Building a general-purpose intelligent home-assistant agent skilled in diverse tasks by human commands is a long-term blueprint of embodied AI research, which poses requirements on task planning, environment modeling, and object interaction. In this work, we study primitive mobile manipulations for embodied agents, i.e. how to navigate and interact based on an instructed verb-noun pair. We propose DISCO, which features non-trivial advancements in contextualized scene modeling and efficient controls. In particular, DISCO incorporates differentiable scene representations of rich semantics in object and affordance, which is dynamically learned on the fly and facilitates navigation planning. Besides, we propose dual-level coarse-to-fine action controls leveraging both global and local cues to accomplish mobile manipulation tasks efficiently. DISCO easily integrates into embodied tasks such as embodied instruction following. To validate our approach, we take the ALFRED benchmark of large-scale long-horizon vision-language navigation and interaction tasks as a test bed. In extensive experiments, we make comprehensive evaluations and demonstrate that DISCO outperforms the art by a sizable +8.6% success rate margin in unseen scenes, even without step-by-step instructions. Our code is publicly released at https://github.com/AllenXuuu/DISCO.
LLM agents have demonstrated remarkable performance across various applications, primarily due to their advanced capabilities in reasoning, utilizing external knowledge and tools, calling APIs, and executing actions to interact with environments. Current agents typically utilize a memory module or a retrieval-augmented generation (RAG) mechanism, retrieving past knowledge and instances with similar embeddings from knowledge bases to inform task planning and execution. However, the reliance on unverified knowledge bases raises significant concerns about their safety and trustworthiness. To uncover such vulnerabilities, we propose a novel red teaming approach AgentPoison, the first backdoor attack targeting generic and RAG-based LLM agents by poisoning their long-term memory or RAG knowledge base. In particular, we form the trigger generation process as a constrained optimization to optimize backdoor triggers by mapping the triggered instances to a unique embedding space, so as to ensure that whenever a user instruction contains the optimized backdoor trigger, the malicious demonstrations are retrieved from the poisoned memory or knowledge base with high probability. In the meantime, benign instructions without the trigger will still maintain normal performance. Unlike conventional backdoor attacks, AgentPoison requires no additional model training or fine-tuning, and the optimized backdoor trigger exhibits superior transferability, in-context coherence, and stealthiness. Extensive experiments demonstrate AgentPoison's effectiveness in attacking three types of real-world LLM agents: RAG-based autonomous driving agent, knowledge-intensive QA agent, and healthcare EHRAgent. On each agent, AgentPoison achieves an average attack success rate higher than 80% with minimal impact on benign performance (less than 1%) with a poison rate less than 0.1%.
In recent years, Multi-modal Foundation Models (MFMs) and Embodied Artificial Intelligence (EAI) have been advancing side by side at an unprecedented pace. The integration of the two has garnered significant attention from the AI research community. In this work, we attempt to provide an in-depth and comprehensive evaluation of the performance of MFM s on embodied task planning, aiming to shed light on their capabilities and limitations in this domain. To this end, based on the characteristics of embodied task planning, we first develop a systematic evaluation framework, which encapsulates four crucial capabilities of MFMs: object understanding, spatio-temporal perception, task understanding, and embodied reasoning. Following this, we propose a new benchmark, named MFE-ETP, characterized its complex and variable task scenarios, typical yet diverse task types, task instances of varying difficulties, and rich test case types ranging from multiple embodied question answering to embodied task reasoning. Finally, we offer a simple and easy-to-use automatic evaluation platform that enables the automated testing of multiple MFMs on the proposed benchmark. Using the benchmark and evaluation platform, we evaluated several state-of-the-art MFMs and found that they significantly lag behind human-level performance. The MFE-ETP is a high-quality, large-scale, and challenging benchmark relevant to real-world tasks.
Validating safety-critical autonomous systems in high-dimensional domains such as robotics presents a significant challenge. Existing black-box approaches based on Markov chain Monte Carlo may require an enormous number of samples, while methods based on importance sampling often rely on simple parametric families that may struggle to represent the distribution over failures. We propose to sample the distribution over failures using a conditional denoising diffusion model, which has shown success in complex high-dimensional problems such as robotic task planning. We iteratively train a diffusion model to produce state trajectories closer to failure. We demonstrate the effectiveness of our approach on high-dimensional robotic validation tasks, improving sample efficiency and mode coverage compared to existing black-box techniques.
The state of an object reflects its current status or condition and is important for a robot's task planning and manipulation. However, detecting an object's state and generating a state-sensitive plan for robots is challenging. Recently, pre-trained Large Language Models (LLMs) and Vision-Language Models (VLMs) have shown impressive capabilities in generating plans. However, to the best of our knowledge, there is hardly any investigation on whether LLMs or VLMs can also generate object state-sensitive plans. To study this, we introduce an Object State-Sensitive Agent (OSSA), a task-planning agent empowered by pre-trained neural networks. We propose two methods for OSSA: (i) a modular model consisting of a pre-trained vision processing module (dense captioning model, DCM) and a natural language processing model (LLM), and (ii) a monolithic model consisting only of a VLM. To quantitatively evaluate the performances of the two methods, we use tabletop scenarios where the task is to clear the table. We contribute a multimodal benchmark dataset that takes object states into consideration. Our results show that both methods can be used for object state-sensitive tasks, but the monolithic approach outperforms the modular approach. The code for OSSA is available at https://github.com/Xiao-wen-Sun/OSSA
The unprecedented advancements in Multimodal Large Language Models (MLLMs) have demonstrated strong potential in interacting with humans through both language and visual inputs to perform downstream tasks such as visual question answering and scene understanding. However, these models are constrained to basic instruction-following or descriptive tasks, facing challenges in complex real-world remote sensing applications that require specialized tools and knowledge. To address these limitations, we propose RS-Agent, an AI agent designed to interact with human users and autonomously leverage specialized models to address the demands of real-world remote sensing applications. RS-Agent integrates four key components: a Central Controller based on large language models, a dynamic toolkit for tool execution, a Solution Space for task-specific expert guidance, and a Knowledge Space for domain-level reasoning, enabling it to interpret user queries and orchestrate tools for accurate remote sensing task. We introduce two novel mechanisms: Task-Aware Retrieval, which improves tool selection accuracy through expert-guided planning, and DualRAG, a retrieval-augmented generation method that enhances knowledge relevance through weighted, dual-path retrieval. RS-Agent supports flexible integration of new tools and is compatible with both open-source and proprietary LLMs. Extensive experiments across 9 datasets and 18 remote sensing tasks demonstrate that RS-Agent significantly outperforms state-of-the-art MLLMs, achieving over 95% task planning accuracy and delivering superior performance in tasks such as scene classification, object counting, and remote sensing visual question answering. Our work presents RS-Agent as a robust and extensible framework for advancing intelligent automation in remote sensing analysis.
Large Language Models (LLMs) are being deployed across various domains today. However, their capacity to solve Capture the Flag (CTF) challenges in cybersecurity has not been thoroughly evaluated. To address this, we develop a novel method to assess LLMs in solving CTF challenges by creating a scalable, open-source benchmark database specifically designed for these applications. This database includes metadata for LLM testing and adaptive learning, compiling a diverse range of CTF challenges from popular competitions. Utilizing the advanced function calling capabilities of LLMs, we build a fully automated system with an enhanced workflow and support for external tool calls. Our benchmark dataset and automated framework allow us to evaluate the performance of five LLMs, encompassing both black-box and open-source models. This work lays the foundation for future research into improving the efficiency of LLMs in interactive cybersecurity tasks and automated task planning. By providing a specialized benchmark, our project offers an ideal platform for developing, testing, and refining LLM-based approaches to vulnerability detection and resolution. Evaluating LLMs on these challenges and comparing with human performance yields insights into their potential for AI-driven cybersecurity solutions to perform real-world threat management. We make our benchmark dataset open source to public https://github.com/NYU-LLM-CTF/NYU_CTF_Bench along with our playground automated framework https://github.com/NYU-LLM-CTF/llm_ctf_automation.
