Tianning Ray Chai retweeted
Excited to share Agima, an omni agent that plans by imagining futures!
Trained with SFT + agentic RL, it unifies policy, world, and reward models: the same model proposes actions, imagines their visual outcomes, and evaluates them before acting
Trained with SFT + agentic RL, it unifies policy, world, and reward models: the same model proposes actions, imagines their visual outcomes, and evaluates them before acting
We trained an imaginative agent! โจ
Agima: an omni agent that plans by imagining futures.
๐ฆ๐๐ง: Directly generalizes to harder tasks! ๐ฎ%โ๐ฐ๐ฌ%, beats GPT-5.6 Sol (๐ฎ๐ฌ%).
๐ฅ๐: New ways to imagine emerge! Imagines a second plan only if the first one fails (๐ฏ๐ฎ%โ๐ญ๐ฌ๐ฌ%).
1
6
42
12,667
Tianning Ray Chai retweeted
We trained an imaginative agent! โจ
Agima: an omni agent that plans by imagining futures.
๐ฆ๐๐ง: Directly generalizes to harder tasks! ๐ฎ%โ๐ฐ๐ฌ%, beats GPT-5.6 Sol (๐ฎ๐ฌ%).
๐ฅ๐: New ways to imagine emerge! Imagines a second plan only if the first one fails (๐ฏ๐ฎ%โ๐ญ๐ฌ๐ฌ%).
Agima: an omni agent that plans by imagining futures.
๐ฆ๐๐ง: Directly generalizes to harder tasks! ๐ฎ%โ๐ฐ๐ฌ%, beats GPT-5.6 Sol (๐ฎ๐ฌ%).
๐ฅ๐: New ways to imagine emerge! Imagines a second plan only if the first one fails (๐ฏ๐ฎ%โ๐ญ๐ฌ๐ฌ%).
16
60
357
45,195