and compression as an architectural research problem for long-horizon web agents.
DeskCraft evaluates professional desktop workflows and human-agent collaboration through mid-execution clarification, interruption and post-completion feedback. Its tasks cover creative applications and expose difficulties in long-horizon execution and proactive clarification.
MACU represents computer-use objectives as a dependency graph whose manager dispatches parallel subagents and revises tasks as new information arrives. Desktop and web experiments examine coordination, information handoff and task-completion time.
AndroidDaily evaluates mobile GUI agents on daily workflows in closed-source Android apps. Its GRADE evaluator follows visual trajectories against operational obligations, output-quality requirements and negative constraints, producing process-level diagnostics without hidden app state.
Claw-Anything benchmarks persistent personal assistance across activity histories, backend services and integrated GUI/CLI interaction. Its simulated event histories introduce irrelevant or conflicting context, and a separate generation pipeline supplies training environments.
MementoGUI learns a controller for selecting, compressing and retrieving textual and region-level visual memories while leaving the GUI-agent backbone fixed. It also converts computer-use traces into controller training data and evaluates semantic actions, progress and memory consistency on long-horizon tasks.
SaaS-Bench evaluates browser agents on professional workflows across self-hosted applications. Weighted checkpoints measure task completion and partial progress, with application-state checks and configured content judges documented in the official harness.
Executable Agentic Memory stores GUI routines in a knowledge graph built through state-aware exploration and action-group mining. A learned value model guides tree search over this executable memory for retrieval-based planning, with AndroidWorld and efficiency evaluation.
Introduces Mem-W, which compresses previous trajectories and current-session segments into latent memory tokens used directly by the GUI policy. Self-distillation and outcome supervision train this memory representation for web and mobile navigation.
Proposes a step-level model cascade that runs a smaller computer-use policy until learned monitors flag stalled progress or semantic drift. Separate history-based stuck detection and milestone checks determine when to escalate for recovery or verification without retraining the larger model.
Introduces Odysseys, a live-web benchmark of long, multi-site tasks derived from browsing sessions. Graded task rubrics and a rubric-score-per-step measure evaluate both partial progress and trajectory efficiency.
WebUncertainty adapts planning mode to task uncertainty and guides action-level tree search with confidence-derived uncertainty estimates. Its evaluations examine autonomous execution of dynamic, long-horizon web tasks on WebArena and WebVoyager.
UI-Copilot separates GUI execution from on-demand memory retrieval and numerical assistance. Its training procedure treats tool selection and multi-turn task execution as distinct optimization targets while keeping persistent observations outside transient context.
Introduces Gym-Anything, where a setup agent configures software environments and an independent auditor checks the resulting evidence. CUA-World supplies long-horizon tasks across professional applications, with experiments on trajectory distillation and test-time auditing.
GUIDE evaluates GUI trajectories by segmenting them into subtasks, diagnosing each segment, and aggregating structured findings into a task verdict. It tests diagnostic judgments on e-commerce, web-agent and Android-control traces rather than relying on one holistic trajectory score.
Describes a web-trajectory verifier built around structured rubrics, separate process and outcome judgments, and explicit treatment of uncontrollable failures. CUAVerifierBench supplies human labels for evaluating these choices and screenshot-based context management.
CareFlow benchmarks long healthcare-software workflows, while CarePilot coordinates action proposals, execution checks and corrective feedback using short- and long-term memory. Its actor consumes visual interfaces and system state to select semantic actions.
The framework separates inference-time subgoal planning from MiRA, a reinforcement-learning method that supplies milestone rewards. WebArena-Lite experiments evaluate these mechanisms for long-horizon web navigation.
Introduces AndroTMem-Bench for Android tasks whose later actions depend on earlier UI states. Anchored State Memory retains causally linked intermediate states for subgoal-specific retrieval and evaluates them against full-history and summary-based memory.
MemoryArena links tasks across sessions so that agents must distill earlier interaction experience and use it in later decisions. Its evaluation includes web navigation alongside planning, search and formal reasoning, testing memory through subsequent actions rather than recall alone.
Darwinian Memory splits GUI trajectories into reusable units and updates the memory by retaining useful paths and pruning poor ones. It evaluates this training-free memory mechanism on long multi-application tasks.
BEAP-Agent treats GUI execution as depth-first search with coordinated planning, execution and task-state tracking. It supports backtracking across multiple levels of earlier states and evaluates recovery on OSWorld.
Introduces OS-Marathon to evaluate long repetitive computer-use workflows whose execution grows with the amount of input data. It studies failure accumulation under task decomposition and GraphDemo, which adapts agents using a demonstration of the recurring workflow.
EvoCUA combines task synthesis with executable validators, asynchronous sandbox rollouts and iterative policy updates. It turns successful routines and analyzed failures into supervision and evaluates the evolving agent on OSWorld.
第 1–60 条，共 105 条资源。
通过主题导出清单获取完整记录和证据。克隆目录后，可将主题记录直接交给标准 RAG 与引用导出工具。
