Bibliography and LLM files
Sources and Machine-Readable Files
This site is built from research papers, benchmark reports, and engineering guidance on context engineering, RAG, long-context behavior, compression, memory, and evaluation.
Key facts
Sources and Machine-Readable Files
- The bibliography spans context engineering, retrieval, long-context behavior, compression, memory systems, and RAG evaluation.
- The site publishes both /llms.txt and /llms-full.txt for compact and expanded machine-readable summaries.
- Pages use JSON-LD, source links, citation anchors, and cite-this-page blocks to make claims easier to inspect.
- Curated Context distinguishes empirical findings, engineering guidance, and practical heuristics instead of treating one architecture as universally best.
Machine-readable files
Treatment T4 includes both dense schema and LLM-oriented files. The concise file is at /llms.txt. The expanded file is at /llms-full.txt. They summarize the site purpose, page map, citation policy, and core source list.
"retrieval and generation, context processing and context management"
Research stance
Curated Context distinguishes between established patterns, empirical findings, and practical heuristics. The papers below do not imply that one architecture always wins. They show that context length, placement, retrieval quality, compression, and evaluation all matter.
Sources Used
Research survey - 2025
A Survey of Context Engineering for Large Language Models
Frames context engineering as retrieval and generation, context processing, and context management, with a large taxonomy of implementations.
Engineering guide - 2025
Effective Context Engineering for AI Agents
Defines context engineering as the practice of curating and maintaining the optimal set of tokens during inference.
Research paper - 2020
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Introduces the RAG formulation that combines parametric model knowledge with non-parametric retrieved memory.
Research paper - 2023/2024
Lost in the Middle: How Language Models Use Long Contexts
Shows that models often use information better near the start or end of a prompt than in the middle.
Benchmark paper - 2024
RULER: What's the Real Context Size of Your Long-Context Language Models?
Extends needle-in-a-haystack tests with multi-needle, tracing, and aggregation tasks for long-context models.
Comparative study - 2024
Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach
Compares RAG and long-context approaches and argues for hybrid systems that use both strengths.
Research paper - 2025
Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
Reports that longer input length can hurt performance even when the relevant evidence is available.
Technical report - 2025
Context Rot: How Increasing Input Tokens Impacts LLM Performance
Popularizes context rot as non-uniform performance degradation as prompts get longer.
Research paper - 2023
LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
Introduces token-level prompt compression with reported high compression ratios and limited performance loss on studied tasks.
Research paper - 2023/2024
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
Extends prompt compression to long-context scenarios with question-aware filtering and recovery.
Research paper - 2023
MemGPT: Towards LLMs as Operating Systems
Uses a virtual context management metaphor to move information between memory tiers and the active prompt.
Research paper - 2023/2024
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Shows adaptive retrieval and critique as an alternative to indiscriminately retrieving a fixed number of passages.
Evaluation paper - 2023/2024
RAGAS: Automated Evaluation of Retrieval Augmented Generation
Defines reference-free RAG evaluation dimensions, including context relevance and answer faithfulness.
Evaluation paper - 2023/2024
ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems
Evaluates context relevance, answer faithfulness, and answer relevance with synthetic data and lightweight judges.
Experience report - 2024
Seven Failure Points When Engineering a Retrieval Augmented Generation System
Documents operational failure modes in RAG systems and argues that validation is only feasible during operation.
Benchmark paper - 2023/2024
LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
Introduces long-context tasks across QA, summarization, few-shot learning, synthetic tasks, and code completion.
Cite This Page
Curated Context. "Sources and Machine-Readable Files." Accessed July 6, 2026. https://curatedcontext.com/sources
https://curatedcontext.com/sources