Task Memory Engine (TME): A Structured Memory Framework with Graph-Aware Extensions for Multi-Step LLM Agent Tasks

• URL: http://arxiv.org/abs/2504.08525v3
• Date: Wed, 16 Apr 2025 14:48:13 GMT
• Title: Task Memory Engine (TME): A Structured Memory Framework with Graph-Aware Extensions for Multi-Step LLM Agent Tasks
• Abstract summary: We propose a lightweight and structured memory module that tracks task execution using a hierarchical Task Memory Tree (TMT)<n>TME is designed to be graph-aware, supporting reusable substeps, converging task paths, and shared dependencies.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) are increasingly used as autonomous agents for multi-step tasks. However, most existing frameworks fail to maintain a structured understanding of the task state, often relying on linear prompt concatenation or shallow memory buffers. This leads to brittle performance, frequent hallucinations, and poor long-range coherence. In this work, we propose the Task Memory Engine (TME), a lightweight and structured memory module that tracks task execution using a hierarchical Task Memory Tree (TMT). Each node in the tree corresponds to a task step, storing relevant input, output, status, and sub-task relationships. We introduce a prompt synthesis method that dynamically generates LLM prompts based on the active node path, significantly improving execution consistency and contextual grounding. Through case studies and comparative experiments on multi-step agent tasks, we demonstrate that TME leads to better task completion accuracy and more interpretable behavior with minimal implementation overhead. A reference implementation of the core TME components is available at https://github.com/biubiutomato/TME-Agent, including basic examples and structured memory integration. While the current implementation uses a tree-based structure, TME is designed to be graph-aware, supporting reusable substeps, converging task paths, and shared dependencies. This lays the groundwork for future DAG-based memory architectures.

Related papers

• Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents [72.3752981234916]
  Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks.<n>We present Memory as a Controlled Process (MemCon), a framework that models memory operations as a Markov Decision Process.<n>MemCon consistently outperforms multiple memory baselines by up to 15.2 points in task success while reducing token consumption by 5-20%.
  arXiv  Detail & Related papers  (2026-07-15T08:32:40Z)
• Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning [40.577016426387694]
  Multi-modal large language models (MLLMs) depend on in-context learning (ICL) for rapid task adaptation.<n>Existing memory compression approaches rely on rigid token removal or sample-dependent importance estimation.<n>We introduce TASM, a training-free framework that addresses these limitations through task-aware, structure-preserving, and dynamically accessible memory construction.
  arXiv  Detail & Related papers  (2026-06-10T09:30:25Z)
• Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents [29.28371047415946]
  HORMA is a hierarchical organize-and-Retrieve Memory Agent for large language models.<n>It decomposes working memory into two stages: structured memory construction and navigation-based retrieval.<n>It consistently achieves better efficiency-performance trade-offs and generalizes effectively to unseen tasks.
  arXiv  Detail & Related papers  (2026-06-10T05:49:14Z)
• Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents [51.30250860677378]
  We propose MRAgent, a framework that combines an associative memory graph with an active reconstruction mechanism.<n>Running on a Cue-Tag-Content graph, our active reconstruction mechanism integrates reasoning directly into memory access.<n>Experiments on the LoCoMo benchmark and LongMemEval benchmark demonstrate significant improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-06-04T11:29:46Z)
• GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0) [56.81743709880371]
  Long-horizon large language model (LLM) agents are fundamentally limited by context.<n>We argue that long-horizon performance is determined not by context length, but by how much decision-relevant information is maintained within a finite context budget.<n>We present GenericAgent (GA), a general-purpose, self-evolving LLM agent system built around a single principle: information density and context.
  arXiv  Detail & Related papers  (2026-04-18T17:59:15Z)
• PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents [74.4491017652226]
  We propose PlugMem, a task-agnostic memory module that can be attached to arbitrary LLM agents without task-specific redesign.<n>Motivated by the fact that decision-relevant information is concentrated as abstract knowledge rather than raw experience, we draw on cognitive science to structure episodic memories into a compact, knowledge-centric memory graph.<n>We evaluate PlugMem unchanged across three benchmarks (long-horizon conversational question answering, multi-hop knowledge retrieval, and web agent tasks)
  arXiv  Detail & Related papers  (2026-02-06T18:55:38Z)
• Learning to Share: Selective Memory for Efficient Parallel Agentic Systems [49.78267008828593]
  Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results.<n>Recent approaches deploy multiple agent teams running in parallel to explore diverse reasoning trajectories.<n>We propose Learning to Share (LTS), a learned shared-memory mechanism for parallel agentic frameworks.
