Cover Image

SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jain, Jitesh, Li, Jialuo, Ma, Zixian, Zhang, Jieyu, Kim, Chris Dongjoo, Lee, Sangho, Tripathi, Rohun, Gupta, Tanmay, Clark, Christopher, Shi, Humphrey
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
by: Clark, Christopher, et al.
Published: (2026)

MolmoPoint: Better Pointing for VLMs with Grounding Tokens
by: Clark, Christopher, et al.
Published: (2026)

Unified Spatio-Temporal Token Scoring for Efficient Video VLMs
by: Zhang, Jianrui, et al.
Published: (2026)

m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks
by: Ma, Zixian, et al.
Published: (2024)

AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User Memory
by: Jain, Jitesh, et al.
Published: (2025)

ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams
by: Kim, Chris Dongjoo, et al.
Published: (2025)

VideoSAGE: Video Summarization with Graph Representation Learning
by: Chaves, Jose M. Rojas, et al.
Published: (2024)

Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation
by: Jain, Jitesh, et al.
Published: (2024)

SAGE: Smart home Agent with Grounded Execution
by: Rivkin, Dmitriy, et al.
Published: (2023)

Benchmarking Object Detectors with COCO: A New Path Forward
by: Singh, Shweta, et al.
Published: (2024)

SAGE: Scene Graph-Aware Guidance and Execution for Long-Horizon Manipulation Tasks
by: Li, Jialiang, et al.
Published: (2025)

Slow-Fast Architecture for Video Multi-Modal Large Language Models
by: Shi, Min, et al.
Published: (2025)

RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents
by: Zhang, Zijing, et al.
Published: (2025)

SAGE: Multi-Agent Self-Evolution for LLM Reasoning
by: Peng, Yulin, et al.
Published: (2026)

Any House Any Task: Scalable Long-Horizon Planning for Abstract Human Tasks
by: Liu, Zhihong, et al.
Published: (2026)

Video-Based Reward Modeling for Computer-Use Agents
by: Song, Linxin, et al.
Published: (2026)

Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding
by: Li, Jialuo, et al.
Published: (2025)

Reinforcement Learning for Long-Horizon Interactive LLM Agents
by: Chen, Kevin, et al.
Published: (2025)

LongVideoAgent: Multi-Agent Reasoning with Long Videos
by: Liu, Runtao, et al.
Published: (2025)

PAI-Bench: A Comprehensive Benchmark For Physical AI
by: Zhou, Fengzhe, et al.
Published: (2025)

VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking
by: Lin, Jingyang, et al.
Published: (2026)

Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation Training
by: Gao, Ziqi, et al.
Published: (2024)

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
by: Xi, Zhiheng, et al.
Published: (2025)

The Case against Scale: Empirical Evidence of Underperformance in Large Secondary Funds
by: Gurav, Jitesh
Published: (2025)

Reinforcement Learning for Long-Horizon Multi-Turn Search Agents
by: Kalyan, Vivek, et al.
Published: (2025)

Visual Agentic AI for Spatial Reasoning with a Dynamic API
by: Marsili, Damiano, et al.
Published: (2025)

COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context
by: Wan, Guangya, et al.
Published: (2025)

SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent
by: Hu, Yuyang, et al.
Published: (2026)

AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning
by: Hu, Yuyang, et al.
Published: (2026)

PyraVid: Hierarchical Multimodal Memory for Long-Horizon Video Reasoning
by: Yan, Sikuan, et al.
Published: (2026)

LH-Bench: Skill-Grounded Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks
by: Chandwani, Abhishek, et al.
Published: (2026)

Train Short, Inference Long: Training-free Horizon Extension for Autoregressive Video Generation
by: Li, Jia, et al.
Published: (2026)

VeruSAGE: A Study of Agent-Based Verification for Rust Systems
by: Yang, Chenyuan, et al.
Published: (2025)

Task Me Anything
by: Zhang, Jieyu, et al.
Published: (2024)

VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning
by: Zhang, Ruiyang, et al.
Published: (2026)

WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents
by: Liu, Junteng, et al.
Published: (2025)

Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism
by: Ni, Tianwei, et al.
Published: (2025)

The Verifier Tax: Horizon Dependent Safety Success Tradeoffs in Tool Using LLM Agents
by: Sah, Tanmay, et al.
Published: (2026)

FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning
by: He, Jialuo, et al.
Published: (2024)

WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoning
by: Yu, Xinmiao, et al.
Published: (2026)