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

• URL: http://arxiv.org/abs/2511.15715v1
• Date: Tue, 11 Nov 2025 07:42:37 GMT
• Title: Graph-Memoized Reasoning: Foundations Structured Workflow Reuse in Intelligent Systems
• Authors: Yash Raj Singh,
• Abstract summary: We introduce Graph-Memoized Reasoning, a formal framework for representing, storing and reusing reasoning as graph-structured memory.<n>By encoding past decision graphs and retrieving them through structural and semantic similarity, our approach enables compositional reuse of subgraphs across new reasoning tasks.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Certifiable Estimation with Factor Graphs [11.391420452904166]
  We show that factor graph structure is preserved under Shor's relaxation and Burer-Monteiro factorization.<n>Applying these transformations to a QCQP with an associated factor graph representation yields a lifted problem admitting a factor graph model with identical connectivity.
  arXiv  Detail & Related papers  (2026-03-01T20:50:51Z)
• Computability of Agentic Systems [0.0]
  The Quest Graph is a formal framework for analyzing the capabilities of agentic systems with finite context.<n>We show that reference-augmented (Turing-complete) systems can be exponentially more efficient at simulating complex graphs than their non-augmented (context-free) counterparts.
  arXiv  Detail & Related papers  (2026-01-26T16:06:15Z)
• Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models [45.28250076657801]
  Long Chain-of-Thought (LCoT) has proven effective in enhancing the reasoning capabilities of Large Language Models (LLMs)<n>Despite RLVR-based optimization, existing methods still suffer from coarse-grained supervision, reward hacking, high training costs, and poor generalization.<n>We propose the Graph Reasoning Paradigm (GRP), which realizes structured and symbolic reasoning, implemented via graph-structured representations with step-level cognitive labels.
  arXiv  Detail & Related papers  (2026-01-19T12:23:00Z)
• MemRec: Collaborative Memory-Augmented Agentic Recommender System [57.548438733740504]
  We propose MemRec, a framework that architecturally decouples reasoning from memory management.<n>MemRec introduces a dedicated LM_Mem to manage a dynamic collaborative memory graph.<n>It achieves state-of-the-art performance on four benchmarks.
  arXiv  Detail & Related papers  (2026-01-13T18:51:16Z)
• PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agency [50.712873697511206]
  Existing work often lacks adaptability to diverse tasks and overlooks the constructive and task-oriented role of AI agent memory.<n>We propose PISA, a pragmatic, psych-inspired unified memory system that treats memory as a constructive and adaptive process.<n>Our empirical evaluation, conducted on the existing LOCOMO benchmark and our newly proposed AggQA benchmark for data analysis tasks, confirms that PISA sets a new state-of-the-art by significantly enhancing adaptability and long-term knowledge retention.
  arXiv  Detail & Related papers  (2025-10-12T10:34:35Z)
• Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search [62.1546099504045]
  We propose a dual-phase test-time scaling framework that separates reasoning into planning and execution.<n>Specifically, we decompose reasoning trajectories and develop reward models for each phase, enabling the search to explore and prune plans and executions separately.<n> Experiments on both mathematical reasoning and code generation benchmarks demonstrate that our approach consistently improves accuracy while reducing computation redundant.
  arXiv  Detail & Related papers  (2025-09-29T19:27:23Z)
• Implicit Reasoning in Large Language Models: A Comprehensive Survey [67.53966514728383]
  Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks.<n>Recent studies have shifted attention from explicit chain-of-thought prompting toward implicit reasoning.<n>This survey introduces a taxonomy centered on execution paradigms, shifting the focus from representational forms to computational strategies.
  arXiv  Detail & Related papers  (2025-09-02T14:16:02Z)
• A Pre-training Framework for Relational Data with Information-theoretic Principles [57.93973948947743]
  We introduce Task Vector Estimation (TVE), a novel pre-training framework that constructs supervisory signals via set-based aggregation over relational graphs.<n>TVE consistently outperforms traditional pre-training baselines.<n>Our findings advocate for pre-training objectives that encode task heterogeneity and temporal structure as design principles for predictive modeling on relational databases.
  arXiv  Detail & Related papers  (2025-07-14T00:17:21Z)
• PixelThink: Towards Efficient Chain-of-Pixel Reasoning [70.32510083790069]
  PixelThink is a simple yet effective scheme that integrates externally estimated task difficulty and internally measured model uncertainty.<n>It learns to compress reasoning length in accordance with scene complexity and predictive confidence.<n> Experimental results demonstrate that the proposed approach improves both reasoning efficiency and overall segmentation performance.
  arXiv  Detail & Related papers  (2025-05-29T17:55:49Z)
• Quantifying Memory Utilization with Effective State-Size [73.52115209375343]
  We develop a measure of textitmemory utilization'<n>This metric is tailored to the fundamental class of systems with textitinput-invariant and textitinput-varying linear operators
  arXiv  Detail & Related papers  (2025-04-28T08:12:30Z)
• Autonomous Structural Memory Manipulation for Large Language Models Using Hierarchical Embedding Augmentation [0.0]
  This study introduces hierarchical embedding augmentation as a means to redefine the representation of tokens through multi-level semantic structures.<n>Results reveal substantial improvements in computational efficiency, with marked reductions in processing overhead for longer input sequences.<n>The ability to dynamically adjust token representations and memory configurations contributed to the model's robustness under varied and unpredictable input conditions.
  arXiv  Detail & Related papers  (2025-01-23T22:20:36Z)
• GraphIC: A Graph-Based In-Context Example Retrieval Model for Multi-Step Reasoning [22.115256310400817]
  In-context learning (ICL) enhances large language models (LLMs) by incorporating demonstration examples.<n>Current methods typically use text embeddings to measure semantic similarity, which often introduces bias in multi-step reasoning tasks.<n>We propose GraphIC, a graph-based retrieval model that leverages reasoning-aware representation and specialized similarity metric for in-context example retrieval.
  arXiv  Detail & Related papers  (2024-10-03T04:33:02Z)
• Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation [19.582494782591386]
  This work proposes an unsupervised learning framework for optimization (CO) problems. Our key contribution is the observation that if the relaxed objective satisfies entry-wise concavity, a low optimization loss guarantees the quality of the final integral solutions. In particular, this observation can guide the design of objective models in applications where the objectives are not given explicitly while requiring being modeled in prior.
  arXiv  Detail & Related papers  (2022-07-13T06:44:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.