VOS-Agent: The 1st Place Solution for the 8th LSVOS Challenge (MOSEv2 Track)

• URL: http://arxiv.org/abs/2608.12721v1
• Date: Thu, 13 Aug 2026 02:08:00 GMT
• Title: VOS-Agent: The 1st Place Solution for the 8th LSVOS Challenge (MOSEv2 Track)
• Abstract summary: VOS-Agent conditionally activates specialized agents according to target characteristics.<n>A Target Perception and Routing Agent assigns each sequence to a regular, tiny, or semantic-dominated route.<n>On the MOSEv2 test set, VOS-Agent achieves 69.82% on the official $mathcalJ&dotmathcalF$ metric.
• Score: 15.751702557806595
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Complex video object segmentation requires robust target propagation under severe occlusion, disappearance and reappearance. Although SAM3 provides strong promptable mask propagation, a uniform inference path remains unreliable for tiny targets with insufficient visual evidence and semantic-dominated targets whose identities depend on explicit attributes. To this end, we present VOS-Agent, a collaborative framework that retains SAM3 as the shared dense segmentation module and conditionally activates specialized agents according to target characteristics. A Target Perception and Routing Agent assigns each sequence to a regular, tiny, or semantic-dominated route. Tiny targets are supported by a Visual Tracking Agent through confidence-aware box prompts, while semantic-dominated targets are handled by an MLLM-based Semantic Agent through description-guided localization and candidate verification. On the MOSEv2 test set, VOS-Agent achieves 69.82% on the official $\mathcal{J}\&\dot{\mathcal{F}}$ metric and ranks first in the MOSEv2 Track of the 8th LSVOS Challenge at ECCV 2026.

Related papers

• Competitive Memory Readout for Robust Video Object Segmentation: 2nd Place Technical Report for the MOSEv2 Track of the 8th LSVOS Challenge [51.15679610275694]
  We present our solution for the 8th Large-scale Video Object (LSVOS) Challenge at ECCV 2026.<n>The challenge evaluates robust video object segmentation under complex temporal dynamics.<n>Our method builds on SAM3 and focuses on its memory readout.
  arXiv  Detail & Related papers  (2026-08-22T18:09:51Z)
• AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents [29.81912218748482]
  Large language model (LLM) agents automate penetration testing through an observation-action loop.<n>Current defenses rely heavily on static, isolated artifacts planted in the environment prior to an attack.<n>AgentSnare dynamically unfolds a decoy environment to continually steer the penetration agent away from the real target.
  arXiv  Detail & Related papers  (2026-07-29T14:56:31Z)
• AgentAbstain: Do LLM Agents Know When Not to Act? [19.223843408018997]
  Existing evaluations mostly focus on task success rather than whether agents know when to abstain.<n>We present the first systematic evaluation framework for agentic abstention: the calibrated ability of tool-using LLM agents to recognize when not to act.<n>AgentAbstain is a paired-task benchmark built on an agent-native taxonomy of 8 abstention scenarios across pre-execution reasoning and runtime discovery.
  arXiv  Detail & Related papers  (2026-07-11T00:57:36Z)
• Re-Prompting SAM 3 via Object Retrieval: 3rd of the 5th PVUW MOSE Track [51.15679610275694]
  We develop an automatic re-prompting framework to improve robustness under target disappearance and reappearance.<n>Our solution achieves a J&F of 51.17% on the test set, ranking 3rd in the MOSEv2 track.
  arXiv  Detail & Related papers  (2026-03-24T23:45:15Z)
• Beyond Input Guardrails: Reconstructing Cross-Agent Semantic Flows for Execution-Aware Attack Detection [32.301679396929536]
  We propose SysName, a framework that shifts the defensive paradigm from static input filtering to execution-aware analysis.<n>SysName synthesizes fragmented operational primitives into contiguous behavioral trajectories, enabling a holistic view of system activity.<n> Empirical evaluations demonstrate that SysName effectively detects over ten distinct compound attack vectors, achieving F1-scores of 85.3% and 66.7% for node-level and path-level end-to-end attack detection, respectively.
  arXiv  Detail & Related papers  (2026-03-04T01:59:16Z)
• BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents [58.83028403414688]
  Large language model (LLM) agents execute tasks through multi-step workflow that combine planning, memory, and tool use.<n>Backdoor triggers injected into specific stages of an agent workflow can persist through multiple intermediate states and adversely influence downstream outputs.<n>We propose textbfBackdoorAgent, a modular and stage-aware framework that provides a unified agent-centric view of backdoor threats in LLM agents.
  arXiv  Detail & Related papers  (2026-01-08T03:49:39Z)
• AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents [54.29555239363013]
  We propose a generic black-box fuzzing framework, AgentVigil, to automatically discover and exploit indirect prompt injection vulnerabilities.<n>We evaluate AgentVigil on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o.<n>We apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.
  arXiv  Detail & Related papers  (2025-05-09T07:40:17Z)
• Improving Zero-Shot ObjectNav with Generative Communication [60.84730028539513]
  We propose a new method for improving zero-shot ObjectNav. Our approach takes into account that the ground agent may have limited and sometimes obstructed view.
  arXiv  Detail & Related papers  (2024-08-03T22:55:26Z)
• Dissecting Adversarial Robustness of Multimodal LM Agents [70.2077308846307]
  We manually create 200 targeted adversarial tasks and evaluation scripts in a realistic threat model on top of VisualWebArena.<n>We find that we can successfully break latest agents that use black-box frontier LMs, including those that perform reflection and tree search.<n>We also use ARE to rigorously evaluate how the robustness changes as new components are added.
  arXiv  Detail & Related papers  (2024-06-18T17:32:48Z)
• Traffic Agent Trajectory Prediction Using Social Convolution and Attention Mechanism [57.68557165836806]
  We propose a model to predict the trajectories of target agents around an autonomous vehicle. We encode the target agent history trajectories as an attention mask and construct a social map to encode the interactive relationship between the target agent and its surrounding agents. To verify the effectiveness of our method, we widely compare with several methods on a public dataset, achieving a 20% error decrease.
  arXiv  Detail & Related papers  (2020-07-06T03:48:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.