This article presents a general and flexible method for prompting a large language model (LLM) to reveal its (hidden) token input embedding up to homeomorphism. Moreover, this article provides strong theoretical justification -- a mathematical proof for generic LLMs -- for why this method should be expected to work. With this method in hand, we demonstrate its effectiveness by recovering the token subspace of Llemma-7B. The results of this paper apply not only to LLMs but also to general nonlinear autoregressive processes.
With the recent advancements in deep learning, semantic communication which transmits only task-oriented features, has rapidly emerged. However, since feature extraction relies on learning-based models, its performance fundamentally depends on the training dataset or tasks. For practical scenarios, it is essential to design a model that demonstrates robust performance regardless of dataset or tasks. In this correspondence, we propose a novel text transmission model that selects and transmits only a few characters and recovers the missing characters at the receiver using a large language model (LLM). Additionally, we propose a novel importance character extractor (ICE), which selects transmitted characters to enhance LLM recovery performance. Simulations demonstrate that the proposed filter selection by ICE outperforms random filter selection, which selects transmitted characters randomly. Moreover, the proposed model exhibits robust performance across different datasets and tasks and outperforms traditional bit-based communication in low signal-to-noise ratio conditions.
Large language model (LLM)-based test generation has gained attention in software engineering, yet most studies evaluate LLMs' ability to generate unit tests in a single attempt for a given language, missing the opportunity to leverage LLM diversity for more robust testing. This paper introduces PolyTest, a novel approach that enhances test generation by exploiting polyglot and temperature-controlled diversity. PolyTest systematically leverages these properties in two complementary ways: (1) Cross-lingual test generation, where tests are generated in multiple languages at zero temperature and then unified; (2) Diverse test sampling, where multiple test sets are generated within the same language at a higher temperature before unification. A key insight is that LLMs can generate diverse yet contradicting tests -- same input, different expected outputs -- across languages and generations. PolyTest mitigates inconsistencies by unifying test sets, fostering self-consistency and improving overall test quality. Unlike single-language or single-attempt approaches, PolyTest enhances testing without requiring on-the-fly execution, making it particularly beneficial for weaker-performing languages. We evaluate PolyTest on Llama3-70B, GPT-4o, and GPT-3.5 using EvalPlus, generating tests in five languages (Java, C, Python, JavaScript, and a CSV-based format) at temperature 0 and sampling multiple sets at temperature 1. We observe that LLMs frequently generate contradicting tests across settings, and that PolyTest significantly improves test quality across all considered metrics -- number of tests, passing rate, statement/branch coverage (up to +9.01%), and mutation score (up to +11.23%). Finally, PolyTest outperforms Pynguin in test generation, passing rate, and mutation score.
We present PANDORA, a novel diffusion-based policy learning framework designed specifically for dexterous robotic piano performance. Our approach employs a conditional U-Net architecture enhanced with FiLM-based global conditioning, which iteratively denoises noisy action sequences into smooth, high-dimensional trajectories. To achieve precise key execution coupled with expressive musical performance, we design a composite reward function that integrates task-specific accuracy, audio fidelity, and high-level semantic feedback from a large language model (LLM) oracle. The LLM oracle assesses musical expressiveness and stylistic nuances, enabling dynamic, hand-specific reward adjustments. Further augmented by a residual inverse-kinematics refinement policy, PANDORA achieves state-of-the-art performance in the ROBOPIANIST environment, significantly outperforming baselines in both precision and expressiveness. Ablation studies validate the critical contributions of diffusion-based denoising and LLM-driven semantic feedback in enhancing robotic musicianship. Videos available at: https://taco-group.github.io/PANDORA
Open-Ended Learning (OEL) autonomous robots can acquire new skills and knowledge through direct interaction with their environment, relying on mechanisms such as intrinsic motivations and self-generated goals to guide learning processes. OEL robots are highly relevant for applications as they can autonomously leverage acquired knowledge to perform tasks beneficial to human users in unstructured environments, addressing challenges unforeseen at design time. However, OEL robots face a significant limitation: their openness may lead them to waste time learning information that is irrelevant to tasks desired by specific users. Here, we propose a solution called `Purpose-Directed Open-Ended Learning' (POEL), based on the novel concept of `purpose' introduced in previous work. A purpose specifies what users want the robot to achieve. The key insight of this work is that purpose can focus OEL on learning self-generated classes of tasks that, while unknown during autonomous learning (as typical in OEL), involve objects relevant to the purpose. This concept is operationalised in a novel robot architecture capable of receiving a human purpose through speech-to-text, analysing the scene to identify objects, and using a Large Language Model to reason about which objects are purpose-relevant. These objects are then used to bias OEL exploration towards their spatial proximity and to self-generate rewards that favour interactions with them. The solution is tested in a simulated scenario where a camera-arm-gripper robot interacts freely with purpose-related and distractor objects. For the first time, the results demonstrate the potential advantages of purpose-focused OEL over state-of-the-art OEL methods, enabling robots to handle unstructured environments while steering their learning toward knowledge acquisition relevant to users.
