mlsanityData to 14 Oct 2026

Reuse, Don't Recompute: Efficient Large Reasoning Model Inference via Memory Orchestration

arXiv 2511.12987 ↗First posted 17 Nov 2025cs.MAcited by 0

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

Abstract (arXiv)

Large reasoning models (LRMs) achieve strong accuracy through test-time scaling, generating longer chains of thought or sampling multiple solutions, but at steep costs in tokens and latency. We argue that memory is a core ingredient for efficient reasoning: when evidence already exists, models should think less by reusing structured memory instead of recomputing derivations. We present ENGRAM-R, an inference-time memory layer that integrates typed retrieval with compact fact card representations and explicit citation control. On the LoCoMo benchmark, ENGRAM-R reduces input tokens by 85% and reasoning tokens by 75% compared to full context while maintaining high accuracy. On a multi-hop slice of the LongMemEval benchmark, it achieves similar efficiency with substantial accuracy gains. These results show that memory is not only critical for long-horizon correctness but also a practical lever for efficient reasoning under tight compute, memory, and latency budgets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 14 of its 22 references that are in the map. First posted on arXiv 17 Nov 2025.

Builds on

14 of 22 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation28 Jul

Other references · 13

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  8. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  9. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 707
  10. 2025HealthBench: Evaluating Large Language Models Towards Improved Human Healthcited by 429
  11. 2025Chain of Draft: Thinking Faster by Writing Lesscited by 297
  12. 2025MemOS: A Memory OS for AI Systemcited by 138
1 more
  1. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agentscited by 102

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Efficient Inference for Large Reasoning Models: A Survey
  2. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond
  3. 2025Hydra: A Modular Architecture for Efficient Long-Context Reasoning
  4. 2026MemDuet: Learning Dual-Process Memory for Long-Context Reasoning
  5. 2026Memory Augmentation Unlocks Efficient Chain-of-Thought Reasoning
  6. 2026PI-Mem: Pushing Long-Context Reasoning to 3.6M Tokens with Parallel-Iterative Memory
  7. 2025Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning
  8. 2024Disentangling Memory and Reasoning Ability in Large Language Models