Time series Forecasting with large language models (LLMs) requires bridging numerical patterns and natural language. Effective forecasting on LLM often relies on extensive pre-processing and fine-tuning. Recent studies show that a frozen LLM can rival specialized forecasters when supplied with a carefully engineered natural-language prompt, but crafting such a prompt for each task is itself onerous and ad-hoc. We introduce FLAIRR-TS, a test-time prompt optimization framework that utilizes an agentic system: a Forecaster-agent generates forecasts using an initial prompt, which is then refined by a refiner agent, informed by past outputs and retrieved analogs. This adaptive prompting generalizes across domains using creative prompt templates and generates high-quality forecasts without intermediate code generation. Experiments on benchmark datasets show FLAIRR-TS improves forecasting over static prompting and retrieval-augmented baselines, approaching the performance of specialized prompts.FLAIRR-TS provides a practical alternative to fine-tuning, achieving strong performance via its agentic approach to adaptive prompt refinement and retrieval.
论文检索
输入标题、作者或关键词，从 2,101 篇学术成果中精准定位
In recent months, substantial progress has been made in complex reasoning of Large Language Models (LLMs), particularly through the application of test-time scaling. Notable examples include, though are not limited to, OpenAI’s o1/o3/o4 series and DeepSeek-R1. When responding to a query, these models generate an extended reasoning trajectory, during which the model explores, reflects, backtracks, and self-verifies before arriving at a conclusion. However, fine-tuning models with such reasoning trajectories may not always be optimal. Our findings indicate that not all components within these reasoning trajectories contribute positively to the reasoning process; in fact, some components may affect the overall performance negatively. In this study, we divide a reasoning trajectory into individual subtrajectories and develop a “5+2” framework to: (1) systematically identify suboptimal subtrajectories within the reasoning trajectory based on five human-established criteria; (2) assess the independence of the suboptimal subtrajectories identified in (1) from the subsequent content, ensuring that their elimination does not compromise overall flow and coherence of the reasoning process. Additionally, a sampling algorithm, built upon the “5+2” framework, is employed to select data whose reasoning process is free from suboptimal subtrajectories to the highest degree. Experimental results demonstrate that our method can reduce the number of suboptimal subtrajectories by 25.9% during the inference. Furthermore, our method achieves an average accuracy of 58.92% on highly challenging AIME24, AIME25, AMC24 and MATH500 benchmarks with only two thirds of training data, surpassing the average accuracy of 58.06% achieved with the entire data, and outperforming open-source datasets, including s1K-1.1, Light-R1-SFT-stage-1, OpenR1-Math-94k, and OpenThoughts-114k, when fine-tuning Qwen2.5-Math-7B. Finally, we have validated the efficacy of our method under resource-constrained scenarios, where it exhibits performance improvements across different maximum inference token limits: 2k, 4k, 8k, and 16k tokens.
This paper studies the problem of time series forecasting, which aims to generate future predictions given historical trajectories. Recent researchers have applied large language models (LLMs) into time series forecasting, which usually align the time series space with textual space and output future predictions with strong autoregressive reasoning abilities. Despite their remarkable progress, these approaches usually lack an understanding of holistic temporal patterns with potential error accumulation. Towards this end, this paper proposes a simple yet effective framework that marries \underline{\text{L}}arg\underline{\text{e}} Langu\underline{\text{a}}ge Diffusion Model with time series \underline{\text{f}}orecasting (LEAF). The core of our framework is to generate future predictions with a diffusion model from a holistic view. In particular, we first introduce a tokenization module to convert time series into tokens and then adopt the language diffusion models to capture the temporal dependencies. In this way, we can transform masked time series into all the predictions with the remasking strategy. Extensive experiments on various benchmark datasets validate the effectiveness of the proposed LEAF in comparison to various baselines.
STARQA: A Question Answering Dataset for Complex Analytical Reasoning over Structured Databases
PDF ↗Our goal is to assess how well current Text2SQL systems support SQL analysts in their primary work of performing complex analytics on specialized relational databases. Although several benchmarks evaluate Text2SQL models, the complexity of questions (and the output SQL queries) in most datasets is inherently limited – they do not focus on intents involving analytics and reasoning. In response, we present STARQA, the first public human-created dataset focused on complex analytical questions and answers (involving nested joins, time series analytics, statistical operations, and more) on three specialized-domain databases. In addition to standard Text2SQL baselines, we also evaluate a novel approach (Text2SQLCode) that decomposes the task through a combination of SQL and Python: SQL is responsible for data fetch, and Python more naturally performs reasoning. Our results demonstrate that both existing Text2SQL systems and our Text2SQLCode approach find STARQA questions quite challenging, even though Text2SQLCode achieves better performance on the more difficult questions. Further analyses assess the typical errors made by existing systems and charts a research path for pushing the capabilities of real-world systems.