  arXiv  Detail & Related papers  (2026-02-05T18:20:21Z)
• Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents [57.38404718635204]
  Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows.<n>Existing methods typically handle long-term memory (LTM) and short-term memory (STM) as separate components.<n>We propose Agentic Memory (AgeMem), a unified framework that integrates LTM and STM management directly into the agent's policy.
  arXiv  Detail & Related papers  (2026-01-05T08:24:16Z)
• Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory [89.65731902036669]
  Evo-Memory is a streaming benchmark and framework for evaluating self-evolving memory in large language model (LLM) agents.<n>We evaluate over ten representative memory modules and evaluate them across 10 diverse multi-turn goal-oriented and single-turn reasoning and QA datasets.
  arXiv  Detail & Related papers  (2025-11-25T21:08:07Z)
• ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning [6.600538353483611]
  We propose a hierarchical task-planning method that decomposes a complex goal into more manageable subgoals within a dynamically constructed agent tree.<n>ReAcTree consistently outperforms strong task-planning baselines such as ReAct across diverse large language models.
  arXiv  Detail & Related papers  (2025-11-04T09:55:40Z)
• TALM: Dynamic Tree-Structured Multi-Agent Framework with Long-Term Memory for Scalable Code Generation [0.0]
  Agentic code generation requires large language models capable of complex context management and multi-step reasoning.<n>We propose TALM, a dynamic framework that integrates structured task decomposition, localized re-reasoning, and long-term memory mechanisms.<n> Experimental results on HumanEval, BigCodeBench, and ClassEval benchmarks demonstrate that TALM consistently delivers strong reasoning performance and high token efficiency.
  arXiv  Detail & Related papers  (2025-10-27T05:07:36Z)
• RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory [57.449129198822476]
  RCR is a role-aware context routing framework for multi-agent large language model (LLM) systems.<n>It dynamically selects semantically relevant memory subsets for each agent based on its role and task stage.<n>A lightweight scoring policy guides memory selection, and agent outputs are integrated into a shared memory store.
  arXiv  Detail & Related papers  (2025-08-06T21:59:34Z)
• MapAgent: Trajectory-Constructed Memory-Augmented Planning for Mobile Task Automation [5.433829353194621]
  MapAgent is a framework that leverages memory constructed from historical trajectories to augment current task planning.<n>We introduce a coarse-to-fine task planning approach that retrieves relevant pages from the memory database based on similarity.<n>Results in real-world scenarios demonstrate that MapAgent achieves superior performance to existing methods.
  arXiv  Detail & Related papers  (2025-07-29T16:05:32Z)
• Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents [19.04968632268433]
  We propose a hierarchical memory architecture for Large Language Model Agents (LLM Agents)<n>Each memory vector is embedded with a positional index encoding pointing to its semantically related sub-memories in the next layer.<n>During the reasoning phase, an index-based routing mechanism enables efficient, layer-by-layer retrieval without performing exhaustive similarity computations.
  arXiv  Detail & Related papers  (2025-07-23T12:45:44Z)
• MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents [84.62985963113245]
  We introduce MEM1, an end-to-end reinforcement learning framework that enables agents to operate with constant memory across long multi-turn tasks.<n>At each turn, MEM1 updates a compact shared internal state that jointly supports memory consolidation and reasoning.<n>We show that MEM1-7B improves performance by 3.5x while reducing memory usage by 3.7x compared to Qwen2.5-14B-Instruct on a 16-objective multi-hop QA task.
  arXiv  Detail & Related papers  (2025-06-18T19:44:46Z)
• G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems [44.844636264484905]
  Large language model (LLM)-powered multi-agent systems (MAS) have demonstrated cognitive and execution capabilities that far exceed those of single LLM agents.<n>We introduce G-Memory, a hierarchical, agentic memory system for MAS inspired by organizational memory theory.<n>G-Memory improves success rates in embodied action and accuracy in knowledge QA by up to $20.89%$ and $10.12%$, respectively.
  arXiv  Detail & Related papers  (2025-06-09T03:43:46Z)
• Task Memory Engine: Spatial Memory for Robust Multi-Step LLM Agents [0.0]
  Large Language Models (LLMs) falter in multi-step interactions due to reliance on linear, unstructured context.<n>We introduce the Task Memory Engine (TME), a modular memory controller that transforms existing LLMs into robust, revision-aware agents.<n>TME implements a spatial memory framework that replaces flat context with graph-based structures to support consistent, multi-turn reasoning.
  arXiv  Detail & Related papers  (2025-05-26T02:53:22Z)
• Rethinking Memory in AI: Taxonomy, Operations, Topics, and Future Directions [55.19217798774033]
  Memory is a fundamental component of AI systems, underpinning large language models (LLMs) based agents. We introduce six fundamental memory operations: Consolidation, Updating, Indexing, Forgetting, Retrieval, and Compression. This survey provides a structured and dynamic perspective on research, benchmark datasets, and tools related to memory in AI.
