We study a Federated Reinforcement Learning (FedRL) problem with constraint heterogeneity. In our setting, we aim to solve a reinforcement learning problem with multiple constraints while $N$ training agents are located in $N$ different environments with limited access to the constraint signals and they are expected to collaboratively learn a policy satisfying all constraint signals. Such learning problems are prevalent in scenarios of Large Language Model (LLM) fine-tuning and healthcare applications. To solve the problem, we propose federated primal-dual policy optimization methods based on traditional policy gradient methods. Specifically, we introduce $N$ local Lagrange functions for agents to perform local policy updates, and these agents are then scheduled to periodically communicate on their local policies. Taking natural policy gradient (NPG) and proximal policy optimization (PPO) as policy optimization methods, we mainly focus on two instances of our algorithms, ie, {FedNPG} and {FedPPO}. We show that FedNPG achieves global convergence with an $\tilde{O}(1/\sqrt{T})$ rate, and FedPPO efficiently solves complicated learning tasks with the use of deep neural networks.

Most instance perception and image understanding solutions focus mainly on natural images. However, applications for synthetic images, and more specifically, images of Graphical User Interfaces (GUI) remain limited. This hinders the development of autonomous computer-vision-powered Artificial Intelligence (AI) agents. In this work, we present Search Instruction Coordinates or SIC, a multi-modal solution for object identification in a GUI. More precisely, given a natural language instruction and a screenshot of a GUI, SIC locates the coordinates of the component on the screen where the instruction would be executed. To this end, we develop two methods. The first method is a three-part architecture that relies on a combination of a Large Language Model (LLM) and an object detection model. The second approach uses a multi-modal foundation model.

This paper presents reports on a series of experiments with a novel dataset evaluating how well Large Language Models (LLMs) can mark (i.e. grade) open text responses to short answer questions, Specifically, we explore how well different combinations of GPT version and prompt engineering strategies performed at marking real student answers to short answer across different domain areas (Science and History) and grade-levels (spanning ages 5-16) using a new, never-used-before dataset from Carousel, a quizzing platform. We found that GPT-4, with basic few-shot prompting performed well (Kappa, 0.70) and, importantly, very close to human-level performance (0.75). This research builds on prior findings that GPT-4 could reliably score short answer reading comprehension questions at a performance-level very close to that of expert human raters. The proximity to human-level performance, across a variety of subjects and grade levels suggests that LLMs could be a valuable tool for supporting low-stakes formative assessment tasks in K-12 education and has important implications for real-world education delivery.

This paper presents the use of Retrieval Augmented Generation (RAG) to improve the feedback generated by Large Language Models for programming tasks. For this purpose, corresponding lecture recordings were transcribed and made available to the Large Language Model GPT-4 as external knowledge source together with timestamps as metainformation by using RAG. The purpose of this is to prevent hallucinations and to enforce the use of the technical terms and phrases from the lecture. In an exercise platform developed to solve programming problems for an introductory programming lecture, students can request feedback on their solutions generated by GPT-4. For this task GPT-4 receives the students' code solution, the compiler output, the result of unit tests and the relevant passages from the lecture notes available through the use of RAG as additional context. The feedback generated by GPT-4 should guide students to solve problems independently and link to the lecture content, using the time stamps of the transcript as meta-information. In this way, the corresponding lecture videos can be viewed immediately at the corresponding positions. For the evaluation, students worked with the tool in a workshop and decided for each feedback whether it should be extended by RAG or not. First results based on a questionnaire and the collected usage data show that the use of RAG can improve feedback generation and is preferred by students in some situations. Due to the slower speed of feedback generation, the benefits are situation dependent.

The digitization of traffic sensing infrastructure has significantly accumulated an extensive traffic data warehouse, which presents unprecedented challenges for transportation analytics. The complexities associated with querying large-scale multi-table databases require specialized programming expertise and labor-intensive development. Additionally, traditional analysis methods have focused mainly on numerical data, often neglecting the semantic aspects that could enhance interpretability and understanding. Furthermore, real-time traffic data access is typically limited due to privacy concerns. To bridge this gap, the integration of Large Language Models (LLMs) into the domain of traffic management presents a transformative approach to addressing the complexities and challenges inherent in modern transportation systems. This paper proposes an intelligent online chatbot, TP-GPT, for efficient customized transportation surveillance and management empowered by a large real-time traffic database. The innovative framework leverages contextual and generative intelligence of language models to generate accurate SQL queries and natural language interpretations by employing transportation-specialized prompts, Chain-of-Thought prompting, few-shot learning, multi-agent collaboration strategy, and chat memory. Experimental study demonstrates that our approach outperforms state-of-the-art baselines such as GPT-4 and PaLM 2 on a challenging traffic-analysis benchmark TransQuery. TP-GPT would aid researchers and practitioners in real-time transportation surveillance and management in a privacy-preserving, equitable, and customizable manner.

