Graphical user interface (GUI) agents autonomously operate across platforms (e.g., Linux) to complete tasks by interacting with visual elements. Specifically, a user instruction is decomposed into a sequence of action proposals, each corresponding to an interaction with the GUI. After each action, the agent observes the updated GUI environment to plan the next step. However, two main challenges arise: i) resolving ambiguity in task planning (i.e., the action proposal sequence), where selecting an appropriate plan is non-trivial, as many valid ones may exist; ii) accurately grounding actions in complex and high-resolution interfaces, i.e., precisely interacting with visual targets. This paper investigates the two aforementioned challenges with our GUI Test-time Scaling Agent, namely GTA1. First, to select the most appropriate action proposal, we introduce a test-time scaling method. At each step, we sample multiple candidate action proposals and leverage a judge model to evaluate and select the most suitable one. It trades off computation for better decision quality by concurrent sampling, shortening task execution steps, and improving overall performance. Second, we propose a model that achieves improved accuracy when grounding the selected action proposal to its corresponding visual elements. Our key insight is that reinforcement learning (RL) facilitates visual grounding through inherent objective alignments, rewarding successful clicks on interface elements. Experimentally, our method establishes state-of-the-art performance across diverse benchmarks. For example, GTA1-7B achieves 50.1%, 92.4%, and 67.7% accuracies on Screenspot-Pro, Screenspot-V2, and OSWorld-G, respectively. When paired with a planner applying our test-time scaling strategy, it exhibits state-of-the-art agentic performance (e.g., 45.2% task success rate on OSWorld). We open-source our code and models here.
This survey examines the rapidly evolving field of Deep Research systems -- AI-powered applications that automate complex research workflows through the integration of large language models, advanced information retrieval, and autonomous reasoning capabilities. We analyze more than 80 commercial and non-commercial implementations that have emerged since 2023, including OpenAI/Deep Research, Gemini/Deep Research, Perplexity/Deep Research, and numerous open-source alternatives. Through comprehensive examination, we propose a novel hierarchical taxonomy that categorizes systems according to four fundamental technical dimensions: foundation models and reasoning engines, tool utilization and environmental interaction, task planning and execution control, and knowledge synthesis and output generation. We explore the architectural patterns, implementation approaches, and domain-specific adaptations that characterize these systems across academic, scientific, business, and educational applications. Our analysis reveals both the significant capabilities of current implementations and the technical and ethical challenges they present regarding information accuracy, privacy, intellectual property, and accessibility. The survey concludes by identifying promising research directions in advanced reasoning architectures, multimodal integration, domain specialization, human-AI collaboration, and ecosystem standardization that will likely shape the future evolution of this transformative technology. By providing a comprehensive framework for understanding Deep Research systems, this survey contributes to both the theoretical understanding of AI-augmented knowledge work and the practical development of more capable, responsible, and accessible research technologies. The paper resources can be viewed at https://github.com/scienceaix/deepresearch.
The problem of relocating a set of objects to designated areas amidst movable obstacles can be framed as a Geometric Task and Motion Planning (G-TAMP) problem, a subclass of task and motion planning (TAMP). Traditional approaches to G-TAMP have relied either on domain-independent heuristics or on learning from planning experience to guide the search, both of which typically demand significant computational resources or data. In contrast, humans often use common sense to intuitively decide which objects to manipulate in G-TAMP problems. Inspired by this, we propose leveraging Large Language Models (LLMs), which have common sense knowledge acquired from internet-scale data, to guide task planning in G-TAMP problems. To enable LLMs to perform geometric reasoning, we design a predicate-based prompt that encodes geometric information derived from a motion planning algorithm. We then query the LLM to generate a task plan, which is then used to search for a feasible set of continuous parameters. Since LLMs are prone to mistakes, instead of committing to LLM's outputs, we extend Monte Carlo Tree Search (MCTS) to a hybrid action space and use the LLM to guide the search. Unlike the previous approach that calls an LLM at every node and incurs high computational costs, we use it to warm-start the MCTS with the nodes explored in completing the LLM's task plan. On six different G-TAMP problems, we show our method outperforms previous LLM planners and pure search algorithms. Code can be found at: https://github.com/iMSquared/prime-the-search
The real world is messy and unstructured. Uncovering critical information often requires active, goal-driven exploration. It remains to be seen whether Vision-Language Models (VLMs), which recently emerged as a popular zero-shot tool in many difficult tasks, can operate effectively in such conditions. In this paper, we answer this question by introducing FlySearch, a 3D, outdoor, photorealistic environment for searching and navigating to objects in complex scenes. We define three sets of scenarios with varying difficulty and observe that state-of-the-art VLMs cannot reliably solve even the simplest exploration tasks, with the gap to human performance increasing as the tasks get harder. We identify a set of central causes, ranging from vision hallucination, through context misunderstanding, to task planning failures, and we show that some of them can be addressed by finetuning. We publicly release the benchmark, scenarios, and the underlying codebase.
With the rapid advancement of low-altitude remote sensing and Vision-Language Models (VLMs), Embodied Agents based on Unmanned Aerial Vehicles (UAVs) have shown significant potential in autonomous tasks. However, current evaluation methods for UAV-Embodied Agents (UAV-EAs) remain constrained by the lack of standardized benchmarks, diverse testing scenarios and open system interfaces. To address these challenges, we propose BEDI (Benchmark for Embodied Drone Intelligence), a systematic and standardized benchmark designed for evaluating UAV-EAs. Specifically, we introduce a novel Dynamic Chain-of-Embodied-Task paradigm based on the perception-decision-action loop, which decomposes complex UAV tasks into standardized, measurable subtasks. Building on this paradigm, we design a unified evaluation framework encompassing five core sub-skills: semantic perception, spatial perception, motion control, tool utilization, and task planning. Furthermore, we construct a hybrid testing platform that integrates static real-world environments with dynamic virtual scenarios, enabling comprehensive performance assessment of UAV-EAs across varied contexts. The platform also offers open and standardized interfaces, allowing researchers to customize tasks and extend scenarios, thereby enhancing flexibility and scalability in the evaluation process. Finally, through empirical evaluations of several state-of-the-art (SOTA) VLMs, we reveal their limitations in embodied UAV tasks, underscoring the critical role of the BEDI benchmark in advancing embodied intelligence research and model optimization. By filling the gap in systematic and standardized evaluation within this field, BEDI facilitates objective model comparison and lays a robust foundation for future development in this field. Our benchmark will be released at https://github.com/lostwolves/BEDI .
Large Language Model (LLM) agents can automate cybersecurity tasks and can adapt to the evolving cybersecurity landscape without re-engineering. While LLM agents have demonstrated cybersecurity capabilities on Capture-The-Flag (CTF) competitions, they have two key limitations: accessing latest cybersecurity expertise beyond training data, and integrating new knowledge into complex task planning. Knowledge-based approaches that incorporate technical understanding into the task-solving automation can tackle these limitations. We present CRAKEN, a knowledge-based LLM agent framework that improves cybersecurity capability through three core mechanisms: contextual decomposition of task-critical information, iterative self-reflected knowledge retrieval, and knowledge-hint injection that transforms insights into adaptive attack strategies. Comprehensive evaluations with different configurations show CRAKEN's effectiveness in multi-stage vulnerability detection and exploitation compared to previous approaches. Our extensible architecture establishes new methodologies for embedding new security knowledge into LLM-driven cybersecurity agentic systems. With a knowledge database of CTF writeups, CRAKEN obtained an accuracy of 22% on NYU CTF Bench, outperforming prior works by 3% and achieving state-of-the-art results. On evaluation of MITRE ATT&CK techniques, CRAKEN solves 25-30% more techniques than prior work, demonstrating improved cybersecurity capabilities via knowledge-based execution. We make our framework open source to public https://github.com/NYU-LLM-CTF/nyuctf_agents_craken.