It has been demonstrated that incorporating external information as textual modality can effectively improve time series forecasting accuracy. However, current multi-modal models ignore the dynamic and different relations between time series patterns and textual features, which leads to poor performance in temporal-textual feature fusion. In this paper, we propose a lightweight and model-agnostic temporal-textual fusion framework named Cross-MoE. It replaces Cross Attention with Cross-Ranker to reduce computational complexity, and enhances modality-aware correlation memorization with Mixture-of-Experts (MoE) networks to tolerate the distributional shifts in time series. The experimental results demonstrate a 8.78% average reduction in Mean Squared Error (MSE) compared to the SOTA multi-modal time series framework. Notably, our method requires only 75% of computational overhead and 12.5% of activated parameters compared with Cross Attention mechanism. Our codes are available at https://github.com/Kilosigh/Cross-MoE.git
Reasoning over temporal and numerical data, such as time series, is a crucial aspect of fact-checking. While many systems have recently been developed to handle this form of evidence, their evaluation remains limited by existing datasets, which often lack structured evidence, provide insufficient justifications for verdicts, or rely on synthetic claims. In this paper, we introduce TSVer, a new benchmark dataset for fact verification focusing on temporal and numerical reasoning with time-series evidence. TSVer contains 304 real-world claims sourced from 41 fact-checking organizations and a curated database of 400 time series covering diverse domains. Each claim is annotated with time frames across all pertinent time series, along with a verdict and justifications reflecting how the evidence is used to reach the verdict. Using an LLM-assisted multi-step annotation process, we improve the quality of our annotations and achieve an inter-annotator agreement of \kappa = 0.77 on verdicts. We also develop a baseline for verifying claims against time-series evidence and show that even the state-of-the-art reasoning models like Gemini-2.5-Pro are challenged by time series, achieving a 63.57 accuracy score on verdicts and an \mathrm{Ev}^{2}\mathrm{R} score of 48.63 on verdict justifications.
Investigating the interaction of linguistic and mathematical reasoning in language models using multilingual number puzzles
PDF ↗Across languages, numeral systems vary widely in how they construct and combine numbers. While humans consistently learn to navigate this diversity, large language models (LLMs) struggle with linguistic-mathematical puzzles involving cross-linguistic numeral systems, which humans can learn to solve successfully. We investigate why this task is difficult for LLMs through a series of experiments that untangle the linguistic and mathematical aspects of numbers in language. Our experiments establish that models cannot consistently solve such problems unless the mathematical operations in the problems are explicitly marked using known symbols (+, \times, etc, as in “twenty + three”). In further ablation studies, we probe how individual parameters of numeral construction and combination affect performance. While humans use their linguistic understanding of numbers to make inferences about the implicit compositional structure of numerals, LLMs seem to lack this notion of implicit numeral structure. We conclude that the ability to flexibly infer compositional rules from implicit patterns in human-scale data remains an open challenge for current reasoning models.
Large language models (LLMs) can now access a wide range of external tools, thanks to the Model Context Protocol (MCP). This greatly expands their abilities as various agents. However, LLMs rely entirely on the text descriptions of tools to decide which ones to use—a process that is surprisingly fragile. In this work, we expose a vulnerability in prevalent tool/function-calling protocols by investigating a series of edits to tool descriptions, some of which can drastically increase a tool’s usage from LLMs when competing with alternatives. Through controlled experiments, we show that tools with properly edited descriptions receive **over 10 times more usage** from GPT-4.1 and Qwen2.5-7B than tools with original descriptions. We further evaluate how various edits to tool descriptions perform when competing directly with one another and how these trends generalize or differ across a broader set of 17 different models. These phenomena, while giving developers a powerful way to promote their tools, underscore the need for a more reliable foundation for agentic LLMs to select and utilize tools and resources. Our code is publicly available at [https://github.com/kazemf78/llm-unreliable-tool-preferences](https://github.com/kazemf78/llm-unreliable-tool-preferences).
