{"total":82,"rows":[{"id":"2503.16858","title":"MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering","created":"2025-03-21","cited_by_count":55,"area":"lr"},{"id":"2503.01013","title":"TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop","created":"2025-03-02","cited_by_count":39,"area":null},{"id":"2509.22295","title":"Aurora: Towards Universal Generative Multimodal Time Series Forecasting","created":"2025-09-26","cited_by_count":29,"area":null},{"id":"2509.24803","title":"TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models","created":"2025-09-29","cited_by_count":27,"area":null},{"id":"2601.13653","title":"TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation","created":"2026-01-20","cited_by_count":26,"area":"lr"},{"id":"2503.13709","title":"Multi-modal Time Series Analysis: A Tutorial and Survey","created":"2025-03-17","cited_by_count":24,"area":null},{"id":"2509.11575","title":"A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models","created":"2025-09-15","cited_by_count":21,"area":"lr"},{"id":"2503.11835","title":"How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook","created":"2025-03-14","cited_by_count":20,"area":null},{"id":"2506.13705","title":"TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning","created":"2025-06-16","cited_by_count":18,"area":"lr"},{"id":"2601.18744","title":"TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models","created":"2026-01-26","cited_by_count":18,"area":"lr"},{"id":"2510.03255","title":"SciTS: Scientific Time Series Understanding and Generation with LLMs","created":"2025-09-26","cited_by_count":15,"area":"lr"},{"id":"2509.05215","title":"BEDTime: A Unified Benchmark for Automatically Describing Time Series","created":"2025-09-05","cited_by_count":12,"area":null},{"id":"2601.23204","title":"TSAQA: Time Series Analysis Question And Answering Benchmark","created":"2026-01-30","cited_by_count":11,"area":null},{"id":"2603.06638","title":"HEARTS: Benchmarking LLM Reasoning on Health Time Series","created":"2026-02-25","cited_by_count":11,"area":"lr"},{"id":"2510.07432","title":"TS-Agent: Understanding and Reasoning Over Raw Time Series via Iterative Insight Gathering","created":"2025-10-08","cited_by_count":9,"area":"lr"},{"id":"2507.15066","title":"Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback","created":"2025-07-20","cited_by_count":8,"area":null},{"id":"2505.18411","title":"DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understanding","created":"2025-05-23","cited_by_count":7,"area":"mllm"},{"id":"2601.03248","title":"STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning","created":"2026-01-06","cited_by_count":7,"area":"lr"},{"id":"2602.17149","title":"TimeOmni-VL: Unified Models for Time Series Understanding and Generation","created":"2026-02-19","cited_by_count":7,"area":null},{"id":"2607.06973","title":"Rethinking Multimodal Time-Series Forecasting Evaluation","created":"2026-07-08","cited_by_count":7,"area":null},{"id":"2604.10291","title":"TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale","created":"2026-04-11","cited_by_count":6,"area":"lr"},{"id":"2604.21199","title":"ARFBench: Benchmarking Time Series Question Answering Ability for Software Incident Response","created":"2026-04-23","cited_by_count":6,"area":null},{"id":"2510.01116","title":"Eliciting Chain-of-Thought Reasoning for Time Series Analysis using Reinforcement Learning","created":"2025-10-01","cited_by_count":5,"area":"lr"},{"id":"2510.06063","title":"TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2511.08616","title":"Reasoning on Time-Series for Financial Technical Analysis","created":"2025-11-06","cited_by_count":5,"area":"lr"},{"id":"2506.12412","title":"Cross-Domain Conditional Diffusion Models for Time Series Imputation","created":"2025-06-14","cited_by_count":4,"area":"diffusion"},{"id":"2509.24378","title":"AXIS: Explainable Time Series Anomaly Detection with Large Language Models","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2602.18645","title":"Adaptive Time Series Reasoning via Segment Selection","created":"2026-02-20","cited_by_count":4,"area":"lr"},{"id":"2603.01042","title":"Thoth: Mid-Training Bridges LLMs to Time Series Understanding","created":"2026-03-01","cited_by_count":4,"area":null},{"id":"2607.09880","title":"CLIR-Bench: Benchmarking Multimodal Question Answering over Irregular Clinical Time Series","created":"2026-07-10","cited_by_count":4,"area":null},{"id":"2506.20073","title":"A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs","created":"2025-06-25","cited_by_count":3,"area":"lr"},{"id":"2510.07858","title":"Augur: Modeling Covariate Causal Associations in Time Series via Large Language Models","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2511.06344","title":"TimeSense:Making Large Language Models Proficient in Time-Series Analysis","created":"2025-11-09","cited_by_count":3,"area":"lr"},{"id":"2602.07830","title":"Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning","created":"2026-02-08","cited_by_count":3,"area":"lr"},{"id":"2606.05404","title":"Harnessing Generalist Agents for Contextualized Time Series","created":"2026-06-03","cited_by_count":3,"area":"agents"},{"id":"2506.11250","title":"Can Time-Series Foundation Models Perform Building Energy Management Tasks?","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2510.16980","title":"Towards Interpretable and Trustworthy Time Series Reasoning: A BlueSky Vision","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2602.19455","title":"SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoning","created":"2026-02-23","cited_by_count":2,"area":"lr"},{"id":"2605.25045","title":"AION: Next-Generation Tasks and Practical Harness for Time Series","created":"2026-05-24","cited_by_count":2,"area":null},{"id":"2605.29401","title":"Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2607.08940","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2609.15087","title":"Beyond Numerical Time Series: A Unified Benchmark for Multimodal Forecasting with Heterogeneous Context","created":"2026-09-14","cited_by_count":2,"area":null},{"id":"2512.22627","title":"Chain-of-thought Reviewing