Synthius-Mem: Brain-Inspired Hallucination-Resistant Persona Memory Achieving 94.4% Memory Accuracy and 99.6% Adversarial Robustness on LoCoMo

• URL: http://arxiv.org/abs/2604.11563v1
• Date: Mon, 13 Apr 2026 14:47:48 GMT
• Title: Synthius-Mem: Brain-Inspired Hallucination-Resistant Persona Memory Achieving 94.4% Memory Accuracy and 99.6% Adversarial Robustness on LoCoMo
• Abstract summary: We present Synthius-Mem, a brain-inspired structured persona memory system that takes a fundamentally different approach.<n>On the LoCoMo benchmark, Synthius-Mem achieves 94.37% accuracy, exceeding all published systems.<n> Synthius-Mem reduces token consumption by 5x compared to full-context replay while achieving higher accuracy.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Providing AI agents with reliable long-term memory that does not hallucinate remains an open problem. Current approaches to memory for LLM agents -- sliding windows, summarization, embedding-based RAG, and flat fact extraction -- each reduce token cost but introduce catastrophic information loss, semantic drift, or uncontrolled hallucination about the user. The structural reason is architectural: every published memory system on the LoCoMo benchmark treats conversation as a retrieval problem over raw or lightly summarized dialogue segments, and none reports adversarial robustness, the ability to refuse questions about facts the user never disclosed. We present Synthius-Mem, a brain-inspired structured persona memory system that takes a fundamentally different approach. Instead of retrieving what was said, Synthius-Mem extracts what is known about the person: a full persona extraction pipeline decomposes conversations into six cognitive domains (biography, experiences, preferences, social circle, work, psychometrics), consolidates and deduplicates per domain, and retrieves structured facts via CategoryRAG at 21.79 ms latency. On the LoCoMo benchmark (ACL 2024, 10 conversations, 1,813 questions), Synthius-Mem achieves 94.37% accuracy, exceeding all published systems including MemMachine (91.69%, adversarial score is not reported) and human performance (87.9 F1). Core memory fact accuracy reaches 98.64%. Adversarial robustness, the hallucination resistance metric that no competing system reports, reaches 99.55%. Synthius-Mem reduces token consumption by ~5x compared to full-context replay while achieving higher accuracy. Synthius-Mem achieves state-of-the-art results on LoCoMo and is, to our knowledge, the only persona memory system that both exceeds human-level performance and reports adversarial robustness.

