paper-with-me

홈 › Papers

Graph-Memoized Reasoning: Foundations Structured Workflow Reuse in Intelligent Systems

2025-11-11 · Yash Raj Singh arxiv

Modern large language model-based reasoning systems frequently recompute similar reasoning steps across tasks, wasting computational resources, inflating inference latency, and limiting reproducibility. These inefficiencies underscore the need for persistent reasoning mechanisms that can recall and reuse prior computational traces. We introduce Graph-Memoized Reasoning, a formal framework for representing, storing, and reusing reasoning workflows as graph-structured memory. By encoding past decision graphs and retrieving them through structural and semantic similarity, our approach enables compositional reuse of subgraphs across new reasoning tasks. We formulate an optimization objective that minimizes total reasoning cost regularized by inconsistency between stored and generated workflows, providing a theoretical foundation for efficiency-consistency trade-offs in intelligent systems. We outline a conceptual evaluation protocol aligned with the proposed optimization objective. This framework establishes the groundwork for interpretable, cost-efficient, and self-improving reasoning architectures, offering a step toward persistent memory in large-scale agentic systems.

📄 PDF Abstract BibTeX arXiv:2511.15715

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic Similarity

Similar Papers 제목 키워드 기반

Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning

2025-11-11 · Songze Li, Zhiqiang Liu, Zhaoyan Gong, Xiaoke Guo 외 arxiv

Large Language Models (LLMs) achieve excellent performance in natural language reasoning tasks through pre-training on vast unstructured text, enabling them to understand the logic in natural language and generate logic-…

Graph Question AnsweringKnowledge Graphs

Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering

2026-03-14 · Lin Fan, Yafei Ou, Zhipeng Deng, Pengyu Dai 외 arxiv

Chain-of-thought (CoT) reasoning has advanced medical visual question answering (VQA), yet most existing CoT rationales are free-form and fail to capture the structured reasoning process clinicians actually follow. This …

Visual Question Answering

Endowing Robots with Longer-term Autonomy by Recovering from External Disturbances in Manipulation through Grounded Anomaly Classification and Recovery Policies

2018-09-11 · Hongmin Wu, Shuangqi Luo, Longxin Chen, Shuangda Duan 외

Robot manipulation is increasingly poised to interact with humans in co-shared workspaces. Despite increasingly robust manipulation and control algorithms, failure modes continue to exist whenever models do not capture t…

Anomaly ClassificationGeneral ClassificationMotion GenerationRobot Manipulation+1

Foundations and Architectures of Artificial Intelligence for Motor Insurance

2026-03-19 · Teerapong Panboonyuen arxiv

This handbook presents a systematic treatment of the foundations and architectures of artificial intelligence for motor insurance, grounded in large-scale real-world deployment. It formalizes a vertically integrated AI p…

Representation LearningMultimodal Reasoning

FlowMind: Execute-Summarize for Structured Workflow Generation from LLM Reasoning

2026-02-12 · Yihao Liu, Ziyun Zhang, Zile He, Huaqian Cai arxiv

LLMs can solve complex tasks through reasoning and tool use, but accurately translating these solutions into structured workflows remains challenging. We model workflows as sequences of tool use and reformulate the probl…