Unmanned Surface Vessels (USVs) are essential for various maritime operations. USV mission planning approach offers autonomous solutions for monitoring, surveillance, and logistics. Existing approaches, which are based on static methods, struggle to adapt to dynamic environments, leading to suboptimal performance, higher costs, and increased risk of failure. This paper introduces a novel mission planning framework that uses Large Language Models (LLMs), such as GPT-4, to address these challenges. LLMs are proficient at understanding natural language commands, executing symbolic reasoning, and flexibly adjusting to changing situations. Our approach integrates LLMs into maritime mission planning to bridge the gap between high-level human instructions and executable plans, allowing real-time adaptation to environmental changes and unforeseen obstacles. In addition, feedback from low-level controllers is utilized to refine symbolic mission plans, ensuring robustness and adaptability. This framework improves the robustness and effectiveness of USV operations by integrating the power of symbolic planning with the reasoning abilities of LLMs. In addition, it simplifies the mission specification, allowing operators to focus on high-level objectives without requiring complex programming. The simulation results validate the proposed approach, demonstrating its ability to optimize mission execution while seamlessly adapting to dynamic maritime conditions.
In recent years, the development of Large Language Models (LLMs) has made significant breakthroughs in the field of natural language processing and has gradually been applied to the field of humanities and social sciences research. LLMs have a wide range of application value in the field of humanities and social sciences because of its strong text understanding, generation and reasoning capabilities. In humanities and social sciences research, LLMs can analyze large-scale text data and make inferences. This article analyzes the large language model DeepSeek-R1 from seven aspects: low-resource language translation, educational question-answering, student writing improvement in higher education, logical reasoning, educational measurement and psychometrics, public health policy analysis, and art education . Then we compare the answers given by DeepSeek-R1 in the seven aspects with the answers given by o1-preview. DeepSeek-R1 performs well in the humanities and social sciences, answering most questions correctly and logically, and can give reasonable analysis processes and explanations. Compared with o1-preview, it can automatically generate reasoning processes and provide more detailed explanations, which is suitable for beginners or people who need to have a detailed understanding of this knowledge, while o1-preview is more suitable for quick reading. Through analysis, it is found that LLM has broad application potential in the field of humanities and social sciences, and shows great advantages in improving text analysis efficiency, language communication and other fields. LLM's powerful language understanding and generation capabilities enable it to deeply explore complex problems in the field of humanities and social sciences, and provide innovative tools for academic research and practical applications.
Reasoning large language models are rapidly evolving across various domains. However, their capabilities in handling complex financial tasks still require in-depth exploration. In this paper, we introduce Fin-R1, a reasoning large language model specifically designed for the financial sector. Fin-R1 is built using a two-stage architecture, leveraging a financial reasoning dataset distilled and processed based on DeepSeek-R1. Through supervised fine-tuning (SFT) and reinforcement learning (RL) training, it demonstrates performance close to DeepSeek-R1 with a parameter size of 7 billion across a range of financial reasoning tasks. It achieves the state-of-the-art (SOTA) in the FinQA and ConvFinQA tasks between those LLMs in our evaluation, surpassing larger models in other tasks as well. Fin-R1 showcases strong reasoning and decision-making capabilities, providing solutions to various problems encountered in the financial domain. Our code is available at https://github.com/SUFE-AIFLM-Lab/Fin-R1.
ChatGPT, powered by a large language model (LLM), has revolutionized everyday human-computer interaction (HCI) since its 2022 release. While now used by millions around the world, a coherent pathway for evaluating the user experience (UX) ChatGPT offers remains missing. In this rapid review (N = 58), I explored how ChatGPT UX has been approached quantitatively so far. I focused on the independent variables (IVs) manipulated, the dependent variables (DVs) measured, and the methods used for measurement. Findings reveal trends, gaps, and emerging consensus in UX assessments. This work offers a first step towards synthesizing existing approaches to measuring ChatGPT UX, urgent trajectories to advance standardization and breadth, and two preliminary frameworks aimed at guiding future research and tool development. I seek to elevate the field of ChatGPT UX by empowering researchers and practitioners in optimizing user interactions with ChatGPT and similar LLM-based systems.
