Long-MDR: Long-Context Reinforcement Learning for Multimodal Deep-Research Agents
cs.CV
Submitted: 2026-10-04
Updated: 2026-10-09
Terminology
Sources
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- Tongyi DeepResearch Technical Report
- Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models
- Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Proximal Policy Optimization Algorithms
- On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents
- DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agents
- POINTS-Seeker: An Open Recipe for Multimodal Search Agents with Visual Memory Management
- REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents
- WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents
- Towards Long-horizon Agentic Multimodal Search
- OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
- SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation
- VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
- WebDancer: Towards Autonomous Information Seeking Agency
- WebSailor: Navigating Super-human Reasoning for Web Agent
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models