In this work, we present the first study to explore inference-time scaling on table reasoning tasks. We develop and evaluate two post-training strategies to enable inference-time scaling: distillation from frontier model reasoning traces and reinforcement learning with verifiable rewards (RLVR). For distillation, we introduce a large-scale dataset of reasoning traces generated by DeepSeek-R1, which we use to fine-tune LLMs into the Table-R1-SFT model. For RLVR, we propose task-specific verifiable reward functions and apply the GRPO algorithm to obtain the Table-R1-Zero model. We evaluate our Table-R1-series models across diverse table reasoning tasks, including short-form QA, fact verification, and free-form QA. Notably, the Table-R1-Zero model matches or exceeds the performance of GPT-4.1 and DeepSeek-R1, while using only a 7B-parameter LLM. It also demonstrates strong generalization to out-of-domain datasets. Extensive ablation and qualitative analyses reveal the benefits of instruction tuning, model architecture choices, and cross-task generalization, as well as emergence of essential table reasoning skills during RL training.
Speech large language models (LLMs) have emerged as a prominent research focus in speech processing. In this work, we introduce VocalNet, a series of high-performance speech LLMs featuring a scalable and model-agnostic training framework as well as a novel multi-token prediction (MTP) paradigm for speech generation. We first propose an efficient two-stage training framework that enables LLMs to acquire real-time speech interaction capabilities. Through extensive experiments on various training configurations, we ensure both simplicity and effectiveness in the training strategy. Furthermore, inspired by advances in language modeling, we introduce MTP into the domain of speech LLMs—an alternative to traditional next-token prediction (NTP)—which enables the model to predict multiple future tokens at each step. Through systematic analysis and improved implementation, we show that MTP not only accelerates inference speed but also significantly enhances speech quality. Experimental results demonstrate that VocalNet achieves performance comparable to state-of-the-art Omni LLMs while outperforming existing open-source speech LLMs, despite using limited training data.
Software debugging is a time-consuming endeavor involving a series of steps, such as fault localization and patch generation, each requiring thorough analysis and a deep understanding of the underlying logic. While large language models (LLMs) demonstrate promising potential in coding tasks, their performance in debugging remains limited. Current LLM-based methods often focus on isolated steps and struggle with complex bugs. In this paper, we propose the first end-to-end framework, UniDebugger, for unified debugging through multi-agent synergy. It mimics the entire cognitive processes of developers, with each agent specialized as a particular component of this process rather than mirroring the actions of an independent expert as in previous multi-agent systems. Agents are coordinated through a three-level design, following a cognitive model of debugging, allowing adaptive handling of bugs with varying complexities. Experiments on extensive benchmarks demonstrate that UniDebugger significantly outperforms state-of-the-art repair methods, fixing 1.25x to 2.56x bugs on the repo-level benchmark, Defects4J. This performance is achieved without requiring ground-truth root-cause code statements, unlike the baselines. Our source code is available on an anonymous link: https://github.com/BEbillionaireUSD/UniDebugger.
Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their further evolution is often hampered by the scarcity of high-quality training data and the heavy reliance of traditional methods on expert-labeled data. This reliance sets a ceiling on LLM performance and is particularly challenging in low data resource scenarios where extensive supervision is unavailable. To address this issue, we propose a novel paradigm named LANCE (**LAN**guage models as **C**ontinuous self-**E**volving data engineers) that enables LLMs to train themselves by autonomously generating, cleaning, reviewing, and annotating data with preference information. Our approach demonstrates that LLMs can serve as continuous self-evolving data engineers, significantly reducing the time and cost of post-training data construction. Through iterative fine-tuning on Qwen2 series models, we validate the effectiveness of LANCE across various tasks, showing that it can maintain high-quality data generation and continuously improve model performance. Across multiple benchmark dimensions, LANCE results in an average score enhancement of **3.64** for Qwen2-7B and **1.75** for Qwen2-7B-Instruct. This autonomous data construction paradigm not only lessens reliance on human experts or external models but also ensures data aligns with human preferences, offering a scalable path for LLM self-improvement, especially in contexts with limited supervisory data. Code is available at: https://github.com/Control-derek/LANCE.