Multi-task semantic communication (SC) can reduce the computational resources in wireless systems since retraining is not required when switching between tasks. However, existing approaches typically rely on task-specific embeddings to identify the intended task, necessitating retraining the entire model when given a new task. Consequently, this drives the need for a multi-task SC system that can handle new tasks without additional training, known as zero-shot learning. Inspired by the superior zero-shot capabilities of large language models (LLMs), we leverage pre-trained instruction-tuned LLMs, referred to as fine-tuned language net (FLAN), to improve the generalization capability. We incorporate a mixture-of-experts (MoE) architecture in the FLAN model and propose MoE-FLAN-SC architecture for multi-task SC systems. Our proposed MoE-FLAN-SC architecture can further improve the performance of FLAN-T5 model without increasing the computational cost. Moreover, we design a multi-task feature extraction module (FEM) which can adaptively extract relevant features across various tasks given the provided features and signal-to-noise ratio (SNR). Simulation results show that our proposed MoE-FLAN-SC architecture outperforms three state-of-the-art models in terms of the average accuracy on four different unseen tasks.
The large language model (LLM)-as-judge paradigm has been used to meet the demand for a cheap, reliable, and fast evaluation of model outputs during AI system development and post-deployment monitoring. While judge models -- LLMs finetuned to specialize in assessing and critiquing model outputs -- have been touted as general purpose evaluators, they are typically evaluated only on non-contextual scenarios, such as instruction following. The omission of contextual settings -- those where external information is used as context to generate an output -- is surprising given the increasing prevalence of retrieval-augmented generation (RAG) and summarization use cases. Contextual assessment is uniquely challenging, as evaluation often depends on practitioner priorities, leading to conditional evaluation criteria (e.g., comparing responses based on factuality and then considering completeness if they are equally factual). To address the gap, we propose ContextualJudgeBench, a judge benchmark with 2,000 challenging response pairs across eight splits inspired by real-world contextual evaluation scenarios. We build our benchmark with a multi-pronged data construction pipeline that leverages both existing human annotations and model-based perturbations. Our comprehensive study across 11 judge models and 9 general purpose models, reveals that the contextual information and its assessment criteria present a significant challenge to even state-of-the-art models. For example, OpenAI's o1, the best-performing model, barely reaches 55% consistent accuracy.
The purpose of this paper is to examine whether large language models (LLMs) can understand what is good and evil with respect to judging good/evil reputation of celebrities. Specifically, we first apply a large language model (namely, ChatGPT) to the task of collecting sentences that mention the target celebrity from articles about celebrities on Web pages. Next, the collected sentences are categorized based on their contents by ChatGPT, where ChatGPT assigns a category name to each of those categories. Those assigned category names are referred to as "aspects" of each celebrity. Then, by applying the framework of retrieval augmented generation (RAG), we show that the large language model is quite effective in the task of judging good/evil reputation of aspects and descriptions of each celebrity. Finally, also in terms of proving the advantages of the proposed method over existing services incorporating RAG functions, we show that the proposed method of judging good/evil of aspects/descriptions of each celebrity significantly outperform an existing service incorporating RAG functions.
Background. Systematic reviews in comparative effectiveness research require timely evidence synthesis. Preprints accelerate knowledge dissemination but vary in quality, posing challenges for systematic reviews. Methods. We propose AutoConfidence (automated confidence assessment), an advanced framework for predicting preprint publication, which reduces reliance on manual curation and expands the range of predictors, including three key advancements: (1) automated data extraction using natural language processing techniques, (2) semantic embeddings of titles and abstracts, and (3) large language model (LLM)-driven evaluation scores. Additionally, we employed two prediction models: a random forest classifier for binary outcome and a survival cure model that predicts both binary outcome and publication risk over time. Results. The random forest classifier achieved AUROC 0.692 with LLM-driven scores, improving to 0.733 with semantic embeddings and 0.747 with article usage metrics. The survival cure model reached AUROC 0.716 with LLM-driven scores, improving to 0.731 with semantic embeddings. For publication risk prediction, it achieved a concordance index of 0.658, increasing to 0.667 with semantic embeddings. Conclusion. Our study advances the framework for preprint publication prediction through automated data extraction and multiple feature integration. By combining semantic embeddings with LLM-driven evaluations, AudoConfidence enhances predictive performance while reducing manual annotation burden. The framework has the potential to facilitate systematic incorporation of preprint articles in evidence-based medicine, supporting researchers in more effective evaluation and utilization of preprint resources.
