Context Language Models

类型：arxiv
标识：2609.37725
链接：https://arxiv.org/abs/2609.37725
主分类：agent
形态：method
TLDR：We introduce Context Language Models (CLMs), language models that natively manage their own context. We implement this by treating the context as a file and allowing the model to make unrestricted updates to this file. This allows the model to learn what is most important to maintain in context, and naturally extends to multi-agent systems where multiple agent contexts coexist as files. Building CLMs zero-shot with existing models outperforms SOTA context management strategies across a variety of tasks: 11.4% higher accuracy with 21.5% fewer FLOPs on BrowseComp-Plus, 5% higher scores with 59%
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-09-30-agent-rag-longcontext-candidates.json

2026-08-27

仓库 ELM-Research/ECG-Language-Models

2026-08-11

仓库 lonePatient/awesome-pretrained-chinese-nlp-models

2026-06-19

笔记 Cool Papers · cs.CL (papers.cool) · RSS 摘要

2026-08-15

仓库 BradyFU/Awesome-Multimodal-Large-Language-Models

2026-08-14

笔记精读笔记：Characterizing State Space Model and Hybrid Language Model Performance with Long Context

2026-08-30

arXiv

2609.37725

TLDR

We introduce Context Language Models (CLMs), language models that natively manage their own context. We implement this by treating the context as a file and allowing the model to make unrestricted updates to this file. This allows the model to learn what is most important to maintain in context, and naturally extends to multi-agent systems where multiple agent contexts coexist as files. Building CLMs zero-shot with existing models outperforms SOTA context management strategies across a variety of tasks: 11.4% higher accuracy with 21.5% fewer FLOPs on BrowseComp-Plus, 5% higher scores with 59%

Context Language Models

相关 · 按语义匹配