mlsanityData to 7 Oct 2026

PASCAL: A Phase-Aware Scheduling Algorithm for Serving Reasoning-based Large Language Models

arXiv 2602.11530 ↗First posted 12 Feb 2026cs.LG cs.ARcited by 1

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

The emergence of reasoning-based LLMs leveraging Chain-of-Thought (CoT) inference introduces new serving challenges, as their extended reasoning phases delay user-visible output and inflate Time-To-First-Token (TTFT). Existing LLM serving frameworks fail to distinguish between reasoning and answering phases, leading to performance degradation under GPU memory constraints. We present PASCAL, a phase-aware scheduling algorithm that prioritizes reasoning to reduce TTFT while using controlled preemption and token pacing during answering to preserve Quality-of-Experience (QoE). Our hierarchical scheduler combines instance-level placement with intra-instance execution and enables dynamic migration at phase boundaries to balance load and reduce interference. Across benchmarks using DeepSeek-R1-Distill-Qwen-32B, PASCAL reduces tail TTFT by up to 72% while maintaining answering phase SLO attainment, demonstrating the importance of phase-aware scheduling for reasoning-based LLM deployment.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 37 of its 53 references that are in the map. First posted on arXiv 12 Feb 2026.

Builds on

37 of 53 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning2 Apr
  2. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Models17 May

Other references · 35

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  8. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  9. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  10. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  11. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  12. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
23 more
  1. 2024Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluatorscited by 865
  2. 2023H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Modelscited by 805
  3. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 684
  4. 2024DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Servingcited by 595
  5. 2023FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPUcited by 567
  6. 2023Splitwise: Efficient generative LLM inference using phase splittingcited by 536
  7. 2024Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Servecited by 507
  8. 2024From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipelinecited by 484
  9. 2024PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funnelingcited by 420
  10. 2023LLM in a flash: Efficient Large Language Model Inference with Limited Memorycited by 170
  11. 2024Llumnix: Dynamic Scheduling for Large Language Model Servingcited by 167
  12. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generationcited by 158
  13. 2023Fast Distributed Inference Serving for Large Language Modelscited by 143
  14. 2024Vidur: A Large-Scale Simulation Framework For LLM Inferencecited by 115
  15. 2024DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inferencecited by 106
  16. 2024ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Cachingcited by 48
  17. 2024POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inferencecited by 46
  18. 2024Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Servicescited by 44
  19. 2024Queue management for slo-oriented large language model servingcited by 36
  20. 2023vTrain: A Simulation Framework for Evaluating Cost-effective and Compute-optimal Large Language Model Trainingcited by 22
  21. 2025Past-Future Scheduler for LLM Serving under SLA Guaranteescited by 20
  22. 2024SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Servingcited by 18
  23. 2024AQUA: Network-Accelerated Memory Offloading for LLMs in Scale-Up GPU Domainscited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Simthesizer: An Agent-Driven Simulation Framework for LLM Serving Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Optimal Scheduling Algorithms for LLM Inference: Theory and Practice
  2. 2026Multi-Layer Scheduling for MoE-Based LLM Reasoning
  3. 2025Intra-request branch orchestration for efficient LLM reasoning
  4. 2025Ranking Before Serving: Low-Latency LLM Serving via Pairwise Learning-to-Rank
  5. 2025Arrow: Adaptive Scheduling Mechanisms for Disaggregated LLM Inference Architecture
  6. 2026Predictive Scheduling for Efficient Inference-Time Reasoning in Large Language Models
  7. 2026ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning
  8. 2026Queueing-Aware Optimization of Reasoning Tokens for Accuracy-Latency Trade-offs in LLM Servers