Meituan LongCat launches native multimodal AI model LongCat-2.5: 1.6T parameters, tailored for long-horizon agent tasks
Meituan's LongCat has launched the native multimodal model LongCat-2.5 today, designed for long-horizon agent tasks. The model features a total of 1.6 trillion parameters, with approximately 4.8 billion parameters activated per token.
Continue looking at this topic
OpportunitiesAfter half a year in Shengcai, how did a beginner earn 100,000+ with AI? ↗News and AnalysisAI agents generated only hundreds of orders: how should we view DoorDash's pilot? ↗Open-source projectMultiple agents share a single warehouse: are the rules and Git hooks sufficient? ↗Hotly discussed viewsConcerned that agents may become less capable after data desensitization? Which task details should be retained first? ↗Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open the original article on ITHome