Large Language Models (LLMs) demonstrate strong reasoning and task planning capabilities but remain fundamentally limited in physical interaction modeling. Existing approaches integrate perception via Vision-Language Models (VLMs) or adaptive decision-making through Reinforcement Learning (RL), but they fail to capture dynamic object interactions or require task-specific training, limiting their real-world applicability. We introduce APEX (Anticipatory Physics-Enhanced Execution), a framework that equips LLMs with physics-driven foresight for real-time task planning. APEX constructs structured graphs to identify and model the most relevant dynamic interactions in the environment, providing LLMs with explicit physical state updates. Simultaneously, APEX provides low-latency forward simulations of physically feasible actions, allowing LLMs to select optimal strategies based on predictive outcomes rather than static observations. We evaluate APEX on three benchmarks designed to assess perception, prediction, and decision-making: (1) Physics Reasoning Benchmark, testing causal inference and object motion prediction; (2) Tetris, evaluating whether physics-informed prediction enhances decision-making performance in long-horizon planning tasks; (3) Dynamic Obstacle Avoidance, assessing the immediate integration of perception and action feasibility analysis. APEX significantly outperforms standard LLMs and VLM-based models, demonstrating the necessity of explicit physics reasoning for bridging the gap between language-based intelligence and real-world task execution. The source code and experiment setup are publicly available at https://github.com/hwj20/APEX_EXP .
PDDL-based symbolic task planning remains pivotal for robot autonomy yet struggles with dynamic human-robot collaboration due to scalability, re-planning demands, and delayed plan availability. Although a few neurosymbolic frameworks have previously leveraged LLMs such as GPT-3 to address these challenges, reliance on closed-source, remote models with limited context introduced critical constraints: third-party dependency, inconsistent response times, restricted plan length and complexity, and multi-domain scalability issues. We present Gideon, a novel framework that enables the transition to modern, smaller, local LLMs with extended context length. Gideon integrates a novel problem generator to systematically generate large-scale datasets of realistic domain-problem-plan tuples for any domain, and adapts neurosymbolic planning for local LLMs, enabling on-device execution and extended context for multi-domain support. Preliminary experiments in single-domain scenarios performed on Qwen-2.5 1.5B and trained on 8k-32k samples, demonstrate a valid plan percentage of 66.1% (32k model) and show that the figure can be further scaled through additional data. Multi-domain tests on 16k samples yield an even higher 70.6% planning validity rate, proving extensibility across domains and signaling that data variety can have a positive effect on learning efficiency. Although long-horizon planning and reduced model size make Gideon training much less efficient than baseline models based on larger LLMs, the results are still significant considering that the trained model is about 120x smaller than baseline and that significant advantages can be achieved in inference efficiency, scalability, and multi-domain adaptability, all critical factors in human-robot collaboration. Training inefficiency can be mitigated by Gideon's streamlined data generation pipeline.
Intelligent agent systems based on Large Language Models (LLMs) have shown great potential in real-world applications. However, existing agent frameworks still face critical limitations in task planning and execution, restricting their effectiveness and generalizability. Specifically, current planning methods often lack clear global goals, leading agents to get stuck in local branches, or produce non-executable plans. Meanwhile, existing execution mechanisms struggle to balance complexity and stability, and their limited action space restricts their ability to handle diverse real-world tasks. To address these limitations, we propose GoalAct, a novel agent framework that introduces a continuously updated global planning mechanism and integrates a hierarchical execution strategy. GoalAct decomposes task execution into high-level skills, including searching, coding, writing and more, thereby reducing planning complexity while enhancing the agents' adaptability across diverse task scenarios. We evaluate GoalAct on LegalAgentBench, a benchmark with multiple types of legal tasks that require the use of multiple types of tools. Experimental results demonstrate that GoalAct achieves state-of-the-art (SOTA) performance, with an average improvement of 12.22% in success rate. These findings highlight GoalAct's potential to drive the development of more advanced intelligent agent systems, making them more effective across complex real-world applications. Our code can be found at https://github.com/cjj826/GoalAct.