Existing reinforcement learning (RL) strategies based on outcome supervision have proven effective in enhancing the performance of large language models (LLMs) for code generation. While reinforcement learning based on process supervision shows great potential in multi-step reasoning tasks, its effectiveness in the field of code generation still lacks sufficient exploration and verification. The primary obstacle stems from the resource-intensive nature of constructing a high-quality process-supervised reward dataset, which requires substantial human expertise and computational resources. To overcome this challenge, this paper proposes a “mutation/refactoring-execution verification” strategy. Specifically, the teacher model is used to mutate and refactor the statement lines or blocks, and the execution results of the compiler are used to automatically label them, thus generating a process-supervised reward dataset. Based on this dataset, we have carried out a series of RL experiments. The experimental results show that, compared with the method relying only on outcome supervision, reinforcement learning based on process supervision performs better in handling complex code generation tasks. In addition, this paper for the first time confirms the advantages of the Direct Preference Optimization (DPO) method in the RL task of code generation based on process supervision, providing new ideas and directions for code generation research.
EcoTune: Token-Efficient Multi-Fidelity Hyperparameter Optimization for Large Language Model Inference
PDF ↗Tuning inference hyperparameters, such as temperature and maximum output tokens, on downstream tasks can enhance inference performance. However, directly applying hyperparameter optimization to these hyperparameters is token-expensive. Multi-fidelity optimization improves HPO efficiency with low-fidelity evaluations, but its static scheduling strategies ignore token consumption, leading to high costs. To address these limitations, we propose a token-efficient multi-fidelity optimization method, which enhances inference performance and minimizes token usage. Our method is empowered by (i) a token-based fidelity definition with explicit token cost modeling on configurations; (ii) a novel Token-Aware Expected Improvement acquisition function that selects configurations based on performance gain per token; and (iii) a dynamic fidelity scheduling mechanism that adapts to real-time budget status. We evaluate our method on LLaMA-2 and LLaMA-3 series across MMLU, Humaneval, MedQA, and OpenBookQA. Our method improves over the HELM leaderboard by 7.1%, 24.3%, 21.9%, and 4.6%, respectively. Compared to existing multi-fidelity HPO baselines, our method reduces token consumption by over 80% while maintaining or surpassing performance, demonstrating the state-of-the-art token efficiency for inference-time optimization.
ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration
PDF ↗Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in vision-language understanding. Recently, with the integration of test-time scaling techniques, these models have also shown strong potential in visual reasoning. However, most existing reasoning approaches remain text-level in nature: MLLMs are prompted to explore various combinations of textual tokens via their underlying language model, while the visual input remains fixed throughout the reasoning process. This paradigm limits the model’s ability to fully exploit rich visual information, particularly when dealing with images containing numerous fine-grained elements. In such cases, vision-level reasoning becomes crucial—where models dynamically zoom into specific regions of the image to gather detailed visual cues necessary for accurate decision-making. In this paper, we propose Zoom Eye, a training-free, model-agnostic tree search algorithm tailored for vision-level reasoning. Zoom Eye treats an image as a hierarchical tree structure, where each child node represents a zoomed-in sub-region of its parent, and the root corresponds to the full image. The algorithm enables MLLMs to simulate human-like zooming behavior by navigating from root to leaf nodes in search of task-relevant visual evidence. We experiment on a series of elaborate high-resolution benchmarks and the results demonstrate that Zoom Eye not only consistently improves the performance of a series of MLLMs with large margin (e.g., InternVL2.5-8B increases by 15.71% and 17.69% on HR-Bench) but also enables small 3-8B MLLMs to outperform strong large models such as GPT-4o.
Contrastive Language–Image Pre-training (CLIP) has recently demonstrated remarkable success in aligning vision and language. Aligning time series with text leverages the rich semantic cues of language to enhance interpretability and generalization, addressing a largely underexplored area of research. Although applying the CLIP training paradigm to time-series and language pairs is promising, it may result in label collapse due to the sparse semantic annotations and the absence of visual cues in time-series data. To address this, we introduce Time Series CLIP (TS-CLIP), a novel approach that tackles label collapse using a synonym bank mechanism. Synonym bank exploits word analogy phenomena to generate potential synonym embeddings as alignment targets. Specifically, the synonym bank facilitates aligning time series with a word distribution instead of a precise textual description. We conducted extensive zero-shot and few-shot experiments on 128 sub-datasets from the UCR archive. The results show that TS-CLIP achieves state-of-the-art (SOTA) performance in zero-shot settings on 51 datasets. Comprehensive ablation studies and visualization analyzes reveal that TS-CLIP effectively aligns time series with natural language. To the best of our knowledge, this is the first foundational model to achieve general time series and natural language alignment. TS-CLIP introduces a new paradigm for the semantic understanding of time series and opens the possibility of integrating the time series modality into multimodal large models.