  arXiv  Detail & Related papers  (2025-05-01T17:31:33Z)
• Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge [12.367471198090655]
  Task Arithmetic (TA), which combines task vectors derived from fine-tuning, enables multi-task learning and task forgetting but struggles to isolate task-specific knowledge from general instruction-following behavior.<n>We propose Layer-Aware Task Arithmetic (LATA), a novel approach that assigns layer-specific weights to task vectors based on their alignment with instruction-following or task-specific components.
  arXiv  Detail & Related papers  (2025-02-27T15:22:14Z)
• PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision Transformer [76.39111896665585]
  Incremental Learning (IL) aims to learn deep models on sequential tasks continually. Recent vast pre-trained models (PTMs) have achieved outstanding performance by prompt technique in practical IL without the old samples.
  arXiv  Detail & Related papers  (2024-07-04T10:37:58Z)
• Planning with Multi-Constraints via Collaborative Language Agents [13.550774629515843]
  This paper introduces Planning with Multi-Constraints (PMC), a zero-shot methodology for collaborative multi-agent systems.<n>PMC simplifies complex task planning with constraints by decomposing it into a hierarchy of subordinate tasks.<n>PMC achieved an average 42.68% success rate on TravelPlanner, significantly higher than GPT-4 (2.92%), and outperforming GPT-4 with ReAct on API-Bank by 13.64%.
  arXiv  Detail & Related papers  (2024-05-26T10:33:17Z)
• Cross-Task Affinity Learning for Multitask Dense Scene Predictions [5.939164722752263]
  Multitask learning (MTL) has become prominent for its ability to predict multiple tasks jointly. We introduce the Cross-Task Affinity Learning (CTAL) module, a lightweight framework that enhances task refinement in multitask networks. Our results demonstrate state-of-the-art MTL performance for both CNN and transformer backbones, using significantly fewer parameters than single-task learning.
  arXiv  Detail & Related papers  (2024-01-20T05:31:47Z)
• ADaPT: As-Needed Decomposition and Planning with Language Models [131.063805299796]
  We introduce As-Needed Decomposition and Planning for complex Tasks (ADaPT) ADaPT explicitly plans and decomposes complex sub-tasks as-needed, when the Large Language Models is unable to execute them. Our results demonstrate that ADaPT substantially outperforms established strong baselines.
  arXiv  Detail & Related papers  (2023-11-08T17:59:15Z)
• Provable Pathways: Learning Multiple Tasks over Multiple Paths [31.43753806123382]
  We develop novel generalization bounds for empirical risk minimization problems learning multiple tasks over multiple paths. In conjunction, we formalize the benefits of resulting multipath representation when adapting to new downstream tasks.
  arXiv  Detail & Related papers  (2023-03-08T02:25:28Z)
• Decomposed Prompting: A Modular Approach for Solving Complex Tasks [55.42850359286304]
  We propose Decomposed Prompting to solve complex tasks by decomposing them (via prompting) into simpler sub-tasks. This modular structure allows each prompt to be optimized for its specific sub-task. We show that the flexibility and modularity of Decomposed Prompting allows it to outperform prior work on few-shot prompting.
  arXiv  Detail & Related papers  (2022-10-05T17:28:20Z)
• Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization [101.72755769194677]
  We formulate it as a few-shot reinforcement learning problem where a task is characterized by a subtask graph. Our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks. Our experiment results on 2D grid-world and complex web navigation domains show that the proposed method can learn and leverage the common underlying structure of the tasks for faster adaptation to the unseen tasks.
  arXiv  Detail & Related papers  (2022-05-25T10:44:25Z)
• Task Adaptive Parameter Sharing for Multi-Task Learning [114.80350786535952]
  Adaptive Task Adapting Sharing (TAPS) is a method for tuning a base model to a new task by adaptively modifying a small, task-specific subset of layers. Compared to other methods, TAPS retains high accuracy on downstream tasks while introducing few task-specific parameters. We evaluate our method on a suite of fine-tuning tasks and architectures (ResNet, DenseNet, ViT) and show that it achieves state-of-the-art performance while being simple to implement.
  arXiv  Detail & Related papers  (2022-03-30T23:16:07Z)
• MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning [71.90902837008278]
  We propose to incorporate neural architecture search (NAS) into general-purpose multi-task learning (GP-MTL) In order to adapt to different task combinations, we disentangle the GP-MTL networks into single-task backbones. We also propose a novel single-shot gradient-based search algorithm that closes the performance gap between the searched architectures.
  arXiv  Detail & Related papers  (2020-03-31T09:49:14Z)

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.