No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by EvolvingLMMs-Lab · Agent Tool · ★ 55
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ParaVT safe to install? View the security audit →
ParaVT Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Overview Long-video understanding is increasingly framed as agentic video reasoning: a large multimodal model (LMM) post-trained with reinforcement learning to invoke video-processing tools. Prior work in this line, including our earlier LongVT (CVPR 2026), dispatches tool calls sequentially — brittle to single mis-localizations, prone to multi-turn context drift, and linear in cost. <img src="assets/method.png" width="620" alt="ParaVT architecture: sequential one-tool-per-turn (left) vs parallel single-turn dispatch with weight-sharin
| Stars | 55 |
| Forks | 2 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 70.7349419360204/100 |
| Open Issues | 2 |
| Last Updated | 2026-06-02 |
| Created | 2026-04-28 |
| Platforms | python |
| Est. Tokens | ~326k |
These tools work well together with ParaVT for enhanced workflows:
Looking for a ParaVT alternative? If you're comparing ParaVT with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A framework for agentic tool use training with reinforcement learning
NEWTON: Agentic Planning for Physically Grounded Video Generation
🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models
Fixing GRPO training collapse in long-horizon multi-tool agents. A lightweight PRM-Lite + LATA joint approach
A travel agent based on Qwen2.5, fine-tuned by SFT + DPO/PPO/GRPO using traveling question-answer dataset, a m
OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Q
Explore other popular agent tool tools:
ParaVT is ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning. It is categorized as a Agent Tool with 55 GitHub stars.
ParaVT is primarily written in Python. It covers topics such as agentic-rl, grpo, long-video-understanding.
You can find installation instructions and usage details in the ParaVT GitHub repository at github.com/EvolvingLMMs-Lab/ParaVT. The project has 55 stars and 2 forks, indicating an active community.
ParaVT is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to ParaVT on Agent Skills Hub include ToolBrain, NEWTON, llm-rl-environments-lil-course. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: