WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents

arXiv:2508.21475v3 Announce Type: replace Abstract: Existing multimodal browsing benchmarks often fail to require genuine multimodal reasoning, as many tasks can be solved with

arXiv:2603.18532v1 Announce Type: cross Abstract: The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar

arXiv:2604.05013v1 Announce Type: cross Abstract: Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to

arXiv:2604.22436v1 Announce Type: new Abstract: The rapid growth of AI agent ecosystems is transforming how complex tasks are delegated and executed, creating a new challenge of

arXiv:2609.03493v1 Announce Type: new Abstract: Modern vision-language models (VLMs) can directly answer many image-grounded questions, yet they often struggle with complex

arXiv:2605.00412v1 Announce Type: new Abstract: World models have recently re-emerged as a central paradigm for embodied intelligence, robotics, autonomous driving, and

arXiv:2605.08828v1 Announce Type: new Abstract: Large language model agents increasingly operate through environment-facing scaffolds that expose files, web pages, APIs, and logs.

arXiv:2608.20771v1 Announce Type: new Abstract: Search Agents face a severe reliability crisis during reinforcement learning (RL) fine-tuning. Heuristic Top-K retrieval often