and Correction for Time Series Question Answering","created":"2025-12-27","cited_by_count":1,"area":"lr"},{"id":"2602.19919","title":"Janus-Q: End-to-End Event-Driven Trading via Hierarchical-Gated Reward Modeling","created":"2026-02-23","cited_by_count":1,"area":"alignment"},{"id":"2604.24935","title":"CAN-QA: A Question-Answering Benchmark for Reasoning over In-Vehicle CAN Traffic","created":"2026-04-27","cited_by_count":1,"area":"lr"},{"id":"2605.08614","title":"DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2606.15107","title":"Towards Verifiable Agentic Data Science: Solving Irregular TSQA Via Tool-Grounded Reasoning","created":"2026-06-13","cited_by_count":1,"area":"lr"},{"id":"2607.14109","title":"ReasonLab: A Controlled and Auditable Evaluation of Prompting Techniques for Multiple-Choice QA","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2608.05238","title":"Decoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Language","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.27182","title":"TraceBench: Controlled Evaluation of LLM Agents for Time-Series Root-Cause Attribution","created":"2026-08-27","cited_by_count":1,"area":"agents"},{"id":"2506.11512","title":"From Time Series Analysis to Question Answering: A Survey in the LLM Era","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2508.20578","title":"Human-AI Collaborative Bot Detection in MMORPGs","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2509.20007","title":"DiffNator: Generating Structured Explanations of Time-Series Differences","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2509.25696","title":"Can VLM Pseudo-Labels Train a Time-Series QA Model That Outperforms the VLM?","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2602.17001","title":"Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2602.20494","title":"KairosVL: Orchestrating Time Series and Semantics for Unified Reasoning","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2604.23446","title":"IndustryAssetEQA: A Neurosymbolic Operational Intelligence System for Embodied Question Answering in Industrial Asset Maintenance","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.28866","title":"Continuity and Ordinality Matter: Constraining Time Series Tokens for Effective Time Series Analysis with Large Language Models","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.13624","title":"Beyond Uniform Tokens: Adaptive Compression for Time Series Language Models","created":"2026-06-11","cited_by_count":0,"area":"inference"},{"id":"2606.18986","title":"Beyond Tokenization: Direct Timestep Embedding and Contrastive Alignment for Time-Series Question Answering","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.24950","title":"MacroLens: A Multi-Task Benchmark for Contextual Financial Reasoning under Macroeconomic Scenarios","created":"2026-06-23","cited_by_count":0,"area":"lr"},{"id":"2608.14270","title":"TimeSage-EV: A Live Benchmark for Agentic Time Series Analysis in Evolving Environments","created":"2026-08-14","cited_by_count":0,"area":"agents"},{"id":"2608.23473","title":"MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters","created":"2026-08-24","cited_by_count":0,"area":"agents"},{"id":"2608.24910","title":"From Plots to Words: Model-Aware Multimodal Explanations as a Foundation for Accessible, Non-Visual Interaction","created":"2026-07-22","cited_by_count":0,"area":"mllm"},{"id":"2609.06117","title":"STQA: A Benchmark for Stock-Focused Tabular Question Answering over Historical and Forecasted Data","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.06976","title":"HealthLoopQA: A Context-Aware Question Answering Benchmark for Interpreting Wearable Monitoring Data in Diabetes Care","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.13457","title":"TimeThink: Eliciting Compositional Reasoning in Timeseries Large Language Models","created":"2026-09-11","cited_by_count":0,"area":"lr"},{"id":"2609.14142","title":"T-SMART: Mechanism-Level Attribution for Tool-Augmented Time-Series Question Answering","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.18812","title":"WaveTLM: Reliable Time-Series Language Modeling through Task Compilation","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.20836","title":"PhysioBench: A Unified Benchmark for Physiological Signal Question Answering","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.24677","title":"TimeLitmus: A Diagnostic Benchmark for Cross-Modal Understanding and Explanation Faithfulness in Event-Conditioned Time-Series Prediction","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.26389","title":"TimeInteract: Towards Real-Time Interactive Intelligence for Streaming Time Series","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.27277","title":"TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.31448","title":"ViSTA: A Simple Bridge Extends Visual Alignment to Clinical Time-Series Understanding in Multimodal LLMs","created":"2026-09-25","cited_by_count":0,"area":"mllm"},{"id":"2609.40265","title":"OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.04407","title":"TimeNet: An Extensible Unified Data Infrastructure for Next-Generation Temporal Foundation Models","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.04942","title":"Zero-Shot Time-Series Question Answering via Decoupled Perception and Reasoning","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05211","title":"Image Synthesis as an Intermediate for Controllable Time Series Generation","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05686","title":"Do Time-Series QA Systems Read the Time Series? Evidence Use and Reasoning Reliability","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.17794","title":"GIFT-Eval-CTX: A Benchmark For Contextual Forecasting Model Evaluation","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.17856","title":"MMTA: Benchmarking Multimodal Temporal Analysis with Time Series, Text, and Vision","created":"2026-10-13","cited_by_count":0,"area":"mllm"},{"id":"2610.18877","title":"Lotus: Learning to Understand Time-series by Learning to Forecast","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}