POINTS-Seeker: Towards Training a Multimodal Agentic Search Model from Scratch
- URL: http://arxiv.org/abs/2604.14029v1
- Date: Wed, 15 Apr 2026 16:09:37 GMT
- Title: POINTS-Seeker: Towards Training a Multimodal Agentic Search Model from Scratch
- Abstract summary: We introduce Agentic Seeding, a dedicated phase designed to weave the precursors necessary for eliciting agentic behaviors.<n>We propose V-Fold, an adaptive history-aware compression scheme that preserves recent dialogue turns in high fidelity while folding historical context into the visual space via rendering.<n>We develop POINTS-Seeker-8B, a state-of-the-art multimodal agentic search model that consistently outperforms existing models across six diverse benchmarks.
- Score: 84.73366911912512
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: While Large Multimodal Models (LMMs) demonstrate impressive visual perception, they remain epistemically constrained by their static parametric knowledge. To transcend these boundaries, multimodal search models have been adopted to actively interact with the external environment for evidence retrieval. Diverging from prevailing paradigms that merely retrofit general LMMs with search tools as modular extensions, we explore the potential of building a multimodal agentic search model from scratch. Specifically, we make the following contributions: (i) we introduce Agentic Seeding, a dedicated phase designed to weave the foundational precursors necessary for eliciting agentic behaviors; (ii) we uncover a performance bottleneck in long-horizon interactions, where the increasing volume of interaction history overwhelms the model's ability to locate ground-truth evidence. To mitigate this, we propose V-Fold, an adaptive history-aware compression scheme that preserves recent dialogue turns in high fidelity while folding historical context into the visual space via rendering; and (iii) we develop POINTS-Seeker-8B, a state-of-the-art multimodal agentic search model that consistently outperforms existing models across six diverse benchmarks, effectively resolving the challenges of long-horizon, knowledge-intensive visual reasoning.
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) - DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agents [21.799085797512955]
Multimodal large language models (MLLMs) have advanced visual understanding and reasoning.<n>DeepVoyager-VL is a long-horizon multimodal deep-search framework for vision-in-the-loop search.
arXiv Detail & Related papers (2026-08-03T07:36:48Z) - Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models [65.4947731385794]
We present a unified multi-agent visual reasoning framework that evolves from our foundational image-centric model, Insight-V.<n>We introduce two novel algorithms, ST-GRPO and J-GRPO, which enhance spatial-temporal reasoning and improve evaluative robustness.<n>Experiments on base models like LLaVA-NeXT and Qwen2.5-VL demonstrate significant performance gains across challenging image and video reasoning benchmarks.
arXiv Detail & Related papers (2026-03-18T15:28:07Z) - DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories [52.57197752244638]
We introduce DeepImageSearch, a novel agentic paradigm that reformulates image retrieval as an autonomous exploration task.<n>Models must plan and perform multi-step reasoning over raw visual histories to locate targets based on implicit contextual cues.<n>We construct DISBench, a challenging benchmark built on interconnected visual data.
arXiv Detail & Related papers (2026-02-11T12:51:10Z) - NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching [64.10695425442164]
We introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms.<n>Trained on large-scale interleaved text, image, video, and audio data, NExT-OMNI delivers competitive performance on multimodal generation and understanding benchmarks.<n>To advance further research, we release training details, data protocols, and open-source both the code and model checkpoints.
arXiv Detail & Related papers (2025-10-15T16:25:18Z) - Agent-ScanKit: Unraveling Memory and Reasoning of Multimodal Agents via Sensitivity Perturbations [34.15274225730601]
We propose textbfAgent-ScanKit to unravel the memory and reasoning capabilities of multimodal agents under controlled perturbations.<n>Results show that mechanical memorization often outweighs systematic reasoning.<n>Our findings underscore the necessity of robust reasoning modeling for multimodal agents in real-world scenarios.
arXiv Detail & Related papers (2025-10-01T04:29:39Z) - Progressive Multimodal Reasoning via Active Retrieval [64.74746997923967]
Multi-step multimodal reasoning tasks pose significant challenges for large language models (MLLMs)<n>We propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs.<n>We show that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning.
arXiv Detail & Related papers (2024-12-19T13:25:39Z)
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.