AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

When Does Divide and Conquer Work for Long Context LLM? A Noise Decomposition Framework

Zach Xu, Shang Zhu, Jue WANG, Junlin Wang, Ben Athiwaratkun, Chi Wang, James Zou, Ce Zhang

ICLR 2026 · Large language models › Retrieval and knowledge · approach: Long-context and personalized retrieval · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
split 128K KV input into 16K chunks (D&C) instead of single agentllama70b · KV (128K)accuracy: 0.15 -> 1.00Improved
split 128K Math input into 16K chunks (D&C) instead of single agentllama70b · Math (128K)accuracy: 0.09 -> 0.57Improved
split 128K KV input into 32K chunks (D&C) instead of single agentgpt4omini · KV (128K)accuracy: 0.60 -> 1.00Improved
choose chunk size from 3 samples instead of exhaustive search (ablation)llama70b D&C · QA-IB (128K)F1: 0.63 -> 0.55Hurt
choose chunk size from 5 samples instead of exhaustive search (ablation)llama70b D&C · QA-IB (128K)F1: 0.63 -> 0.63No clear effect
choose chunk size from 5 samples instead of exhaustive search (ablation)qwen72b D&C · Sum (128K)ROUGE: 0.29 -> 0.29No clear effect
add 1K token overlap between chunks (16K chunks) (ablation)llama70b D&C · QA-IB (128K)F1: 0.63 -> 0.54Hurt
add 1K token overlap between chunks (4K chunks) (ablation)llama70b D&C · Sum (128K)ROUGE: 0.23 -> 0.19Hurt
add 1K token overlap between chunks (16K chunks) (ablation)llama70b D&C · Sum (128K)ROUGE: 0.24 -> 0.25No clear effect
use planner-based instead of manual aggregator prompt (ablation)D&C · Math and QA-LB (large T)accuracyImproved
increase input length for single agent from 1K to 128Kgpt4omini · KVaccuracy: 1.00 -> 0.60Hurt
increase input length for single agent from 1K to 128Kllama70b · Mathaccuracy: 0.63 -> 0.09Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy