AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

CoS: Towards Optimal Event Scheduling via Chain-of-Scheduling

Yiming Zhao, Jiwei Tang, Shimin Di, Libin Zheng, Jianxing Yu, Jian Yin

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Data and evaluation methodology · 2 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
add exploration step (top-k candidates) (ablation)CoS Qwen2.5-7B · New YorkUtility score: 3.15 -> 3.37Improved
add verification step (ablation)CoS Qwen2.5-7B · New YorkUtility score: 3.31 -> 3.37Improved
add integration step (pick best) instead of random selection (ablation)CoS Qwen2.5-7B · New YorkUtility score: 3.26 -> 3.37Improved
add post-processing of conflicts (ablation)CoS Qwen2.5-7B · New YorkUtility score: 3.32 -> 3.37Improved
add exploration step (ablation)CoS Qwen2.5-7B · New YorkConflict rate (%): 58 -> 15Improved
use Chain-of-Scheduling SFT instead of Chain-of-Thought promptingQwen2.5-7B · New YorkUtility score: 2.14 -> 3.37Improved
use Chain-of-Scheduling SFT instead of Chain-of-Thought promptingMistral-7B · LondonUtility score: 2.22 -> 4.65Improved
apply CoS to small 7B model vs giant reasoning model DeepSeek-R1Qwen2.5-7B · New YorkLatency (s): 785 -> 1.29Improved
raise exploration k (ablation)CoS · New YorkUtility scoreNo clear effect
raise exploration k (ablation)CoS · New YorkLatencyHurt
add chain-of-thought to general LLM (DeepSeek-V3)DeepSeek-V3 · New YorkUtility score: 2.45 -> 2.48No clear effect
train on New York and test zero-shot on LondonCoS Qwen2.5-7B · London zero-shotUtility score: 3.04 (GNN-DRL) -> 4.22Improved

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