We introduce SensorLLM, a two-stage framework that enables Large Language Models (LLMs) to perform human activity recognition (HAR) from sensor time-series data. Despite their strong reasoning and generalization capabilities, LLMs remain underutilized for motion sensor data due to the lack of semantic context in time-series, computational constraints, and challenges in processing numerical inputs. SensorLLM addresses these limitations through a Sensor-Language Alignment stage, where the model aligns sensor inputs with trend descriptions. Special tokens are introduced to mark channel boundaries. This alignment enables LLMs to capture numerical variations, channel-specific features, and data of varying durations, without requiring human annotations. In the subsequent Task-Aware Tuning stage, we refine the model for HAR classification, achieving performance that matches or surpasses state-of-the-art methods. Our results demonstrate that SensorLLM evolves into an effective sensor learner, reasoner, and classifier through human-intuitive Sensor-Language Alignment, generalizing across diverse HAR datasets. We believe this work establishes a foundation for future research on time-series and text alignment, paving the way for foundation models in sensor data analysis. Our codes are available at https://github.com/zechenli03/SensorLLM.
Applications · Chemistry and Drug Discovery
Machine learning has promised to change the landscape of laboratory chemistry, with impressive results in molecular property prediction and reaction retro-synthesis. However, chemical datasets are often inaccessible to the machine learning community as they tend to require cleaning, thorough understanding of the chemistry, or are simply not available. In this paper, we introduce a novel dataset for yield prediction, providing the first-ever transient flow dataset for machine learning benchmarking, covering over 1200 process conditions. While previous datasets focus on discrete parameters, our experimental set-up allow us to sample a large number of continuous process conditions, generating new challenges for machine learning models. We focus on solvent selection, a task that is particularly difficult to model theoretically and therefore ripe for machine learning applications. We showcase benchmarking for regression algorithms, transfer-learning approaches, feature engineering, and active learning, with important applications towards solvent replacement and sustainable manufacturing.
Applications · Time Series
In-context learning, the ability of large language models to perform tasks using only examples provided in the prompt, has recently been adapted for time series forecasting. This paradigm enables zero-shot prediction, where past values serve as context for forecasting future values, making powerful forecasting tools accessible to non-experts and increasing the performance when training data are scarce. Most existing zero-shot forecasting approaches rely on transformer architectures, which, despite their success in language, often fall short of expectations in time series forecasting, where recurrent models like LSTMs frequently have the edge. Conversely, while LSTMs are well-suited for time series modeling due to their state-tracking capabilities, they lack strong in-context learning abilities. We introduce *TiRex* that closes this gap by leveraging xLSTM, an enhanced LSTM with competitive in-context learning skills. Unlike transformers, state-space models, or parallelizable RNNs such as RWKV, TiRex retains state tracking, a critical property for long-horizon forecasting. To further facilitate its state-tracking ability, we propose a training-time masking strategy called CPM. TiRex sets a new state of the art in zero-shot time series forecasting on the Hugging Face benchmarks *GiftEval* and *Chronos-ZS*, outperforming significantly larger models including *TabPFN-TS* (Prior Labs), *Chronos Bolt* (Amazon), *TimesFM* (Google), and *Moirai* (Salesforce) across both short- and long-term forecasts.
Computer Vision · 3D Rendering & Reconstruction
In-the-wild photo collections often contain limited volumes of imagery and exhibit multiple appearances, e.g., taken at different times of day or seasons, posing significant challenges to scene reconstruction and novel view synthesis. Although recent adaptations of Neural Radiance Field (NeRF) and 3D Gaussian Splatting (3DGS) have improved in these areas, they tend to oversmooth and are prone to overfitting. In this paper, we present MS-GS, a novel framework designed with \textbf{M}ulti-appearance capabilities in \textbf{S}parse-view scenarios using 3D\textbf{GS}. To address the lack of support due to sparse initializations, our approach is built on the geometric priors elicited from monocular depth estimations. The key lies in extracting and utilizing local semantic regions with a Structure-from-Motion (SfM) points anchored algorithm for reliable alignment and geometry cues. Then, to introduce multi-view constraints, we propose a series of geometry-guided supervision steps at virtual views in pixel and feature levels to encourage 3D consistency and reduce overfitting. We also introduce a dataset and an in-the-wild experiment setting to set up more realistic benchmarks. We demonstrate that MS-GS achieves photorealistic renderings under various challenging sparse-view and multi-appearance conditions, and outperforms existing approaches significantly across different datasets.