Diffusion models have exhibit exceptional performance in text-to-image generation and editing. However, existing methods often face challenges when handling complex text prompts that involve multiple objects with multiple attributes and relationships. In this paper, we propose a brand new training-free text-to-image generation/editing framework, namely Recaption, Plan and Generate (RPG), harnessing the powerful chain-of-thought reasoning ability of multimodal LLMs to enhance the compositionality of text-to-image diffusion models. Our approach employs the MLLM as a global planner to decompose the process of generating complex images into multiple simpler generation tasks within subregions. We propose complementary regional diffusion to enable region-wise compositional generation. Furthermore, we integrate text-guided image generation and editing within the proposed RPG in a closed-loop fashion, thereby enhancing generalization ability. Extensive experiments demonstrate our RPG outperforms state-of-the-art text-to-image diffusion models, including DALL-E 3 and SDXL, particularly in multi-category object composition and text-image semantic alignment. Notably, our RPG framework exhibits wide compatibility with various MLLM architectures (e.g., MiniGPT-4) and diffusion backbones (e.g., ControlNet). Our code is available at: https://github.com/YangLing0818/RPG-DiffusionMaster

In this study, we investigated the effects of self-reflection in large language models (LLMs) on problem-solving performance. We instructed nine popular LLMs to answer a series of multiple-choice questions to provide a performance baseline. For each incorrectly answered question, we instructed eight types of self-reflecting LLM agents to reflect on their mistakes and provide themselves with guidance to improve problem-solving. Then, using this guidance, each self-reflecting agent attempted to re-answer the same questions. Our results indicate that LLM agents are able to significantly improve their problem-solving performance through self-reflection ($p < 0.001$). In addition, we compared the various types of self-reflection to determine their individual contribution to performance. All code and data are available on GitHub at https://github.com/matthewrenze/self-reflection

One limitation of existing Transformer-based models is that they cannot handle very long sequences as input since their self-attention operations exhibit quadratic time and space complexity. This problem becomes especially acute when Transformers are deployed on hardware platforms equipped only with CPUs. To address this issue, we propose a novel method for accelerating self-attention at inference time that works with pretrained Transformer models out-of-the-box without requiring retraining. We experiment using our method to accelerate various long-sequence Transformers, including a leading LLaMA 2-based LLM, on various benchmarks and demonstrate a speedup of 2.73 7.63 while retaining 98.6% 99.6% of the accuracy of the original pretrained models. Transformers (Vaswani et al., 2017) have powered incredible advances in NLP, as exemplified by large language models (LLMs) such as GPT-4 and LLaMA 2. Increasingly LLMs are applied to exceptionally long input sequences, which enables many exciting applications such as long-form content creation, extended conversations, and large document search and analysis (OpenAI, 2023; Anthropic, 2023). While LLMs can be feasibly trained with expensive hardware accelerators (e.g. GPUs), they need to be deployed on commodity devices, which may only be equipped with CPUs. However, it is currently challenging to deploy LLMs on CPUs due to their high computation cost (Dice & Kogan, 2021). A significant computational bottleneck arises from the self-attention mechanism that is integral to Transformers - both time and space complexity are quadratic in the sequence length.

Large language models (LLMs) have provided a lot of exciting new capabilities in software development. However, the opaque nature of these models makes them difficult to reason about and inspect. Their opacity gives rise to potential security risks, as adversaries can train and deploy compromised models to disrupt the software development process in the victims' organization. This work presents an overview of the current state-of-the-art trojan attacks on large language models of code, with a focus on triggers -- the main design point of trojans -- with the aid of a novel unifying trigger taxonomy framework. We also aim to provide a uniform definition of the fundamental concepts in the area of trojans in Code LLMs. Finally, we draw implications of findings on how code models learn on trigger design.

In this paper, we introduce a simulacrum of hospital called Agent Hospital that simulates the entire process of treating illness. All patients, nurses, and doctors are autonomous agents powered by large language models (LLMs). Our central goal is to enable a doctor agent to learn how to treat illness within the simulacrum. To do so, we propose a method called MedAgent-Zero. As the simulacrum can simulate disease onset and progression based on knowledge bases and LLMs, doctor agents can keep accumulating experience from both successful and unsuccessful cases. Simulation experiments show that the treatment performance of doctor agents consistently improves on various tasks. More interestingly, the knowledge the doctor agents have acquired in Agent Hospital is applicable to real-world medicare benchmarks. After treating around ten thousand patients (real-world doctors may take over two years), the evolved doctor agent achieves a state-of-the-art accuracy of 93.06% on a subset of the MedQA dataset that covers major respiratory diseases. This work paves the way for advancing the applications of LLM-powered agent techniques in medical scenarios.