PyVision-RL: Forging Open Agentic Vision Models via RL
Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn reasoning, limiting the benefits of agentic behavior. We introduce PyVision-RL, a reinforcement learning framework for open-weight multimodal models that stabilizes training and sustains interaction. Our approach combines an oversampling-filtering-ranking rollout strategy with an accumulative tool reward to prevent collapse and encourage multi-turn tool use. Using a unified training pipeline, we develop PyVision-Image and PyVision-Video for image and video understanding. For video reasoning, PyVision-Video employs on-demand context construction, selectively sampling task-relevant frames during reasoning to significantly reduce visual token usage. Experiments show strong performance and improved efficiency, demonstrating that sustained interaction and on-demand visual processing are critical for scalable multimodal agents.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
PyVision: Agentic Vision with Dynamic Tooling
LLMs are increasingly deployed as agents, systems capable of planning, reasoning, and dynamically calling external tools. However, in visual reasoning, prior approaches largely remain limited by predefined workflows and …
Visual ReasoningKlear-AgentForge: Forging Agentic Intelligence through Posttraining Scaling
Despite the proliferation of powerful agentic models, the lack of critical post-training details hinders the development of strong counterparts in the open-source community. In this study, we present a comprehensive and …
Reinforcement LearningForging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities
The rise of large foundation models, trained on extensive datasets, is revolutionizing the field of AI. Models such as SAM, DALL-E2, and GPT-4 showcase their adaptability by extracting intricate patterns and performing e…
Autonomous DrivingNeRFHybrid Ground-State Quantum Algorithms based on Neural Schrödinger Forging
Entanglement forging based variational algorithms leverage the bi-partition of quantum systems for addressing ground state problems. The primary limitation of these approaches lies in the exponential summation required o…
The Measure of Deception: An Analysis of Data Forging in Machine Unlearning
Motivated by privacy regulations and the need to mitigate the effects of harmful data, machine unlearning seeks to modify trained models so that they effectively ``forget'' designated data. A key challenge in verifying u…