In Large Language Model (LLM) serving, the KV-cache (KVC) bottleneck causes high tail Time-to-First-Token (TTFT) and Time-Between-Tokens (TBT), impairing user experience, particularly in time-sensitive applications. However, satisfying both TTFT and TBT service-level objectives (SLOs) is challenging. To address this, we propose a system, named CacheOPT for mitigating KV Cache competition, based on key insights from our measurements, incorporating novel components. First, it estimates a request's output length, bounding the deviation with a high specified probability, adjusted based on the request arrival rate. Second, it allocates the estimated KVC demand to a request, and reuses other requests' allocated KVC to avoid preemptions while reducing waiting time. Third, it proactively allocates KVC before instead of at the time a request exhausts its allocation and reserves KVC globally to prevent preemptions. Fourth, it chooses a request that has long TBT SLO, long job remaining time and short preemption time to preempt. Fifth, it selects the shortest-latency strategy between swapping and recomputation for preemptions. Experiments show that CacheOPT achieves up to 3.29$\times$ and 2.83$\times$ lower tail TBT and tail TTFT, 47\% and 53\% higher TTFT and TBT SLO attainments, and supports up to 1.58$\times$ higher request arrival rate than the state-of-the-art methods.
In this paper, we consider a mixed-prompt scenario for a large language model (LLM) inference serving system that supports diverse applications with both short prompts and long prompts and heterogeneous SLOs for iteration time. To improve throughput when handling long prompts, previous research introduces a chunking method, but has not addressed heterogeneous SLOs. To address the limitation, we propose AccelGen, a high-throughput LLM inference serving system with heterogeneous SLO guarantees for diverse applications. AccelGen introduces four core components: (1) SLO-guaranteed dynamic chunking, which dynamically adjusts chunk sizes to maximize GPU compute utilization while meeting iteration-level SLOs; (2) Iteration-level SLO-based task prioritization, which prioritizes tight-SLO requests and batches requests with similar SLOs; (3) Multi-resource-aware batching, which selects queued requests to maximize the utilizations of both GPU compute resource and key-value cache (KVC). Trace-driven real experiments demonstrate that AccelGen achieves 1.42-11.21X higher throughput, 1.43-13.71X higher goodput, 37-90% higher SLO attainment, and 1.61-12.22X lower response latency compared to the state-of-the-art approaches. It achieves performance near the Oracle, which optimally maximizes goodput.
Large language models (LLMs) have demonstrated remarkable capabilities in various natural language processing tasks. However, achieving strong performance in specialized domains like mathematical reasoning and non-English languages often requires extensive training on massive datasets. This paper investigates a contrasting approach: strategic fine-tuning on a small, high-quality, bilingual (English-French) dataset to enhance both the reasoning capabilities and French language proficiency of a large language model. Rather than relying on scale, we explore the hypothesis that targeted data curation and optimized training can achieve competitive, or even superior, performance. We demonstrate, through targeted supervised fine-tuning (SFT) on only 2,000 carefully selected samples, significant improvements in mathematical reasoning. Specifically, Pensez 7B exhibits an increase in accuracy of the base model up to 20% on the AIME25 and a 12% increase on a French MATH level 5 benchmark. These results challenge the prevailing assumption that massive datasets are aprerequisite for strong reasoning performance in LLMs, highlighting the potential of strategic data curation and optimized fine-tuning for enhancing both specialized skills and multilingual capabilities. Our findings have implications for the efficient development of high-performing, multilingual LLMs, especially in resource-constrained scenarios.
We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of external sources from an internal knowledge cache that is progressively updated to guide both query generation and evidence selection. This design mitigates bias-reinforcement loops and enables dynamic, trackable search exploration paths, thereby optimizing the trade-off between exploring diverse information and maintaining accuracy through autonomous agent decision-making. Our approach is evaluated on a broad range of open-domain question answering benchmarks, including multi-step tasks that mirror real-world scenarios where integrating information from multiple sources is critical, especially given the vulnerabilities of LLMs that lack explicit reasoning or planning capabilities. The results show that the proposed system not only outperforms single-step baselines regardless of task difficulty but also, compared to conventional iterative retrieval methods, demonstrates pronounced advantages in complex tasks through precise evidence-based reasoning and enhanced efficiency. The proposed system supports both competitive and collaborative sharing of updated context, enabling multi-agent extension. The benefits of multi-agent configurations become especially prominent as task difficulty increases. The number of convergence steps scales with task difficulty, suggesting cost-effective scalability.