We present an embodied robotic system with an LLM-driven agent-orchestration architecture for autonomous household object management. The system integrates memory-augmented task planning, enabling robots to execute high-level user commands while tracking past actions. It employs three specialized agents: a routing agent, a task planning agent, and a knowledge base agent, each powered by task-specific LLMs. By leveraging in-context learning, our system avoids the need for explicit model training. RAG enables the system to retrieve context from past interactions, enhancing long-term object tracking. A combination of Grounded SAM and LLaMa3.2-Vision provides robust object detection, facilitating semantic scene understanding for task planning. Evaluation across three household scenarios demonstrates high task planning accuracy and an improvement in memory recall due to RAG. Specifically, Qwen2.5 yields best performance for specialized agents, while LLaMA3.1 excels in routing tasks. The source code is available at: https://github.com/marc1198/chat-hsr.
Computer use agents automate digital tasks by directly interacting with graphical user interfaces (GUIs) on computers and mobile devices, offering significant potential to enhance human productivity by completing an open-ended space of user queries. However, current agents face significant challenges: imprecise grounding of GUI elements, difficulties with long-horizon task planning, and performance bottlenecks from relying on single generalist models for diverse cognitive tasks. To this end, we introduce Agent S2, a novel compositional framework that delegates cognitive responsibilities across various generalist and specialist models. We propose a novel Mixture-of-Grounding technique to achieve precise GUI localization and introduce Proactive Hierarchical Planning, dynamically refining action plans at multiple temporal scales in response to evolving observations. Evaluations demonstrate that Agent S2 establishes new state-of-the-art (SOTA) performance on three prominent computer use benchmarks. Specifically, Agent S2 achieves 18.9% and 32.7% relative improvements over leading baseline agents such as Claude Computer Use and UI-TARS on the OSWorld 15-step and 50-step evaluation. Moreover, Agent S2 generalizes effectively to other operating systems and applications, surpassing previous best methods by 52.8% on WindowsAgentArena and by 16.52% on AndroidWorld relatively. Code available at https://github.com/simular-ai/Agent-S.
Recent advances in language-conditioned robotic manipulation have leveraged imitation and reinforcement learning to enable robots to execute tasks from human commands. However, these methods often suffer from limited generalization, adaptability, and the lack of large-scale specialized datasets, unlike data-rich domains such as computer vision, making long-horizon task execution challenging. To address these gaps, we introduce DAHLIA, a data-agnostic framework for language-conditioned long-horizon robotic manipulation, leveraging large language models (LLMs) for real-time task planning and execution. DAHLIA employs a dual-tunnel architecture, where an LLM-powered planner collaborates with co-planners to decompose tasks and generate executable plans, while a reporter LLM provides closed-loop feedback, enabling adaptive re-planning and ensuring task recovery from potential failures. Moreover, DAHLIA integrates chain-of-thought (CoT) in task reasoning and temporal abstraction for efficient action execution, enhancing traceability and robustness. Our framework demonstrates state-of-the-art performance across diverse long-horizon tasks, achieving strong generalization in both simulated and real-world scenarios. Videos and code are available at https://ghiara.github.io/DAHLIA/.
Bimanual robotic manipulation provides significant versatility, but also presents an inherent challenge due to the complexity involved in the spatial and temporal coordination between two hands. Existing works predominantly focus on attaining human-level manipulation skills for robotic hands, yet little attention has been paid to task planning on long-horizon timescales. With their outstanding in-context learning and zero-shot generation abilities, Large Language Models (LLMs) have been applied and grounded in diverse robotic embodiments to facilitate task planning. However, LLMs still suffer from errors in long-horizon reasoning and from hallucinations in complex robotic tasks, lacking a guarantee of logical correctness when generating the plan. Previous works, such as LLM+P, extended LLMs with symbolic planners. However, none have been successfully applied to bimanual robots. New challenges inevitably arise in bimanual manipulation, necessitating not only effective task decomposition but also efficient task allocation. To address these challenges, this paper introduces LLM+MAP, a bimanual planning framework that integrates LLM reasoning and multi-agent planning, automating effective and efficient bimanual task planning. We conduct simulated experiments on various long-horizon manipulation tasks of differing complexity. Our method is built using GPT-4o as the backend, and we compare its performance against plans generated directly by LLMs, including GPT-4o, V3 and also recent strong reasoning models o1 and R1. By analyzing metrics such as planning time, success rate, group debits, and planning-step reduction rate, we demonstrate the superior performance of LLM+MAP, while also providing insights into robotic reasoning. Code is available at https://github.com/Kchu/LLM-MAP.
Recent advancements in large language models (LLMs) have expanded their role in robotic task planning. However, while LLMs have been explored for generating feasible task sequences, their ability to ensure safe task execution remains underdeveloped. Existing methods struggle with structured risk perception, making them inadequate for safety-critical applications where low-latency hazard adaptation is required. To address this limitation, we propose a Graphormer-enhanced risk-aware task planning framework that combines LLM-based decision-making with structured safety modeling. Our approach constructs a dynamic spatio-semantic safety graph, capturing spatial and contextual risk factors to enable online hazard detection and adaptive task refinement. Unlike existing methods that rely on predefined safety constraints, our framework introduces a context-aware risk perception module that continuously refines safety predictions based on real-time task execution. This enables a more flexible and scalable approach to robotic planning, allowing for adaptive safety compliance beyond static rules. To validate our framework, we conduct experiments in the AI2-THOR environment. The experiments results validates improvements in risk detection accuracy, rising safety notice, and task adaptability of our framework in continuous environments compared to static rule-based and LLM-only baselines. Our project is available at https://github.com/hwj20/GGTP
The deployment of Large Language Models (LLMs) in robotic systems presents unique safety challenges, particularly in unpredictable environments. Although LLMs, leveraging zero-shot learning, enhance human-robot interaction and decision-making capabilities, their inherent probabilistic nature and lack of formal guarantees raise significant concerns for safety-critical applications. Traditional model-based verification approaches often rely on precise system models, which are difficult to obtain for real-world robotic systems and may not be fully trusted due to modeling inaccuracies, unmodeled dynamics, or environmental uncertainties. To address these challenges, this paper introduces a safety assurance framework for LLM-controlled robots based on data-driven reachability analysis, a formal verification technique that ensures all possible system trajectories remain within safe operational limits. Our framework specifically investigates the problem of instructing an LLM to navigate the robot to a specified goal and assesses its ability to generate low-level control actions that successfully guide the robot safely toward that goal. By leveraging historical data to construct reachable sets of states for the robot-LLM system, our approach provides rigorous safety guarantees against unsafe behaviors without relying on explicit analytical models. We validate the framework through experimental case studies in autonomous navigation and task planning, demonstrating its effectiveness in mitigating risks associated with LLM-generated commands. This work advances the integration of formal methods into LLM-based robotics, offering a principled and practical approach to ensuring safety in next-generation autonomous systems.
Large Language Models (LLMs) exhibit remarkable capabilities in the hierarchical decomposition of complex tasks through semantic reasoning. However, their application in embodied systems faces challenges in ensuring reliable execution of subtask sequences and achieving one-shot success in long-term task completion. To address these limitations in dynamic environments, we propose Closed-Loop Embodied Agent (CLEA) -- a novel architecture incorporating four specialized open-source LLMs with functional decoupling for closed-loop task management. The framework features two core innovations: (1) Interactive task planner that dynamically generates executable subtasks based on the environmental memory, and (2) Multimodal execution critic employing an evaluation framework to conduct a probabilistic assessment of action feasibility, triggering hierarchical re-planning mechanisms when environmental perturbations exceed preset thresholds. To validate CLEA's effectiveness, we conduct experiments in a real environment with manipulable objects, using two heterogeneous robots for object search, manipulation, and search-manipulation integration tasks. Across 12 task trials, CLEA outperforms the baseline model, achieving a 67.3% improvement in success rate and a 52.8% increase in task completion rate. These results demonstrate that CLEA significantly enhances the robustness of task planning and execution in dynamic environments.