Large language models (LLMs) have demonstrated exceptional reasoning capabilities, enabling them to solve various complex problems. Recently, this ability has been applied to the paradigm of tool learning. Tool learning involves providing examples of tool usage and their corresponding functions, allowing LLMs to formulate plans and demonstrate the process of invoking and executing each tool. LLMs can address tasks that they cannot complete independently, thereby enhancing their potential across different tasks. However, this approach faces two key challenges. First, redundant error correction leads to unstable planning and long execution time. Additionally, designing a correct plan among multiple tools is also a challenge in tool learning. To address these issues, we propose Tool-Planner, a task-processing framework based on toolkits. Tool-Planner groups tools based on the API functions with the same function into a toolkit and allows LLMs to implement planning across the various toolkits. When a tool error occurs, the language model can reselect and adjust tools based on the toolkit. Experiments show that our approach demonstrates a high pass and win rate across different datasets and optimizes the planning scheme for tool learning in models such as GPT-4 and Claude 3, showcasing the potential of our method. Our code is public at https://github.com/OceannTwT/Tool-Planner
Task planning in language agents is emerging as an important research topic alongside the development of large language models (LLMs). It aims to break down complex user requests in natural language into solvable sub-tasks, thereby fulfilling the original requests. In this context, the sub-tasks can be naturally viewed as a graph, where the nodes represent the sub-tasks, and the edges denote the dependencies among them. Consequently, task planning is a decision-making problem that involves selecting a connected path or subgraph within the corresponding graph and invoking it. In this paper, we explore graph learning-based methods for task planning, a direction that is orthogonal to the prevalent focus on prompt design. Our interest in graph learning stems from a theoretical discovery: the biases of attention and auto-regressive loss impede LLMs' ability to effectively navigate decision-making on graphs, which is adeptly addressed by graph neural networks (GNNs). This theoretical insight led us to integrate GNNs with LLMs to enhance overall performance. Extensive experiments demonstrate that GNN-based methods surpass existing solutions even without training, and minimal training can further enhance their performance. The performance gain increases with a larger task graph size.
Recently, tool learning with large language models (LLMs) has emerged as a promising paradigm for augmenting the capabilities of LLMs to tackle highly complex problems. Despite growing attention and rapid advancements in this field, the existing literature remains fragmented and lacks systematic organization, posing barriers to entry for newcomers. This gap motivates us to conduct a comprehensive survey of existing works on tool learning with LLMs. In this survey, we focus on reviewing existing literature from the two primary aspects (1) why tool learning is beneficial and (2) how tool learning is implemented, enabling a comprehensive understanding of tool learning with LLMs. We first explore the "why" by reviewing both the benefits of tool integration and the inherent benefits of the tool learning paradigm from six specific aspects. In terms of "how", we systematically review the literature according to a taxonomy of four key stages in the tool learning workflow: task planning, tool selection, tool calling, and response generation. Additionally, we provide a detailed summary of existing benchmarks and evaluation methods, categorizing them according to their relevance to different stages. Finally, we discuss current challenges and outline potential future directions, aiming to inspire both researchers and industrial developers to further explore this emerging and promising area. We also maintain a GitHub repository to continually keep track of the relevant papers and resources in this rising area at https://github.com/quchangle1/LLM-Tool-Survey.
The rapid advancement of neural language models has sparked a new surge of intelligent agent research. Unlike traditional agents, large language model-based agents (LLM agents) have emerged as a promising paradigm for achieving artificial general intelligence (AGI) due to their superior reasoning and generalization capabilities. Effective planning is crucial for the success of LLM agents in real-world tasks, making it a highly pursued topic in the community. Current planning methods typically translate tasks into executable action sequences. However, determining a feasible or optimal sequence for complex tasks with multiple constraints at fine granularity, which often requires compositing long chains of heterogeneous actions, remains challenging. This paper introduces Planning with Multi-Constraints (PMC), a zero-shot methodology for collaborative LLM-based multi-agent systems that simplifies complex task planning with constraints by decomposing it into a hierarchy of subordinate tasks. Each subtask is then mapped into executable actions. PMC was assessed on two constraint-intensive benchmarks, TravelPlanner and API-Bank. Notably, PMC achieved an average 42.68% success rate on TravelPlanner, significantly higher than GPT-4 (2.92%), and outperforming GPT-4 with ReAct on API-Bank by 13.64%, showing the immense potential of integrating LLM with multi-agent systems. We also show that PMC works with small LLM as the planning core, e.g., LLaMA-3.1-8B.
We present a symbolic learning framework inspired by cognitive-like memory functionalities (i.e., storing, retrieving, consolidating and forgetting) to generate task representations to support high-level task planning and knowledge bootstrapping. We address a scenario involving a non-expert human, who performs a single task demonstration, and a robot, which online learns structured knowledge to re-execute the task based on experiences, i.e., observations. We consider a one-shot learning process based on non-annotated data to store an intelligible representation of the task, which can be refined through interaction, e.g., via verbal or visual communication. Our general-purpose framework relies on fuzzy Description Logic, which has been used to extend the previously developed Scene Identification and Tagging algorithm. In this paper, we exploit such an algorithm to implement cognitive-like memory functionalities employing scores that rank memorised observations over time based on simple heuristics. Our main contribution is the formalisation of a framework that can be used to systematically investigate different heuristics for bootstrapping hierarchical knowledge representations based on robot observations. Through an illustrative assembly task scenario, the paper presents the performance of our framework to discuss its benefits and limitations.
