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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add exploration step (top-k candidates) (ablation) | CoS Qwen2.5-7B · New York | Utility score: 3.15 -> 3.37 | Improved |
| add verification step (ablation) | CoS Qwen2.5-7B · New York | Utility score: 3.31 -> 3.37 | Improved |
| add integration step (pick best) instead of random selection (ablation) | CoS Qwen2.5-7B · New York | Utility score: 3.26 -> 3.37 | Improved |
| add post-processing of conflicts (ablation) | CoS Qwen2.5-7B · New York | Utility score: 3.32 -> 3.37 | Improved |
| add exploration step (ablation) | CoS Qwen2.5-7B · New York | Conflict rate (%): 58 -> 15 | Improved |
| use Chain-of-Scheduling SFT instead of Chain-of-Thought prompting | Qwen2.5-7B · New York | Utility score: 2.14 -> 3.37 | Improved |
| use Chain-of-Scheduling SFT instead of Chain-of-Thought prompting | Mistral-7B · London | Utility score: 2.22 -> 4.65 | Improved |
| apply CoS to small 7B model vs giant reasoning model DeepSeek-R1 | Qwen2.5-7B · New York | Latency (s): 785 -> 1.29 | Improved |
| raise exploration k (ablation) | CoS · New York | Utility score | No clear effect |
| raise exploration k (ablation) | CoS · New York | Latency | Hurt |
| add chain-of-thought to general LLM (DeepSeek-V3) | DeepSeek-V3 · New York | Utility score: 2.45 -> 2.48 | No clear effect |
| train on New York and test zero-shot on London | CoS Qwen2.5-7B · London zero-shot | Utility score: 3.04 (GNN-DRL) -> 4.22 | Improved |
Closest papers by meaning
- ConvRec-R1: Training LLM-based Conversational Recommender Systems with Reinforcement Learning (ICLR 2026 · similarity 0.83)
- Active Large Language Model-Based Knowledge Distillation for Session-Based Recommendation (AAAI 2025 · similarity 0.82)
- LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation (NeurIPS 2024 · similarity 0.82)
- SNS-Bench: Defining, Building, and Assessing Capabilities of Large Language Models in Social Networking Services (ICML 2025 · similarity 0.81)
- SLMRec: Distilling Large Language Models into Small for Sequential Recommendation (ICLR 2025 · similarity 0.81)
- LLM4RSR: Large Language Models as Data Correctors for Robust Sequential Recommendation (AAAI 2025 · similarity 0.81)
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.
