paper-with-me

Papers

MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent

2025-07-03 · Hongli Yu, Tinghong Chen, Jiangtao Feng, Jiangjie Chen, Weinan Dai, Qiying Yu, Ya-Qin Zhang, Wei-Ying Ma, Jingjing Liu, Mingxuan Wang, Hao Zhou

Despite improvements by length extrapolation, efficient attention and memory modules, handling infinitely long documents with linear complexity without performance degradation during extrapolation remains the ultimate challenge in long-text processing. We directly optimize for long-text tasks in an end-to-end fashion and introduce a novel agent workflow, MemAgent, which reads text in segments and updates the memory using an overwrite strategy. We extend the DAPO algorithm to facilitate training via independent-context multi-conversation generation. 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 < 5% and achieves 95%+ in 512K RULER test.

📄 PDF Abstract BibTeX arXiv:2507.02259

Code (0)

등록된 구현이 없습니다.

Tasks

8k

Methods 이 논문이 사용한 방법론

DAPO Dialogue-Adaptive Pre-training Objective (DAPO) is a pre-training objective for dialogue adaptation, which is designed to measure qualities of dialogues from multiple…

Similar Papers 제목 키워드 기반

EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use

2026-02-17 · Siwei Wen, Zhangcheng Wang, Xingjian Zhang, Lei Huang 외 arxiv

Online video understanding requires models to perform continuous perception and long-range reasoning within potentially infinite visual streams. Its fundamental challenge lies in the conflict between the unbounded nature…

Reinforcement Learning

When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning

2026-02-11 · Leheng Sheng, Yongtao Zhang, Wenchang Ma, Yaorui Shi 외 arxiv

While reasoning over long context is crucial for various real-world applications, it remains challenging for large language models (LLMs) as they suffer from performance degradation as the context length grows. Recent wo…

ConvMem: Convolutional Memory for Long-Context Reasoning

2026-09-09 · Hongming Zhang, Zhaozhen Gu, Fengshuo Bai, Ming Hao 외 arxiv

While Large Language Models (LLMs) have demonstrated impressive capabilities, they often struggle with extremely long contexts due to fixed context limits. To address this, sequential approaches like MemAgent extend the …

Reinforcement Learning

Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning

2026-02-09 · Zhuoen Chen, Dongfang Li, Meishan Zhang, Baotian Hu 외 arxiv

Large Language Models (LLMs) face significant challenges in long-context processing, including quadratic computational costs, information forgetting, and the context fragmentation inherent in retrieval-augmented generati…

Reinforcement Learning

InfMem: Learning System-2 Memory Control for Long-Context Agent

2026-02-02 · Xinyu Wang, Mingze Li, Peng Lu, Xiao-Wen Chang 외 arxiv

Reasoning over ultra-long documents requires synthesizing sparse evidence scattered across distant segments under strict memory constraints. While streaming agents enable scalable processing, their passive memory update …