mlsanityData to 7 Oct 2026

SodaMem: Evidence-Grounded Temporal Graph Memory for LLM Agents

arXiv 2608.08055 ↗First posted 8 Aug 2026cs.AIcited by 1

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

Abstract (arXiv)

Large language model (LLM) agents that assist users over weeks of conversation must remember what is currently true, not merely what was once said. Flat RAG diaries and Markdown logs optimize needle retrieval but under-serve currency, provenance, and ordered temporal reasoning (Maharana et al. 2024; Wu et al. 2024; Packer et al. 2023; Chhikara et al. 2025). We present SodaMem, an evidence-grounded temporal graph memory that (i) extracts typed FactEvents with mandatory provenance spans, (ii) persists mention time, occurrence time, and validity with SUPERSEDES/CONTRADICTS/UPDATES edges under hybrid lexical-dense indexing, and (iii) answers via a planner-reader loop that gathers citable evidence before composing a final response. On LongMemEval-S, our store-of-record configuration reaches 92.8% accuracy (464/500; best of N=3) at mean 0.00161/question (approximately 18.3k tokens; median 0.00111 / approximately 14.6k) with deepseek-v4-flash. We compile public systems with estimable API cost into a cost table and cost-accuracy map; under these estimates SodaMem sits near the accuracy frontier at Flash-tier spend and strictly dominates several higher-cost, lower-accuracy points. Accuracy uses the same Flash model as reader and judge (self-grading); costs exclude ingest/judge and cross-system comparisons are compiled estimates rather than a single-harness bake-off.Our code is available at https://github.com/SodaMem/SodaMem

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 16 of its 48 references that are in the map. First posted on arXiv 8 Aug 2026.

Builds on

16 of 48 references.

Closest ancestors · 9

Same direction, newest first

  1. 2026RaMem: Contextual Reinstatement for Long-term Agentic Memory22 Jun
  2. 2026Profile-Graph Memory for LLM Agents: Implicit Cross-Entity Traversal through Narrative Profiles1 Jun
  3. 2026Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agents5 Mar
  4. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents14 Jan
  5. 2026TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents6 Jan
  6. 2026SimpleMem: Efficient Lifelong Memory for LLM Agents5 Jan
  7. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  8. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  9. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memory20 Jan

Other references · 7

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  4. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  5. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  6. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 266
  7. 2025MemOS: A Memory OS for AI Systemcited by 129

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Contract Memory Compiler: Resolve, Then Traversecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoning
  2. 2026Agent Zero Memory: Provenance-Aware Long-Term Memory for LLM Agents
  3. 2026TRACE: State-Aware Query Processing over Temporal Evidence Graphs for Conversational Data
  4. 2026EdgeMem: LLM-Free Agent Memory Construction and Retrieval via Evidence-Preserving Multi-Anchor Hypergraph
  5. 2026Accurate and Efficient Long-Term Memory for LLM Agents
  6. 2026HiGMem: A Hierarchical and LLM-Guided Memory System for Long-Term Conversational Agents
  7. 2026LeanMem: Simple and Efficient Long-Term Memory for LLM Agents
  8. 2026APDMem: Agent-Controlled Progressive Disclosure for Query-Adaptive Long-Term Memory