# ReflecSched: Solving Dynamic Flexible Job-Shop Scheduling via LLM-Powered Hierarchical Reflection

arXiv: https://arxiv.org/abs/2508.01724 · HTML: https://mlsanity.com/paper/2508.01724/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 74 references that are in the map.
- First posted on arXiv 3 Aug 2025.

## Builds on (most cited first, 25 of 25)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search](https://mlsanity.com/paper/2406.03816/) (2024)
- [Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning](https://mlsanity.com/paper/2010.12367/) (2020)
- [HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model](https://mlsanity.com/paper/2408.09559/) (2024)
- [Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents](https://mlsanity.com/paper/2507.22925/) (2025)
- [Can LLMs Follow Simple Rules?](https://mlsanity.com/paper/2311.04235/) (2023)
- [LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities](https://mlsanity.com/paper/2504.16078/) (2025)
- [OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale](https://mlsanity.com/paper/2407.19633/) (2024)
- [Flexible Job Shop Scheduling via Dual Attention Network Based Reinforcement Learning](https://mlsanity.com/paper/2305.05119/) (2023)
- [Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search](https://mlsanity.com/paper/2408.10635/) (2024)
- [HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking](https://mlsanity.com/paper/2505.02322/) (2025)
- [The Lookahead Limitation: Why Multi-Operand Addition is Hard for LLMs](https://mlsanity.com/paper/2502.19981/) (2025)
- [Automatic programming via large language models with population self-evolution for dynamic fuzzy job shop scheduling problem](https://mlsanity.com/paper/2410.22657/) (2024)
- [Learning-Guided Rolling Horizon Optimization for Long-Horizon Flexible Job-Shop Scheduling](https://mlsanity.com/paper/2502.15791/) (2025)
- [PARADISE: Evaluating Implicit Planning Skills of Language Models with Procedural Warnings and Tips Dataset](https://mlsanity.com/paper/2403.03167/) (2024)
- [Effective and interpretable dispatching rules for dynamic job shops via guided empirical learning](https://mlsanity.com/paper/2109.03323/) (2021)

## Built on by (most cited first, 5 of 5)

- [MAFIG: Multi-agent Driven Formal Instruction Generation Framework](https://mlsanity.com/paper/2604.10989/) (2026)
- [DynaSchedBench: Calibrated Dynamic Scheduling Benchmarks and Observability Paradox in LLM-based Scheduling Agents](https://mlsanity.com/paper/2605.27566/) (2026)
- [Harmonizing Real-Time Constraints and Long-Horizon Reasoning: An Asynchronous Agentic Framework for Dynamic Scheduling](https://mlsanity.com/paper/2605.29262/) (2026)
- [Guiding Large Language Models with Genetic Programming-Evolved Heuristic Knowledge for Dynamic Multi-Mode Project Scheduling](https://mlsanity.com/paper/2607.27698/) (2026)
- [A MARL Centered Reference Architecture for Large Language Model Augmentation in Smart Manufacturing](https://mlsanity.com/paper/2608.07148/) (2026)

## Abstract (arXiv)

The NP-hard Dynamic Flexible Job-Shop Scheduling (DFJSP) problem involves real-time events and complex routing. While traditional rules are efficient but rigid, deep learning is opaque and requires feature engineering. Large Language Models (LLMs) promise adaptive reasoning without this engineering overhead, yet we find their direct application is suboptimal. Baseline LLMs suffer from three key pitfalls: the long-context paradox, where crucial data is underutilized; an underutilization of expert heuristics; and myopic decision-making. To address this, we propose ReflecSched, a framework that empowers the LLM beyond a direct scheduler by equipping it with a strategic analysis capability. ReflecSched tasks the LLM to analyze heuristic-driven simulations across multiple planning horizons and distill them into a concise, natural-language summary termed Strategic Experience. This summary is then integrated into the prompt of a final decision-making module, guiding it to produce non-myopic actions. Experiments demonstrate ReflecSched achieves superior performance, with its best variants attaining an average RPD of 6.09% and rank of 4.39 on GEN-Bench, significantly outperforming strong traditional and learning-based methods including HMPSAC and IDDQN. It also statistically and decisively surpasses direct LLM baselines, securing a 71.35% Win Rate while being, on average, 15.1% more token-efficient on Normal-scale problems. Furthermore, cumulative runtime analysis reveals that ReflecSched's zero-shot nature eliminates the training bottleneck, providing a decisive efficiency advantage in high-variability manufacturing environments. Ablation studies attribute this performance to a robust reflection mechanism that leverages high-quality, contrastive experience. Ultimately, the framework's performance is statistically on par with an oracle-like strategy, showcasing its effectiveness and robustness.