Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning

• URL: http://arxiv.org/abs/2605.09395v2
• Date: Sat, 16 May 2026 07:36:34 GMT
• Title: Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning
• Abstract summary: We propose the first VL$underlinetextbfM$ $underlinetextbfa$gentic $underlinetextbfr$easoning framework for few-$underlinetextbfs$hot multimodal $underlinetextbfT$ime $underlinetextbfS$eries $underlinetextbfC$lassification ($textbfMarsTSC$), which introduces a self-evolving knowledge bank as a dynamic context iteratively refined via reflective agent
• Score: 44.69766273765273
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In this paper, we propose the first VL$\underline{\textbf{M}}$ $\underline{\textbf{a}}$gentic $\underline{\textbf{r}}$easoning framework for few-$\underline{\textbf{s}}$hot multimodal $\underline{\textbf{T}}$ime $\underline{\textbf{S}}$eries $\underline{\textbf{C}}$lassification ($\textbf{MarsTSC}$), which introduces a self-evolving knowledge bank as a dynamic context iteratively refined via reflective agentic reasoning. The framework comprises three collaborative roles: i) Generator conducts reliable classification via reasoning; ii) Reflector diagnoses the root causes of reasoning errors to yield discriminative insights targeting the temporal features overlooked by Generator; iii) Modifier applies verified updates to the knowledge bank to prevent context collapse. We further introduce a test-time update strategy to enable cautious, continuous knowledge bank refinement to mitigate few-shot bias and distribution shift. Extensive experiments across 12 mainstream time series benchmarks demonstrate that $\textbf{MarsTSC}$ delivers substantial and consistent performance gains across 6 VLM backbones, outperforming both classical and foundation model-based time series baselines under few-shot conditions, while producing interpretable rationales that ground each classification decision in human-readable feature evidence.

