VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness
cs.CV, cs.AI
Submitted: 2026-10-14
Updated: 2026-10-16
Comments: 50 pages, 15 figures
Project page: https://zihaolinqz.github.io/VideoHarness-SRSI
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Qwen3-VL Technical Report
- Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
- Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
- Meta-Harness: End-to-End Optimization of Model Harnesses
- UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist
- Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
- Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams
- VISTA: A Test-Time Self-Improving Video Generation Agent
- Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
- Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension
- Code as Agent Harness
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
- VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
- Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents
- LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding
- ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
- RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
- TextGrad: Automatic "Differentiation" via Text
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