With the rapid development of Large Language Models (LLMs), LLM-based agents have been widely adopted in various fields, becoming essential for autonomous decision-making and interactive tasks. However, current work typically relies on prompt design or fine-tuning strategies applied to vanilla LLMs, which often leads to limited effectiveness or suboptimal performance in complex agent-related environments. Although LLM optimization techniques can improve model performance across many general tasks, they lack specialized optimization towards critical agent functionalities such as long-term planning, dynamic environmental interaction, and complex decision-making. Although numerous recent studies have explored various strategies to optimize LLM-based agents for complex agent tasks, a systematic review summarizing and comparing these methods from a holistic perspective is still lacking. In this survey, we provide a comprehensive review of LLM-based agent optimization approaches, categorizing them into parameter-driven and parameter-free methods. We first focus on parameter-driven optimization, covering fine-tuning-based optimization, reinforcement learning-based optimization, and hybrid strategies, analyzing key aspects such as trajectory data construction, fine-tuning techniques, reward function design, and optimization algorithms. Additionally, we briefly discuss parameter-free strategies that optimize agent behavior through prompt engineering and external knowledge retrieval. Finally, we summarize the datasets and benchmarks used for evaluation and tuning, review key applications of LLM-based agents, and discuss major challenges and promising future directions. Our repository for related references is available at https://github.com/YoungDubbyDu/LLM-Agent-Optimization.
Traffic Signal Control (TSC) plays a critical role in urban traffic management by optimizing traffic flow and mitigating congestion. While Large Language Models (LLMs) have recently emerged as promising tools for TSC due to their exceptional problem-solving and generalization capabilities, existing approaches fail to address the essential need for inter-agent coordination, limiting their effectiveness in achieving network-wide optimization. To bridge this gap, we propose CoLLMLight, a cooperative LLM agent framework for TSC. Specifically, we first construct a structured spatiotemporal graph to capture real-time traffic dynamics and spatial relationships among neighboring intersections, enabling the LLM to reason about complex traffic interactions. Moreover, we introduce a complexity-aware reasoning mechanism that dynamically adapts reasoning depth based on real-time traffic conditions, ensuring optimal computational efficiency without sacrificing decision quality. Besides, we propose a fine-tuning strategy that leverages iterative simulation-driven data collection and environmental feedback to build a lightweight LLM tailored for cooperative TSC. Extensive experiments on both synthetic and real-world datasets demonstrate that CoLLMLight outperforms state-of-the-art methods in diverse traffic scenarios, showcasing its effectiveness, scalability, and robustness.
The foundation model has heralded a new era in artificial intelligence, pretraining a single model to offer cross-domain transferability on different datasets. Graph neural networks excel at learning graph data, the omnipresent non-Euclidean structure, but often lack the generalization capacity. Hence, graph foundation model is drawing increasing attention, and recent efforts have been made to leverage Large Language Models. On the one hand, existing studies primarily focus on text-attributed graphs, while a wider range of real graphs do not contain fruitful textual attributes. On the other hand, the sequential graph description tailored for the Large Language Model neglects the structural complexity, which is a predominant characteristic of the graph. Such limitations motivate an important question: Can we go beyond Large Language Models, and pretrain a universal model to learn the structural knowledge for any graph? The answer in the language or vision domain is a shared vocabulary. We observe the fact that there also exist shared substructures underlying graph domain, and thereby open a new opportunity of graph foundation model with structural vocabulary. The key innovation is the discovery of a simple yet effective structural vocabulary of trees and cycles, and we explore its inherent connection to Riemannian geometry. Herein, we present a universal pretraining model, RiemannGFM. Concretely, we first construct a novel product bundle to incorporate the diverse geometries of the vocabulary. Then, on this constructed space, we stack Riemannian layers where the structural vocabulary, regardless of specific graph, is learned in Riemannian manifold offering cross-domain transferability. Extensive experiments show the effectiveness of RiemannGFM on a diversity of real graphs.