Towards Data Science August 19, 2026 By Sarah Schürch

Kimi K3’s 1M Token Context Window vs. RAG: Cost, Latency and Answer Quality

Read the original on Towards Data Science →

The article presents a controlled comparison between a top‑5 Retrieval‑Augmented Generation (RAG) pipeline and a single 127,000‑token prompt using the same 12 questions, system prompt, and model. Both approaches were graded blind on correctness, completeness, and grounding. The study evaluates cost, latency, and answer quality for each method.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Towards Data Science.

arXiv AI

Aug 19

Token Optimization and Context Window Management in Multi-Agent AI Workflows

The paper "Token Optimization and Context Window Management in Multi‑Agent AI Workflows" introduces a practitioner framework that reduces token usage and latency in multi‑agent AI systems. It outlines six patterns—context stratification, fetch‑once/process‑locally architecture, schema‑contracted prompts, token‑aware fallback chains, semantic caching, and inter‑agent communication compression—and reports a 60‑70% token reduction and a 61‑116 second cold‑load latency improvement in production. A controlled study on relevance‑contrast context shows that mixing high‑ and low‑relevance items in prompts can improve relevance accuracy by up to +0.084. whyItMatters":"The work provides concrete, repeatable engineering patterns that bridge research and production, enabling faster, cheaper, and more reliable AI workflows."

By Dvir Shamay

llms agents

Towards Data Science

Aug 13

Cut an Enterprise RAG Pipeline’s Latency and Cost by Calling the LLM Less, Not by Buying a Faster Model

Enterprise Document Intelligence [Vol. 1 #9ter] - The pipeline from Article 9 calls a model at several steps to be sure it is right.

By angela shi

llms rag

Towards Data Science

Jun 30

Context Engineering for RAG: The Four Typed Inputs Behind Every Answer

Enterprise Document Intelligence [Vol. 1 #7bis] - Tobi Lütke and Andrej Karpathy named the practice in 2025.

By Kezhan Shi

llms rag

Towards Data Science

Aug 3

Prompt, Context, Loop: The Three Engineering Layers Every RAG System Is Built On

Enterprise Document Intelligence [Vol. 1 #M2] - Every RAG system is built in three engineering layers stacked on one LLM call: prompt (the call itself), context (what fills the model’s window), loop (when the next call fires and when it stops).

By angela shi

llms rag

Towards Data Science

Jun 30

Context Engineering for RAG: The Four Typed Inputs Behind Every RAG Answer

Enterprise Document Intelligence [Vol. 1 #7bis] - Tobi Lütke and Andrej Karpathy named the practice in 2025.

By Kezhan Shi

llms rag

Towards Data Science

Jun 30

Context Engineering for RAG : The Four Typed Inputs Behind Every RAG Answer

Enterprise Document Intelligence [Vol. 1 #7bis] - Tobi Lütke and Andrej Karpathy named the practice in 2025.

By Kezhan Shi

llms rag

One email a morning, machine-written

Related stories

Token Optimization and Context Window Management in Multi-Agent AI Workflows

Cut an Enterprise RAG Pipeline’s Latency and Cost by Calling the LLM Less, Not by Buying a Faster Model

Context Engineering for RAG: The Four Typed Inputs Behind Every Answer

Prompt, Context, Loop: The Three Engineering Layers Every RAG System Is Built On

Context Engineering for RAG: The Four Typed Inputs Behind Every RAG Answer

Context Engineering for RAG : The Four Typed Inputs Behind Every RAG Answer