MemAgent
A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.
About
We propose a novel long-context processing framework — MemAgent, which directly optimizes long-context tasks through end-to-end Reinforcement Learning without altering the underlying model architecture. MemAgent has demonstrated superb long-context capabilities, being able to extrapolate from an 8K context trained on 32K text to a 3.5M QA task with performance loss
Open Source Health
- Stars
- 1,106
- Forks
- 73
- License
- Apache-2.0
- Last commit
- 5 months ago
Resources & Links
Related Categories
Vendor
BytedTsinghua-SIA
The Joint SIA-Lab of Tsinghua AIR & Bytedance Seed - Scalable Intelligent Advanced Technology Joint Research Center
Quick Links
Open Source
More by BytedTsinghua-SIA
Related Products
Dagger
the missing software stack for CI
Top category match
The Algorithm
Source code for the X Recommendation Algorithm
Shared categories
Recommenders
TensorFlow Recommenders is a library for building recommender system models using TensorFlow.
Shared categories
RPG_KDD2025
This repository provides the code for implementing RPG described in our KDD'25 paper "Generating Long Semantic IDs in Parallel for Recommendation".
Shared categories
Pairec
A Go web framework for quickly building recommendation online services based on JSON configuration.
Shared categories