# Meituan LongCat-2.5 scales agentic RL for long-horizon tasks

> Original title: LongCat-2.5 scales an end-to-end agentic RL pipeline across data, environments, algorithms and harnesses for long-horizon tasks, and its ...

- Source: Meituan LongCat
- Published: 2026-11-02T14:35:30.000Z
- Bad Influence: https://badinfluence.news/items/wrjscrzew0aupe7clwd5hgk2a
- Original: https://x.com/Meituan_LongCat/status/2117264340445532597

## Summary

Meituan LongCat says LongCat-2.5 scales an end-to-end agentic reinforcement learning pipeline spanning data, environments, algorithms and harnesses for long-horizon tasks. Its MOPD training retains the previous model's expert groups. Per-cut prefixes and segment-capped student rollouts keep long responses stable, while shared prefill, KV-cache reuse and Tree Attention reduce sampling and training cost.

## Post

LongCat-2.5 scales an end-to-end agentic RL pipeline across data, environments, algorithms and harnesses for long-horizon tasks, and its MOPD training retains the previous model's expert groups:
Per-cut prefixes and segment-capped student rollouts keep long responses stable, while shared prefill, KV-cache reuse and Tree Attention keep sampling and training cheap.

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2117264319478161408%2Fimg%2FQ3crwRVfUXLmXZ6b.jpg&mode=thumb&exp=1793836800&sig=eeb101c594a5db8b)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWIIrkYbkAAxS1u.jpg&mode=thumb&exp=1793836800&sig=edb77df0475ca404)