arXiv:2610.19424v1 Announce Type: new Abstract: LLM system capabilities depend not only on model parameters but also on the executable harnesses that organize information acquisition, tool use, reaso...
AgentHorizon is a benchmark comprising 1,373 computer‑use tasks with instruction‑trajectory pairs collected from 166 hours of human‑recorded activity across three operating systems. The benchmark uses a paired design that swaps instructions to create negative tasks, testing judges’ ability to distinguish successful trajectories from those that completed a similar but incompatible request. Eleven judges were evaluated, with GPT‑5.5 achieving the highest balanced accuracy of 80.9% on the full trajectory subset, while tool‑use benefits some models but harms others, revealing large variability in judges’ performance.
arXiv:2608. 03979v1 Announce Type: cross Abstract: We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video streams, a setting that demands dense spatiotemporal grounding coupled with open-web exploration.
arXiv:2608.31005v1 Announce Type: new Abstract: Existing long-video agents acquire evidence through one uniform behavior, ignoring whether the required evidence is concentrated, requires broad occurr...
VideoResearcher is a training‑free, multi‑agent framework that autonomously designs, tests, and refines high‑impact tools for long‑video understanding. It operates through dual Solving and Evolving loops, analyzing tool‑use trajectories to identify gaps, coordinating specialized agents to develop and validate executable tools, and reusing evolved tools to improve evidence acquisition in subsequent reasoning. The approach achieves state‑of‑the‑art performance among self‑improving agents and approaches the human‑designed upper bound, demonstrating a paradigm that expands agent capabilities while reducing costly manual engineering.
arXiv:2609.12818v1 Announce Type: new Abstract: Long video understanding often behaves like a visual needle-in-a-haystack problem: query-relevant evidence is sparsely distributed across long temporal...
arXiv:2609.37950v1 Announce Type: new Abstract: Video understanding agents acquire evidence through an executable harness that controls what they observe and how they use those observations. However,...
arXiv:2608.23329v1 Announce Type: cross Abstract: Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video a...
arXiv:2608. 14015v1 Announce Type: cross Abstract: Understanding tens-of-minutes surgical videos requires long-horizon temporal reasoning, answering what happens before, after, or across stages of a procedure by grounding the question in visual evidence spread across time.
arXiv:2512.23044v3 Announce Type: replace Abstract: Autonomous agents are shifting information seeking from passive retrieval toward proactive, open-ended research, yet this progress has largely bypa...
VideoHarness‑RSI explores how improving the executable context‑construction program alone can enhance long‑video understanding with frozen vision‑language models. By recursively searching for better harnesses—programs that select and structure video segments—using an outer‑loop proposer that learns from prior programs and execution traces, the method consistently outperforms weaker hand‑crafted baselines and further improves upon stronger ones. The resulting harnesses transfer to other long‑video benchmarks without additional search, demonstrating that executable context construction is a distinct, reusable optimization layer.
VideoWeaver is an agent harness and benchmark for long‑video generation that evaluates and evolves reusable skills. It allows an agent to dynamically compose foundation skills into a workflow based on a single high‑level instruction, rather than following a static pipeline. The benchmark includes 16 task categories and 285 cases with multimodal references, and an evidence‑grounded agent‑as‑judge inspects execution traces and final videos to guide skill evolution, improving both process and output quality.