Related papers

• Agent Zero Memory: Provenance-Aware Long-Term Memory for LLM Agents [3.6666917625778193]
  Agent Zero Memory is a provenance-aware long-term memory system.<n>It distils a user's conversations, files, and connected sources into three parallel memory systems.
  arXiv  Detail & Related papers  (2026-08-30T06:55:59Z)
• VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction [92.2925193726566]
  VoiceMem is a memory architecture with a parallel informational left brain, an emotional right brain, and streaming memory I/O mechanisms.<n>Experiments and real-world deployment show three advantages.
  arXiv  Detail & Related papers  (2026-08-26T16:50:05Z)
• Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory [32.094723684433895]
  Long-term memory systems store what a user says in an external store and retrieve it when a related query arrives.<n>This interface rests on an assumption so natural that it is rarely stated: a memory that is needed will resemble the query that needs it.<n>We call this failure mode the implicit-association blind spot and introduce InMind, a benchmark spanning ten life domains.
  arXiv  Detail & Related papers  (2026-07-27T12:42:12Z)
• Not Forgotten: Implementation and Evaluation of a Personalized Episodic Memory for the Humanoid Robot Head Kim [0.0]
  This paper presents a lightweight episodic memory module that integrates vector-based semantic retrieval with an LLM-controlled dialog system.<n>Results show that episodic memory significantly increased perceived sociability.<n>These findings suggest that episodic memory serves as a social lubricant in embodied Human-Robot Interaction.
  arXiv  Detail & Related papers  (2026-07-27T09:11:55Z)
• MEMPROBE: Probing Long-Term Agent Memory via Hidden User-State Recovery [58.64329475683699]
  We argue that long-term memory should be evaluated as an auditable post-interaction artifact.<n>We instantiate this view in MEMPROBE, a benchmark in which a memory-equipped agent assists simulated users.<n>We find that successful assistance and recoverable memory behave as distinct capabilities.
  arXiv  Detail & Related papers  (2026-06-23T13:52:46Z)
• WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction [72.1620416874118]
  Multimodal large language models are increasingly deployed as long-horizon agents.<n>Existing benchmarks measure recall over static dialogue, collapse memory into a single end-of-task accuracy, and reduce visual observations to captions.<n>We formulate multimodal agent memory as an Action-World Interaction Loop with an observable four-stage lifecycle.
  arXiv  Detail & Related papers  (2026-05-28T04:27:20Z)
• ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Models [60.14219417402433]
  Existing memory benchmarks for LLM agents evaluate explicit recall of facts, yet overlook implicit memory where experience becomes automated behavior without conscious retrieval.<n>We introduce ImplicitMemBench, the first systematic benchmark evaluating implicit memory through three constructs drawn from standard cognitive-science accounts of non-declarative memory.<n>Our 300-item suite employs a unified Learning/Priming-Interfere-Test protocol with first-attempt scoring.
  arXiv  Detail & Related papers  (2026-04-09T10:26:32Z)
• AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents [49.63422082885992]
  We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents.<n>AdaMem organizes dialogue history into working, episodic, persona, and graph memories.<n>We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling.
  arXiv  Detail & Related papers  (2026-03-17T13:22:54Z)
• Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval [59.295767860331004]
  RF-Mem is a familiarity uncertainty-guided dual-path memory retriever.<n>It embeds human-like dual-process recognition into the retriever.<n>It consistently outperforms one-shot retrieval and full-context reasoning under fixed budget and latency constraints.
  arXiv  Detail & Related papers  (2026-03-10T06:31:44Z)
• The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPT [17.579565226391146]
  We analyze 2,050 memory entries from 80 real-world ChatGPT users.<n>A striking 96% of memories in our dataset are created unilaterally by the conversational system.<n>A significant majority of memories (84%) are directly grounded in user context.
  arXiv  Detail & Related papers  (2026-02-01T21:39:36Z)
• Mind the Gap: Why Neural Memory Fails Under Semantic Density [0.0]
  Current AI systems lack this separation, attempting both functions through neural weights alone.<n>We identify the 'Stability Gap' in online neural memory.<n>We show collapse occurs with as few as N=5 facts at high density.<n>We also identify schema drift and version ambiguity as primary failure modes in production systems.
  arXiv  Detail & Related papers  (2026-01-14T18:55:23Z)
• Agentic Learner with Grow-and-Refine Multimodal Semantic Memory [50.81667005063605]
  ViLoMem is a dual-stream memory framework that constructs compact, schema-based memory.<n>It encodes visual distraction patterns and logical reasoning errors, enabling MLLMs to learn from their successful and failed experiences.
  arXiv  Detail & Related papers  (2025-11-26T18:55:08Z)
• CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs [62.116710797795314]
  Large Language Models (LLMs) increasingly use persistent memory from past interactions to enhance personalization and task performance.<n>We present CIMemories, a benchmark for evaluating whether LLMs appropriately control information flow from memory based on task context.
  arXiv  Detail & Related papers  (2025-11-18T21:51:23Z)
• Mnemosyne: An Unsupervised, Human-Inspired Long-Term Memory Architecture for Edge-Based LLMs [1.2582867366903179]
  We introduce Mnemosyne, an unsupervised, human-inspired long-term memory architecture for edge-based large language models (LLM)<n>Our approach uses graph-structured storage, modular substance and redundancy filters, memory committing and pruning mechanisms, and probabilistic recall with temporal decay and refresh processes modeled after human memory.<n>Mnemosyne is designed for use in longitudinal healthcare assistants, where repetitive and semantically similar but temporally distinct conversations are limited by naive retrieval.
  arXiv  Detail & Related papers  (2025-10-07T03:32:53Z)
• MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation [59.31354761628506]
  Temporal context is essential for robotic manipulation because such tasks are inherently non-Markovian, yet mainstream VLA models typically overlook it.<n>We propose MemoryVLA, a Cognition-Memory-Action framework for long-horizon robotic manipulation.<n>We evaluate it on 150+ simulation and real-world tasks across three robots.
  arXiv  Detail & Related papers  (2025-08-26T17:57:16Z)
• HEMA : A Hippocampus-Inspired Extended Memory Architecture for Long-Context AI Conversations [0.0]
  Large language models (LLMs) struggle with maintaining coherence in extended conversations spanning hundreds of turns.<n>This paper introduces HEMA, a dual-memory system inspired by human cognitive processes.<n>With 10K indexed chunks, Vector Memory achieves P@5 >= 0.80 and R@50 >= 0.74, doubling the area under the precision-recall curve.
  arXiv  Detail & Related papers  (2025-04-23T14:27:12Z)

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.