In robotics, the use of Large Language Models (LLMs) is becoming prevalent, especially for understanding human commands. In particular, LLMs are utilized as domain-agnostic task planners for high-level human commands. LLMs are capable of Chain-of-Thought (CoT) reasoning, and this allows LLMs to be task planners. However, we need to consider that modern robots still struggle to perform complex actions, and the domains where robots can be deployed are limited in practice. This leads us to pose a question: If small LMs can be trained to reason in chains within a single domain, would even small LMs be good task planners for the robots? To train smaller LMs to reason in chains, we build `COmmand-STeps datasets' (COST) consisting of high-level commands along with corresponding actionable low-level steps, via LLMs. We release not only our datasets but also the prompt templates used to generate them, to allow anyone to build datasets for their domain. We compare GPT3.5 and GPT4 with the finetuned GPT2 for task domains, in tabletop and kitchen environments, and the result shows that GPT2-medium is comparable to GPT3.5 for task planning in a specific domain. Our dataset, code, and more output samples can be found in https://github.com/Gawon-Choi/small-LMs-Task-Planning
Open-source pre-trained Large Language Models (LLMs) exhibit strong language understanding and generation capabilities, making them highly successful in a variety of tasks. However, when used as agents for dealing with complex problems in the real world, their performance is far inferior to large commercial models such as ChatGPT and GPT-4. As intelligent agents, LLMs need to have the capabilities of task planning, long-term memory, and the ability to leverage external tools to achieve satisfactory performance. Various methods have been proposed to enhance the agent capabilities of LLMs. On the one hand, methods involve constructing agent-specific data and fine-tuning the models. On the other hand, some methods focus on designing prompts that effectively activate the reasoning abilities of the LLMs. We explore both strategies on the 7B and 13B models. We propose a comprehensive method for constructing agent-specific data using GPT-4. Through supervised fine-tuning with constructed data, we find that for these models with a relatively small number of parameters, supervised fine-tuning can significantly reduce hallucination outputs and formatting errors in agent tasks. Furthermore, techniques such as multi-path reasoning and task decomposition can effectively decrease problem complexity and enhance the performance of LLMs as agents. We evaluate our method on five agent tasks of AgentBench and achieve satisfactory results.
Conventional Task and Motion Planning (TAMP) approaches rely on manually crafted interfaces connecting symbolic task planning with continuous motion generation. These domain-specific and labor-intensive modules are limited in addressing emerging tasks in real-world settings. Here, we present LLM^3, a novel Large Language Model (LLM)-based TAMP framework featuring a domain-independent interface. Specifically, we leverage the powerful reasoning and planning capabilities of pre-trained LLMs to propose symbolic action sequences and select continuous action parameters for motion planning. Crucially, LLM^3 incorporates motion planning feedback through prompting, allowing the LLM to iteratively refine its proposals by reasoning about motion failure. Consequently, LLM^3 interfaces between task planning and motion planning, alleviating the intricate design process of handling domain-specific messages between them. Through a series of simulations in a box-packing domain, we quantitatively demonstrate the effectiveness of LLM^3 in solving TAMP problems and the efficiency in selecting action parameters. Ablation studies underscore the significant contribution of motion failure reasoning to the success of LLM^3. Furthermore, we conduct qualitative experiments on a physical manipulator, demonstrating the practical applicability of our approach in real-world settings.
Large language models (LLMs) have recently received considerable attention as alternative solutions for task planning. However, comparing the performance of language-oriented task planners becomes difficult, and there exists a dearth of detailed exploration regarding the effects of various factors such as pre-trained model selection and prompt construction. To address this, we propose a benchmark system for automatically quantifying performance of task planning for home-service embodied agents. Task planners are tested on two pairs of datasets and simulators: 1) ALFRED and AI2-THOR, 2) an extension of Watch-And-Help and VirtualHome. Using the proposed benchmark system, we perform extensive experiments with LLMs and prompts, and explore several enhancements of the baseline planner. We expect that the proposed benchmark tool would accelerate the development of language-oriented task planners.
Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning; adoption that has fueled a wealth of new models such as LLaVa, InstructBLIP, and PaLI-3. Despite the volume of new releases, key design decisions around image preprocessing, architecture, and optimization are under-explored, making it challenging to understand what factors account for model performance $-$ a challenge further complicated by the lack of objective, consistent evaluations. To address these gaps, we first compile a suite of standardized evaluations spanning visual question answering, object localization, and challenge sets that probe properties such as hallucination; evaluations that provide fine-grained insight VLM capabilities. Second, we rigorously investigate VLMs along key design axes, including pretrained visual representations and training from base vs. instruct-tuned language models, amongst others. We couple our analysis with three resource contributions: (1) a unified framework for evaluating VLMs, (2) optimized, flexible training code, and (3) checkpoints for all models, including a family of VLMs at the 7-13B scale that strictly outperform InstructBLIP and LLaVa v1.5, the state-of-the-art in open VLMs.
The rise of LLM-based agents shows great potential to revolutionize task planning, capturing significant attention. Given that these agents will be integrated into high-stake domains, ensuring their reliability and safety is crucial. This paper presents an Agent-Constitution-based agent framework, TrustAgent, with a particular focus on improving the LLM-based agent safety. The proposed framework ensures strict adherence to the Agent Constitution through three strategic components: pre-planning strategy which injects safety knowledge to the model before plan generation, in-planning strategy which enhances safety during plan generation, and post-planning strategy which ensures safety by post-planning inspection. Our experimental results demonstrate that the proposed framework can effectively enhance an LLM agent's safety across multiple domains by identifying and mitigating potential dangers during the planning. Further analysis reveals that the framework not only improves safety but also enhances the helpfulness of the agent. Additionally, we highlight the importance of the LLM reasoning ability in adhering to the Constitution. This paper sheds light on how to ensure the safe integration of LLM-based agents into human-centric environments. Data and code are available at https://github.com/agiresearch/TrustAgent.
Recently, the flourishing large language models(LLM), especially ChatGPT, have shown exceptional performance in language understanding, reasoning, and interaction, attracting users and researchers from multiple fields and domains. Although LLMs have shown great capacity to perform human-like task accomplishment in natural language and natural image, their potential in handling remote sensing interpretation tasks has not yet been fully explored. Moreover, the lack of automation in remote sensing task planning hinders the accessibility of remote sensing interpretation techniques, especially to non-remote sensing experts from multiple research fields. To this end, we present Remote Sensing ChatGPT, an LLM-powered agent that utilizes ChatGPT to connect various AI-based remote sensing models to solve complicated interpretation tasks. More specifically, given a user request and a remote sensing image, we utilized ChatGPT to understand user requests, perform task planning according to the tasks' functions, execute each subtask iteratively, and generate the final response according to the output of each subtask. Considering that LLM is trained with natural language and is not capable of directly perceiving visual concepts as contained in remote sensing images, we designed visual cues that inject visual information into ChatGPT. With Remote Sensing ChatGPT, users can simply send a remote sensing image with the corresponding request, and get the interpretation results as well as language feedback from Remote Sensing ChatGPT. Experiments and examples show that Remote Sensing ChatGPT can tackle a wide range of remote sensing tasks and can be extended to more tasks with more sophisticated models such as the remote sensing foundation model. The code and demo of Remote Sensing ChatGPT is publicly available at https://github.com/HaonanGuo/Remote-Sensing-ChatGPT .
Large Language Model (LLM) agents significantly extend the capabilities of standalone LLMs, empowering them to interact with external tools (e.g., APIs, functions) and complete various tasks in a self-directed fashion. The challenge of tool use demands that LLMs not only understand user queries and generate answers accurately but also excel in task planning, tool invocation, and result summarization. While traditional works focus on training a single LLM with all these capabilities, performance limitations become apparent, particularly with smaller models. To overcome these challenges, we propose a novel approach that decomposes the aforementioned capabilities into a planner, caller, and summarizer. Each component is implemented by a single LLM that focuses on a specific capability and collaborates with others to accomplish the task. This modular framework facilitates individual updates and the potential use of smaller LLMs for building each capability. To effectively train this framework, we introduce a two-stage training paradigm. First, we fine-tune a backbone LLM on the entire dataset without discriminating sub-tasks, providing the model with a comprehensive understanding of the task. Second, the fine-tuned LLM is used to instantiate the planner, caller, and summarizer respectively, which are continually fine-tuned on respective sub-tasks. Evaluation across various tool-use benchmarks illustrates that our proposed multi-LLM framework surpasses the traditional single-LLM approach, highlighting its efficacy and advantages in tool learning.