# Xnhyacinth/Awesome-LLM-Long-Context-Modeling

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

Repository: https://github.com/Xnhyacinth/Awesome-LLM-Long-Context-Modeling
Canonical: https://ross.abutalabs.com/products/awesome-llm-long-context-modeling
Homepage: https://arxiv.org/abs/2503.17407
License: MIT
License Family: permissive
Topics: awsome-list, large-language-models, long-context-modeling, papers, survey, length-extrapolation, compress, rag, llm, benchmark, blogs, evaluation, transformer, ssm, agent, long-term-memory, longcot
Last push: 2026-08-17T08:27:48+00:00

## Health v2 (maintenance only)
Score: 72/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 77
- inputs: {"age_days": 1081, "days_push": 16, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2166, forks 102 (observed 2026-08-28T04:06:21.337137+00:00)

## What it is
A curated awesome-list of must-read papers and blogs on long-context modeling for large language models, accompanying a comprehensive arXiv survey (2503.17407). It covers efficient attention, KV-cache optimization, position encoding and length extrapolation, long-context training, long-term memory, RAG, compression, long reasoning, benchmarks, and evaluation.

## Use cases
- find papers on long context window LLMs
- research KV cache optimization techniques
- learn about length extrapolation and position encoding
- survey long-context benchmarks and evaluation methods
- find resources on long-term memory for LLM agents
- study state-space models and recurrent transformers for long context
- keep up with new long-context modeling research

## When to choose
- you are a researcher or engineer surveying long-context LLM techniques
- you want a curated, categorized reading list with links to papers and blogs
- you need background before building RAG or long-context systems

## When to avoid
- you need runnable code or a library rather than a reading list
- you want a general LLM resource list not focused on long context

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, developer-tools
- domain: large-language-models, artificial-intelligence, tutorials, awesome-lists
- platform: -
- tags: awesome-list, long-context, papers, survey, kv-cache, length-extrapolation, state-space-models, long-term-memory, long-reasoning, natural-language-processing, web-server

## Member repositories
- Xnhyacinth/Awesome-LLM-Long-Context-Modeling (main) score 72

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:21.337137+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:49:56.455681+00:00, confidence not recorded.
  - readme: https://github.com/Xnhyacinth/Awesome-LLM-Long-Context-Modeling (fetched 2026-08-28T04:06:21.337137+00:00, sha 39c767a0e9d6)
  - homepage: https://arxiv.org/abs/2503.17407 (fetched 2026-08-29T10:30:10.788295+00:00, sha 66078651f1cd)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T10:30:10.797369+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T10:30:10.801010+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T10:30:10.802752+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T10:30:10.799252+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.