TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration

• URL: http://arxiv.org/abs/2606.04743v1
• Date: Wed, 03 Jun 2026 11:23:08 GMT
• Title: TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration
• Abstract summary: We introduce TIDE, a template-guided iterative framework with two complementary mechanisms.<n>We propose iterative discovery, which surfaces a small batch of candidates per round while conditioning on what has already been found.<n>We show substantial gains over single-shot and parallel multi-agent baselines on task coverage, identification, and resolution.
• Score: 74.97459526627395
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agents are widely deployed as assistants over documents, tools, and code. However, they typically act only on explicit user requests, which surface only the problems the user has noticed, while many other important problems coexist, hidden in plain sight, within the broader user context, with their total number unknown in advance. We frame this as the task of discovering multiple hidden problems from context, in which coexisting problems should be uncovered, grounded in supporting evidence, and paired with concrete actions. To this end, we introduce TIDE, a template-guided iterative framework with two complementary mechanisms. Specifically, motivated by the observation that single-pass prediction anchors on the most salient cases and yields generic claims, we propose iterative discovery, which surfaces a small batch of candidates per round while conditioning on what has already been found, so subsequent rounds extend coverage; and thought templates, reusable schemas distilled from previously solved cases that specify what contextual signals to attend to and how to connect them, anchoring each prediction in a recognizable problem class. We validate TIDE on two realistic settings, personal workspaces and software repositories, across four model backbones, showing substantial gains over single-shot and parallel multi-agent baselines on task coverage, identification, and resolution.

Related papers

• WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents [53.426679066400844]
  We introduce WeAgent-Harness, a multimodal agentic harness that supports native text-vision interaction and runtime recovery.<n>We develop WeAgent-MMSearch, an integrated system spanning data construction, agentic post-training, and multimodal rollout.<n>We also introduce VisTarget-Bench, a 150-task human-verified benchmark that pairs each question with a held-out target image.
  arXiv  Detail & Related papers  (2026-08-28T08:28:43Z)
• Pretraining Reusable Inference Across Views with Synthetic Task Priors [21.47966082652401]
  Modern pretrained encoders make representations from heterogeneous views increasingly reusable, but the procedure that determines view utility and combines evidence is still relearned for each downstream task.<n>We propose SIMPLE, a prior-fitted multi-view in-context learner that predicts query labels by conditioning on a small labeled support set.<n>Experiments on multi-view and multi-omics benchmarks demonstrate that the frozen variant of SIMPLE achieves competitive performance without updating the inference backbone.
  arXiv  Detail & Related papers  (2026-08-19T17:10:03Z)
• MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors [42.124623200906626]
  MTPano is a robust panoramic foundation model established by a label-free training pipeline.<n>We project panoramic images into perspective patches to generate accurate, domain-gap-free pseudo-labels.<n>To tackle the interference between task types, we categorize tasks into rotation-invariant and rotation-variant groups.
  arXiv  Detail & Related papers  (2026-02-05T05:51:28Z)
• Tracking and Segmenting Anything in Any Modality [75.32774085793498]
  We propose a universal tracking and segmentation framework named SATA, which unifies a broad spectrum of tracking and segmentation subtasks with any modality input.<n> SATA demonstrates superior performance on 18 challenging tracking and segmentation benchmarks, offering a novel perspective for more generalizable video understanding.
  arXiv  Detail & Related papers  (2025-11-22T09:09:22Z)
• Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics [89.1999907891494]
  We present WebDetective, a benchmark of hint-free multi-hop questions paired with a controlled Wikipedia sandbox.<n>Our evaluation of 25 state-of-the-art models reveals systematic weaknesses across all architectures.<n>We develop an agentic workflow, EvidenceLoop, that explicitly targets the challenges our benchmark identifies.
  arXiv  Detail & Related papers  (2025-10-01T07:59:03Z)
• Keypoint Promptable Re-Identification [76.31113049256375]
  Occluded Person Re-Identification (ReID) is a metric learning task that involves matching occluded individuals based on their appearance. We introduce Keypoint Promptable ReID (KPR), a novel formulation of the ReID problem that explicitly complements the input bounding box with a set of semantic keypoints. We release custom keypoint labels for four popular ReID benchmarks. Experiments on person retrieval, but also on pose tracking, demonstrate that our method systematically surpasses previous state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-07-25T15:20:58Z)
• DeTra: A Unified Model for Object Detection and Trajectory Forecasting [68.85128937305697]
  Our approach formulates the union of the two tasks as a trajectory refinement problem. To tackle this unified task, we design a refinement transformer that infers the presence, pose, and multi-modal future behaviors of objects. In our experiments, we observe that ourmodel outperforms the state-of-the-art on Argoverse 2 Sensor and Open dataset.
  arXiv  Detail & Related papers  (2024-06-06T18:12:04Z)
• Debunking Free Fusion Myth: Online Multi-view Anomaly Detection with Disentangled Product-of-Experts Modeling [25.02446577349165]
  Multi-view or even multi-modal data is appealing yet challenging for real-world applications. We propose dPoE, a novel multi-view variational autoencoder model that involves (1) a Product-of-Experts layer in tackling multi-view data, (2) a Total Correction discriminator in disentangling view-common and view-specific representations, and (3) a joint loss function in wrapping up all components.
  arXiv  Detail & Related papers  (2023-10-28T15:14:43Z)
• Exploiting Facial Relationships and Feature Aggregation for Multi-Face Forgery Detection [21.976412231332798]
  existing methods predominantly concentrate on single-face manipulation detection, leaving the more intricate and realistic realm of multi-face forgeries relatively unexplored. This paper proposes a novel framework explicitly tailored for multi-face forgery detection, filling a critical gap in the current research. Our experimental results on two publicly available multi-face forgery datasets demonstrate that the proposed approach achieves state-of-the-art performance in multi-face forgery detection scenarios.
  arXiv  Detail & Related papers  (2023-10-07T15:09:18Z)

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.