arxiv arXiv cs.CL · 52d ago · research

OmniAgent: Native Active Perception for Omni-Modal Understanding

from English

OmniAgent introduces a POMDP-based iterative Observation-Thought-Action cycle for video understanding, enabling on-demand action execution to selectively distill audio-visual cues into persistent textual memory. It achieves state-of-the-art performance on ten benchmarks, with a 7B agent outperforming a 10× larger Qwen2.5-VL-72B model on LVBench (50.5% vs. 47.3%).

Importance 3/3 Beats a top-lab benchmark New feature vs. leaders arXiv cs.CL Mistral AI Alibaba (Qwen) OpenAI AI agents Multimodal Reasoning models

Read original

arxiv arXiv cs.AI · 51d ago · 2 views

Dual-Agent Framework for Cross-Model Verified Translation

A dual-agent framework converts natural-language experiment protocols into executable commands for robotic lab platforms. It uses a Parser Agent and a rule-based mapping engine to translate protocols, with a heterogeneous LLM Validation Agent ensuring accuracy and triggering self-correction. The framework successfully enables end-to-end autonomous execution of microplate-based experiments like the Bradford assay.

arxiv arXiv cs.CL · 51d ago · 1 view

AgentFinVQA: Auditable, On-Premise Financial Chart QA

AgentFinVQA introduces a multi-agent pipeline for financial chart question answering that ensures auditability and on-premise deployability without significant accuracy loss. It outperforms baseline models by +7.68 pp using a proprietary backbone and +4.84 pp with open-weights Qwen3.6-27B-FP8, while providing a confidence signal via verifier output that improves human review routing.

arxiv arXiv cs.AI · 52d ago · 1 view

OneCanvas: 3D Scene Understanding via Panoramic Reprojection

OneCanvas enables 3D scene understanding in Vision-Language Models by aggregating patch features onto a panoramic canvas using 3D world coordinates. It achieves state-of-the-art results on SQA3D and VSI-Bench, with strong generalization on SPBench, using significantly less training compute than prior methods.

arxiv arXiv cs.LG · 52d ago

ViGOS: Decoupling Perception and Reasoning in Multimodal On-Policy Self-Distillation

ViGOS introduces a visually grounded on-policy self-distillation framework for multimodal large language models. It decouples perception and reasoning by using an image-only teacher for visual descriptions and a reasoning teacher for final outputs, reducing reliance on text-only references. This approach improves image-grounded performance across multiple vision-language benchmarks.

arxiv arXiv cs.AI · 52d ago

ThinkDeception: Interpretable Multimodal Deception Detection Framework

ThinkDeception introduces a progressive reinforcement learning framework that enables interpretable multimodal deception detection. It leverages a step-by-step annotated Chain of Thought dataset and proposes Visual-Audio Consistency Group Relative Policy Optimization with a dynamic curriculum, enhancing reasoning quality and outperforming existing methods on mainstream benchmarks.