Home Projects OmniAgent
OmniAgent

OmniAgent

by HarryHsing · GitHub

OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Qwen2.5-VL-72B with 73% fewer frames on LVBench.

# agent# audio-visual# icml2026# llm-agent
View on GitHub
⭐ Stars
53
🍴 Forks
5
🔥 Trending
+1 today
📜 License
Apache-2.0
Commercial use OK
📅 Created
2026
🔄 Last commit
7 days ago
🏷️ Category
agent
💻 Language
You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
OmniAgent — GitHub preview card
📈 Star history
5352
2026-07-202026-07-21
📄 About

OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Qwen2.5-VL-72B with 73% fewer frames on LVBench.

Frequently asked questions

What is OmniAgent?

OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Qwen2.5-VL-72B with 73% fewer frames on LVBench.

Is OmniAgent open source?

OmniAgent is an open-source project. It is released under the Apache-2.0 license.

Is OmniAgent free?

Yes. OmniAgent is free and open source — you can use, modify and self-host it.

🏅 Maintainer of this project?
OpenSourceAI badge — OmniAgent

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![OpenSourceAI](https://opensourceai.tech/badge.php?tool=harryhsing-omniagent)](https://opensourceai.tech/project/harryhsing-omniagent.html)
More badge options →
🧬 Related projects🧬 View the DNA map →