arXiv Computer Vision
Accuracy and Cost Claims Do Not Survive Re-Execution in Agentic VideoQA
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Jun 26
Confidence-Aware Tool Orchestration for Robust Video Understanding
arXiv:2606. 26904v1 Announce Type: cross Abstract: Video reasoning language models implicitly assume that every input frame is equally reliable.
arXiv AI
Oct 9
AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks
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 Machine Learning
Oct 8
Coding-Agent Benchmarks Should Match Their Users' Task Flows
arXiv:2610.09633v1 Announce Type: new Abstract: The evaluation of coding agents generally strives to be as realistic as possible. In our study, we collect 4,782 agent sessions of real software engine...
arXiv AI
Jul 14
AgentAbstain: Do LLM Agents Know When Not to Act?
arXiv:2607. 10059v1 Announce Type: new Abstract: Agent systems based on large language models (LLMs) are increasingly deployed for autonomous tasks, yet existing evaluations mostly focus on task success rather than whether agents know when to abstain.
Hugging Face Trending Papers
Sep 2
VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement
VeriPhy is an auditable physical‑verification system that evaluates generated video by compiling prompts into typed physical obligations and a statically validated execution plan before any frames are observed. During execution, it gates calls to frozen low‑level experts (e.g., segmentation, tracking, counting, depth, OCR, audio‑event detection) and returns provenance‑carrying evidence records, which are mapped to a three‑valued state (supported, contradicted, unknown) with full traceability. On a 1,500‑clip corpus of human‑annotated flaw records, VeriPhy accounts for 228 failures out of 304, outperforming a published question‑decomposition evaluator that accounts for 164, while also providing auditable evidence for each verdict.
Hugging Face Trending Papers
Oct 7
Coding-Agent Benchmarks Should Match Their Users' Task Flows
The evaluation of coding agents generally strives to be as realistic as possible. In our study, we collect 4,782 agent sessions of real software engineers in JetBrains IDEs, which we call Production S...