4arXiv cs.CL (Computation and Language)·
O-VAD: Training-free agentic framework for industrial video anomaly detection via object-centric tracking
Researchers introduce O-VAD, a training-free agentic framework for Industrial Video Anomaly Detection (IVAD) that tracks spatial-temporal object state trajectories and reasons over them to identify anomalies without domain-specific knowledge or retraining on normal clips. The system is designed to handle the complexity of industrial settings with strict physics and procedural constraints, outperforming frontier VLMs, agentic frameworks, and fine-tuned traditional VAD methods on three IVAD benchmarks. The approach emphasizes interpretable reporting of anomaly processes and types, mimicking human inspector reasoning.
Related guides (2)
Related events (8)
HAT-4D: Agentic framework for 4D multi-object interaction reconstruction from monocular video
HAT-4D is a new agentic framework that reconstructs 3D geometry, temporal dynamics, and physical interactions of multiple objects from single monocular videos, targeting scalable data collection for Embodied AI and Vision-Language-Action (VLA) model training. The system integrates VLMs with a multi-level human-in-the-loop feedback mechanism to resolve depth ambiguities and occlusions without expensive multi-camera rigs. The authors also introduce MVOIK-4D, an open-world benchmark for monocular 4D interaction reconstruction with a novel evaluation protocol focused on physical plausibility and temporal consistency. Experiments show state-of-the-art performance on most metrics, and HAT-4D-generated data improves downstream model fine-tuning.
VLESA: Vision-Language Embodied Safety Agent for Real-Time Human Activity Monitoring
Researchers introduce VLESA, a framework that monitors human activities from egocentric video and triggers real-time safety interventions when dangerous actions are predicted. The system addresses intent-dependent safety — where identical actions can be safe or dangerous depending on context — using a goal-conditioned safety Q-filter trained via GRPO and an intent-action prediction agent. On the ASIMOV-2.0 benchmark, VLESA achieves higher intervention accuracy than baselines, with the Q-filter improving action safety by over 41 percentage points through goal-conditioned constrained decoding.
OmniAgent: POMDP-based active perception agent for long video understanding with test-time scaling
Researchers introduce OmniAgent, a multimodal agent that reformulates long video understanding as a POMDP-based iterative Observation-Thought-Action cycle, selectively distilling audio-visual cues into persistent textual memory rather than processing all frames uniformly. The system uses Agentic Supervised Fine-Tuning and a novel reinforcement learning method (TAURA) with turn-level entropy for credit assignment. OmniAgent demonstrates positive test-time scaling and achieves state-of-the-art open-source results across ten benchmarks, with its 7B model outperforming Qwen2.5-VL-72B on LVBench (50.5% vs. 47.3%).
CamVLA: Calibration-free view-robust Vision-Language-Action model for robot deployment
Researchers from Alibaba DAMO Academy introduce CamVLA, a Vision-Language-Action model that eliminates the need for explicit camera calibration during robot deployment. The model decouples manipulation controls from camera geometry by predicting camera-centric end-effector actions and a 6-DoF hand-eye matrix, composing them into robot base-frame actions via deterministic geometric transformation. Operating on a single monocular RGB image without depth or calibration data, CamVLA improves success rates across diverse unseen viewpoints in both simulation and real-world evaluations.
VideoAgent: Agentic framework for video understanding, editing, and remaking
HKUDS has released VideoAgent, an open-source Python framework positioning itself as an all-in-one agentic system for video understanding, editing, and remaking. The repository is trending on GitHub with 1,098 total stars and 150 new stars in a single day. The project represents a multimodal agent harness targeting video as a first-class modality.
VAORA: Visual Action Outcome Reasoning Alignment for physical reasoning generalization in VLMs
Researchers introduce VAORA (Visual Action Outcome Reasoning Alignment), a reward design framework targeting two failure modes in vision-language models applied to interactive physical reasoning: hallucinated chain-of-thought reasoning and misalignment between reasoning and actions. VAORA uses two complementary rewards — a Visual Alignment Reward anchoring reasoning to visual context, and a Visual-Action Alignment Reward grounding reasoning in action outcomes — plus dense rewards from a pre-trained expert agent for training stability. Experiments on the PHYRE and Virtual Tool benchmarks show improved generalization to novel tasks and unseen environments.
VisAnomReasoner: Efficient VLM for Time-Series Anomaly Detection via VisAnomBench
Researchers introduce VisAnomBench, a curated benchmark augmenting public time-series anomaly datasets with natural-language rationales generated and selected from multiple large VLMs using task-specific rewards. Fine-tuning on this benchmark produces VisAnomReasoner, a parameter-efficient vision-language model that outperforms all baselines by at least 21.23 and 23.87 percentage points in precision and F1 on VisAnomBench. Cross-benchmark evaluation on TSB-AD-U shows further generalization gains of 9.57 and 13.39 percentage points in precision and F1, respectively.
OAT: Unsupervised failure attribution for LLM agents via one-class learning on successful trajectories
A new arXiv preprint introduces OAT, a method for attributing failures in LLM-based agentic systems by training exclusively on successful trajectories using one-class learning with neural controlled differential equations. At inference time, each step in a failure trajectory receives an anomaly score based on deviation from learned success dynamics. OAT is reported to be 200–5000× faster than prompting-based baselines while outperforming them by +20% F1 in-domain and +7% out-of-distribution, using only 100 successful trajectories for training. The approach addresses a practical bottleneck in agentic system debugging by eliminating the need for costly step-level failure annotations.