Related papers

• FUSE: An Evaluating Framework for Dangerous Capabilities of LLMs [24.30721158142313]
  Fragmented safety evaluation undermines the governance of dangerous AI capabilities.<n>We present a modular framework that evaluates each model through three orthogonal pipelines---Knowledge, Defense, and Harm.<n>Our first contribution is a horizontal comparison of dangerous capability across models and model families.<n>The second is a temporal analysis of capability evolution: tracking $K$, $D$, and $H$ against model release dates reveals that dangerous capability has not monotonically declined.
  arXiv  Detail & Related papers  (2026-09-02T06:31:39Z)
• MRAFnd: Multimodal Retrieval-Augmented Framework for Zero-Shot Fake News Detection [0.0]
  We introduce textbfMRAFnd, a novel framework for detecting fabricated news in zero-shot scenarios.<n>MRAFnd emulates a collaborative team of analysts to verify news veracity.<n> Comprehensive experiments on three benchmark datasets reveal that MRAFnd markedly surpasses state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-08-02T18:21:15Z)
• WhisperRec: Latent Reasoning for Efficient Foundation Recommendation Models [51.88075626243057]
  We propose WhisperRec, an efficient latent reasoning framework for foundation recommendation models (FRMs)<n>WhisperRec compresses teacher-generated Chain-of-Thought (CoT) into learnable latent reasoning tokens.<n>We show that WhisperRec consistently outperforms explicit-CoT methods and conventional baselines.
  arXiv  Detail & Related papers  (2026-07-29T08:48:35Z)
• TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning [52.67756371231985]
  Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models.<n>We introduce Tree Rollout Allocation for Contrastive Exploration (TRACE), a unified rollout allocation framework.<n>Technically, TRACE allocates rollout budget to both prompt roots and intermediate prefixes that are most likely to yield mixed terminal rewards.
  arXiv  Detail & Related papers  (2026-06-09T17:16:03Z)
• ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox [61.862814740220806]
  $textbfComplexMCP$ is a benchmark designed to evaluate agents in rigorous conditions.<n>Built on the Model Context Protocol (MCP), $textbfComplexMCP$ provides over 300 meticulously tested tools.
  arXiv  Detail & Related papers  (2026-05-11T16:20:51Z)
• DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification [38.65432183778467]
  We introduce DeltaRubric, an approach that reformulates multimodal preference evaluation as a plan-and-execute process within a single MLLM.<n>DeltaRubric operates in two steps: acting first as a $textitDisagreement Planner$, it generates a neutral, instance-specific verification checklist.<n>We formulate DeltaRubric as a multi-role reinforcement learning problem, jointly optimizing planning and verification capabilities.
  arXiv  Detail & Related papers  (2026-05-10T02:32:19Z)
• Quantifying Self-Preservation Bias in Large Language Models [9.590157416396194]
  We introduce the emphTwo-role Benchmark for Self-Preservation.<n>It measures how often role identity overrides objective utility.<n>We observe that in low-improvement regimes, models exploit the interpretive slack to post-hoc rationalization.
  arXiv  Detail & Related papers  (2026-04-02T15:38:31Z)
• CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling [61.75914342638658]
  CDRRM (Contrast-Driven Reward Model) is a framework for high-quality rubric generation and guided preference judgment.<n>This work offers a scalable, interpretable, and data-efficient path for reward modeling.
  arXiv  Detail & Related papers  (2026-03-09T07:15:23Z)
• Contextual Counterfactual Credit Assignment for Multi-Agent Reinforcement Learning in LLM Collaboration [22.269718913202595]
  We introduce Contextual Counterfactual Credit Assignment (textbftextttC3)<n>Instead of distributing rewards across an entire episode, textbftextttC3 isolates the causal impact of individual messages.<n>textbftextttC3 improves terminal performance over established baselines.
  arXiv  Detail & Related papers  (2026-03-06T20:25:11Z)
• Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interaction [49.03500737694832]
  We introduce textbfReinforcement textbfLearning with textbfTurn textbfRLSTA, a generalizable training approach designed to stabilize multi-turn interaction.<n>Experiments show that RLSTA significantly outperforms standard fine-tuning and abstention-based methods.
  arXiv  Detail & Related papers  (2026-03-05T04:04:59Z)
• A Dual-Path Generative Framework for Zero-Day Fraud Detection in Banking Systems [0.2864713389096699]
  High-frequency banking environments face a critical trade-off between low-latency fraud detection and regulatory explainability.<n>Traditional rule-based and discriminative models struggle with "zero-day" attacks due to extreme class imbalance and the lack of historical precedents.<n>This paper proposes a Dual-Path Generative Framework that decouples real-time anomaly detection from offline adversarial training.
  arXiv  Detail & Related papers  (2026-02-17T10:20:40Z)
• CORE: Context-Robust Remasking for Diffusion Language Models [51.59514489363897]
  We propose Context-Robust Remasking (CORE), a training-free framework for inference-time revision.<n>Rather than trusting static token probabilities, CORE identifies context-brittle tokens by probing their sensitivity to targeted masked-context perturbations.<n>On LLaDA-8B-Base, CORE delivers consistent improvements across reasoning and code benchmarks, outperforming compute-matched baselines and improving MBPP by up to 9.2 percentage points.
  arXiv  Detail & Related papers  (2026-02-04T00:12:30Z)
• Look As You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning [55.232400251303794]
  Look As You Think (LAT) is a reinforcement learning framework that trains models to produce verifiable reasoning paths with consistent attribution.<n>LAT consistently improves the vanilla model in both single- and multi-image settings, yielding average gains of 8.23% in soft exact match (EM) and 47.0% in IoU@0.5.
  arXiv  Detail & Related papers  (2025-11-15T02:50:23Z)
• Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning [46.106795445750855]
  REFRAIN is a training-free framework that determines when to stop reasoning to mitigate overthinking.<n> REFRAIN reduces token usage by 20-55% while maintaining or improving accuracy compared to standard CoT prompting.
  arXiv  Detail & Related papers  (2025-10-11T08:30:00Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.