Multi-robot task planning and collaboration are critical challenges in robotics. While Behavior Trees (BTs) have been established as a popular control architecture and are plannable for a single robot, the development of effective multi-robot BT planning algorithms remains challenging due to the complexity of coordinating diverse action spaces. We propose the Multi-Robot Behavior Tree Planning (MRBTP) algorithm, with theoretical guarantees of both soundness and completeness. MRBTP features cross-tree expansion to coordinate heterogeneous actions across different BTs to achieve the team's goal. For homogeneous actions, we retain backup structures among BTs to ensure robustness and prevent redundant execution through intention sharing. While MRBTP is capable of generating BTs for both homogeneous and heterogeneous robot teams, its efficiency can be further improved. We then propose an optional plugin for MRBTP when Large Language Models (LLMs) are available to reason goal-related actions for each robot. These relevant actions can be pre-planned to form long-horizon subtrees, significantly enhancing the planning speed and collaboration efficiency of MRBTP. We evaluate our algorithm in warehouse management and everyday service scenarios. Results demonstrate MRBTP's robustness and execution efficiency under varying settings, as well as the ability of the pre-trained LLM to generate effective task-specific subtrees for MRBTP.
Large Language Models (LLMs) have demonstrated exceptional abilities in reasoning for task planning. However, challenges remain under-explored for parallel schedules. This paper introduces a novel paradigm, plan-over-graph, in which the model first decomposes a real-life textual task into executable subtasks and constructs an abstract task graph. The model then understands this task graph as input and generates a plan for parallel execution. To enhance the planning capability of complex, scalable graphs, we design an automated and controllable pipeline to generate synthetic graphs and propose a two-stage training scheme. Experimental results show that our plan-over-graph method significantly improves task performance on both API-based LLMs and trainable open-sourced LLMs. By normalizing complex tasks as graphs, our method naturally supports parallel execution, demonstrating global efficiency. The code and data are available at https://github.com/zsq259/Plan-over-Graph.
Vision-and-Language Navigation (VLN) is an essential skill for embodied agents, allowing them to navigate in 3D environments following natural language instructions. High-performance navigation models require a large amount of training data, the high cost of manually annotating data has seriously hindered this field. Therefore, some previous methods translate trajectory videos into step-by-step instructions for expanding data, but such instructions do not match well with users' communication styles that briefly describe destinations or state specific needs. Moreover, local navigation trajectories overlook global context and high-level task planning. To address these issues, we propose NavRAG, a retrieval-augmented generation (RAG) framework that generates user demand instructions for VLN. NavRAG leverages LLM to build a hierarchical scene description tree for 3D scene understanding from global layout to local details, then simulates various user roles with specific demands to retrieve from the scene tree, generating diverse instructions with LLM. We annotate over 2 million navigation instructions across 861 scenes and evaluate the data quality and navigation performance of trained models.
Large Language Models (LLMs) have been used in cybersecurity such as autonomous security analysis or penetration testing. Capture the Flag (CTF) challenges serve as benchmarks to assess automated task-planning abilities of LLM agents for cybersecurity. Early attempts to apply LLMs for solving CTF challenges used single-agent systems, where feedback was restricted to a single reasoning-action loop. This approach was inadequate for complex CTF tasks. Inspired by real-world CTF competitions, where teams of experts collaborate, we introduce the D-CIPHER LLM multi-agent framework for collaborative CTF solving. D-CIPHER integrates agents with distinct roles with dynamic feedback loops to enhance reasoning on complex tasks. It introduces the Planner-Executor agent system, consisting of a Planner agent for overall problem-solving along with multiple heterogeneous Executor agents for individual tasks, facilitating efficient allocation of responsibilities among the agents. Additionally, D-CIPHER incorporates an Auto-prompter agent to improve problem-solving by auto-generating a highly relevant initial prompt. We evaluate D-CIPHER on multiple CTF benchmarks and LLM models via comprehensive studies to highlight the impact of our enhancements. Additionally, we manually map the CTFs in NYU CTF Bench to MITRE ATT&CK techniques that apply for a comprehensive evaluation of D-CIPHER's offensive security capability. D-CIPHER achieves state-of-the-art performance on three benchmarks: 22.0% on NYU CTF Bench, 22.5% on Cybench, and 44.0% on HackTheBox, which is 2.5% to 8.5% better than previous work. D-CIPHER solves 65% more ATT&CK techniques compared to previous work, demonstrating stronger offensive capability.