aiqbench analysis
Composing insight from the full article — this may take a moment.
Nexus : An Agentic Framework for Context-Aware Time Series Forecasting
arXiv:2605.14389v2 Announce Type: replace-cross Abstract: Language models have emerged as highly capable reasoners, yet their performance in time series forecasting remains uneven across domains and levels of contextual grounding. This is primarily due to their suboptimal time series reasoning and numerical modeling capabilities. To tackle this, we introduce Nexus, a multimodal forecasting framework that bridges qualitative event reasoning with structural numerical modeling through principled statistical synthesis. Nexus follows three structured stages: (1) Temporal profiling and anchor generation, which distills the multimodal history into a timestamped causal-temporal profile and generates a forecast anchor (2) Dual contextual outlook generation, which produces decoupled macro and micro level forecast trajectories, and (3) Bayesian synthesis, which reconciles the forecasting anchor with both contextual forecast trajectories via closed-form Gaussian updating weighted by empirical error covariances. Evaluated across three diverse forecasting benchmarks constituting eight datasets spanning rich event contexts, abrupt shocks, and purely numerical series, Nexus consistently outperforms leading time-series foundation models and language model baselines, while providing interpretable causal reasoning.
Abstract:Language models have emerged as highly capable reasoners, yet their performance in time series forecasting remains uneven across domains and levels of contextual grounding. This is primarily due to their suboptimal time series reasoning and numerical modeling capabilities. To tackle this, we introduce Nexus, a multimodal forecasting framework that bridges qualitative event reasoning with structural numerical modeling through principled statistical synthesis. Nexus follows three structured stages: (1) Temporal profiling and anchor generation, which distills the multimodal history into a timestamped causal-temporal profile and generates a forecast anchor (2) Dual contextual outlook generation, which produces decoupled macro and micro level forecast trajectories, and (3) Bayesian synthesis, which reconciles the forecasting anchor with both contextual forecast trajectories via closed-form Gaussian updating weighted by empirical error covariances. Evaluated across three diverse forecasting benchmarks constituting eight datasets spanning rich event contexts, abrupt shocks, and purely numerical series, Nexus consistently outperforms leading time-series foundation models and language model baselines, while providing interpretable causal reasoning.
Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
arXiv:2605.14389 [cs.AI]
(or arXiv:2605.14389v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2605.14389 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 258 words
Related coverage
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · Aug 27, 2026
World2TS: Real-World Event Context for Time-Series Forecasting
arXiv · Oct 14, 2026
GlyRAG: Context-Aware Retrieval-Augmented Framework for Blood Glucose Forecasting
arXiv · Jul 21, 2026
CastFSR: A Fast--Slow--Reflect Agentic Reasoning Framework for Context-Aware Time Series Forecasting
arXiv · Aug 5, 2026