mlsanityData to 14 Oct 2026

Semantic XPath: Structured Agentic Memory Access for Conversational AI

arXiv 2603.01160 ↗First posted 1 Mar 2026cs.AI cs.CLcited by 7

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

Conversational AI (ConvAI) agents increasingly maintain structured memory to support long-term, task-oriented interactions. In-context memory approaches append the growing history to the model input, which scales poorly under context-window limits. RAG-based methods retrieve request-relevant information, but most assume flat memory collections and ignore structure. We propose Semantic XPath, a tree-structured memory module to access and update structured conversational memory. Semantic XPath improves performance over flat-RAG baselines by 176.7% while using only 9.1% of the tokens required by in-context memory. We also introduce SemanticXPath Chat, an end-to-end ConvAI demo system that visualizes the structured memory and query execution details. Overall, this paper demonstrates a candidate for the next generation of long-term, task-oriented ConvAI systems built on structured memory.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 16 of its 28 references that are in the map. First posted on arXiv 1 Mar 2026.

Builds on

16 of 28 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension7 Oct
  2. 2025Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents23 Jul
  3. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 13

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  3. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  4. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  5. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  6. 2023Walking Down the Memory Maze: Beyond Context Limit through Interactive Readingcited by 133
  7. 2023MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversationcited by 97
  8. 2024From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMscited by 79
  9. 2024Selective Attention: Enhancing Transformer through Principled Context Controlcited by 16
  10. 2024Elaborative Subtopic Query Reformulation for Broad and Indirect Queries in Travel Destination Recommendationcited by 11
  11. 2025MA-DPR: Manifold-aware Distance Metrics for Dense Passage Retrievalcited by 9
  12. 2025Multimodal Item Scoring for Natural Language Recommendation via Gaussian Process Regression with LLM Relevance Judgmentscited by 9
1 more
  1. 2025A Simple but Effective Elaborative Query Reformulation Approach for Natural Language Recommendationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026Evaluating Scene-based In-Situ Item Labeling for Immersive Conversational Recommendationcited by 5
  2. 2026Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systemscited by 4
  3. 2026SafeGEO: Understanding Generative Engine Optimization Risks in Recommendation Agentscited by 4
  4. 2026Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agentscited by 3
  5. 2026MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulationscited by 1
  6. 2026The Missing Complement: State-Conditioned Minimal Sufficient Evidence for Coding Agentscited by 0
  7. 2026Have I Scene This Before? Spatially Grounded Conversational Memory for Complex Queries in Egocentric Assistantscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategies in Conversational AI Agents
  2. 2026APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI
  3. 2025Memoria: A Scalable Agentic Memory Framework for Personalized Conversational AI
  4. 2026AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications
  5. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
  6. 2026Beyond Memory Construction: Rethinking Memory Access for LLM-based Conversational Agents
  7. 2025ENGRAM: Effective, Lightweight Memory Orchestration for Conversational Agents
  8. 2025Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects