Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving Knowledge

• URL: http://arxiv.org/abs/2606.26511v1
• Date: Thu, 25 Jun 2026 01:31:53 GMT
• Title: Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving Knowledge
• Abstract summary: Retrieval-augmented generation gives agents access to accumulated knowledge, but has no model of time.<n>We present MemStrata, a retrieval memory maintaining temporal validity.<n>Across six benchmarks run locally with a 7B model, MemStrata ties RAG on static knowledge and reaches 0.95-1.00 accuracy on evolving knowledge.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Retrieval-augmented generation (RAG) gives agents access to accumulated knowledge, but has no model of time. When a fact changes (e.g., a function is renamed or API restructured), RAG retrieves both the stale and current value with near-identical embedding similarity. The agent then either abstains or serves the superseded fact. We show this is a structural problem: on a calibrated dataset, cosine similarity distinguishes a contradicted fact from a duplicated one with AUROC 0.59 (near chance), as contradictions are often more embedding-similar to the original than rephrased duplicates. We present MemStrata, a retrieval memory maintaining temporal validity. It stores facts like RAG, preserving static recall, but when a fact's value is contradicted, a deterministic (subject, relation, object) supersession rule retires the stale value in a bi-temporal ledger - with no similarity threshold and no LLM call. Across six benchmarks run locally with a 7B model, MemStrata ties RAG on static knowledge and reaches 0.95-1.00 accuracy on evolving knowledge (where RAG reaches 0.20-0.47). The central result is the stale-fact-error rate: when required to answer, RAG serves superseded values 15-40% of the time; MemStrata drives this to ~0%, a failure class RAG cannot avoid. MemStrata achieves this at retrieval latency (~2.1s) versus ~16-18s for LLM-reranking baselines. We release the harness, datasets, and a marker-free evaluation protocol for memory under knowledge evolution.

Related papers

• ReDraft, Don't Just Distill: Reference-Driven Revision for Continual VLLM Post-Training [66.72708893922605]
  Post-training of large multimodal models should add new capabilities while preserving those from pre-training.<n>SFT gives explicit target supervision that learns a task from near-zero accuracy, but its off-policy targets move the model far enough to cause forgetting.<n>We introduce ReDraft, which obtains both from the model's own failures.
  arXiv  Detail & Related papers  (2026-09-15T04:59:03Z)
• The Immutable Past: Formalizing State Mutability and Conflict Resolution in Mutable RAG [0.0]
  This paper formalizes the mechanics of State Mutability to prove that standard dense retrieval suffers from Asymptotic Recall Decay.<n>To resolve this, we introduce GC-Mem, a strict inference-time consistency protocol.
  arXiv  Detail & Related papers  (2026-09-13T15:28:07Z)
• Temporal Validity on Real Software Histories: Eliminating Stale-Fact Errors in Code-Assistant Memory over GitHub Fixes [0.0]
  Retrieval-augmented generation (RAG) has no model of time.<n>RAG retrieves both the old and new value with near-identical similarity and cannot tell which is current, so it serves the superseded value.<n>MemStrata reaches 0.91 answer accuracy versus RAG's 0.57-0.59; and, the structural result, when forced to answer RAG serves the superseded value 36-38% of the time.
  arXiv  Detail & Related papers  (2026-08-21T02:48:36Z)
• MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations [47.771518253102975]
  MicroVerse is a behavioral-science instrument that measures identity drift in generative agents.<n>Agents carry an immutable "soul file" (core values, moral boundaries, personality, goals) and inhabit a resource-scarce 50 x 50 environment.<n>Anti-self-deception emerges unprompted as the single largest semantic category of identity modification.
  arXiv  Detail & Related papers  (2026-08-16T16:31:42Z)
• Forensic Trajectory Signatures for Agent Memory Poisoning Detection [0.0]
  Successful attacks require calling memory_recall_fact before email_send_email, a transition that non-exfiltrating sessions rarely exhibit.<n>A simple rule exploiting this invariant alone achieves AUC = 0.9563.<n>A strictly prefix-only variant achieves AUC = 0.934, suggesting that real-time blocking is feasible with moderate degradation.
  arXiv  Detail & Related papers  (2026-06-29T17:09:03Z)
• ConvMemory v3: A Validity Context Layer for Conversational Memory via Target-Conditioned Relation Verification [0.0]
  ConvMemory v3 adds a validity context layer that detects and surfaces this update evidence.<n>The core mechanism is a dual-evidence gate that conditions a relation judgment on the specific target proposition.<n>On a synthetic multi-hop validity benchmark the gate reaches 90.12% +/- 1.73 accuracy.
  arXiv  Detail & Related papers  (2026-06-25T08:36:43Z)
• When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents [0.0]
  Long-answer LLM agents can fail quietly: they settle on one reading of the evidence early, then spend the rest of the run defending it.<n>We define representational commitment as cross-run hidden-state convergence at a fixed reasoning step.<n>A runtime monitor detects inconsistent trajectories from hidden states at AUROC up to 0.97 (0.85--0.88 under a stricter split)
  arXiv  Detail & Related papers  (2026-06-22T07:13:13Z)
• Learning What to Remember: A Cognitively Grounded Multi-Factor Value Model for Agentic Memory [1.2127875744950842]
  Long-running LLM agents accumulate interaction histories far larger than any context window.<n>Production systems answer with semantic similarity or recency.<n>We propose a multi-factor memory function V(m)=sum_i w_i f_i(m) over seven interpretable factors.
  arXiv  Detail & Related papers  (2026-06-11T06:17:31Z)
• Belief Memory: Agent Memory Under Partial Observability [56.41506249481312]
  We propose BeliefMem, which shifts the memory paradigm from committing to a single conclusion per observation to retaining multiple candidate conclusions with their probabilities.<n> BeliefMem preserves the uncertainty that the deterministic paradigm discards, enabling the agent to act with high confidence.<n> Empirical evaluations on LoCoMo and ALFWorld benchmarks show that, even with limited data, BeliefMem achieves the best average performance.
  arXiv  Detail & Related papers  (2026-05-07T02:03:13Z)
• Self-Aware Vector Embeddings for Retrieval-Augmented Generation: A Neuroscience-Inspired Framework for Temporal, Confidence-Weighted, and Relational Knowledge [0.0]
  Modern retrieval-augmented generation (RAG) systems treat vector embeddings as static, context-free artifacts.<n>We propose Smart, a framework that augments dense embeddings with three explicit properties -- temporal awareness, confidence decay, and relational awareness.
  arXiv  Detail & Related papers  (2026-04-22T14:13:50Z)
• Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory [22.19616466232313]
  RoMem is a drop-in temporal knowledge graph module for structured memory systems.<n>It learns from data that evolving relations should rotate fast while persistent ones should remain stable.<n>On temporal knowledge graph completion, RoMem achieves state-of-the-art results on ICEWS05-15.
  arXiv  Detail & Related papers  (2026-04-13T14:35:47Z)
• 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)
• Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents [80.33280979339123]
  We introduce Memory-T1, a framework that learns a time-aware memory selection policy using reinforcement learning (RL)<n>On the Time-Dialog benchmark, Memory-T1 boosts a 7B model to an overall score of 67.0%, establishing a new state-of-the-art performance for open-source models.
  arXiv  Detail & Related papers  (2025-12-23T06:37:29Z)
• TARG: Training-Free Adaptive Retrieval Gating for Efficient RAG [46.122203287541005]
  Training-free Adaptive Retrieval Gating (TARG) is a single-shot policy that decides when to retrieve using only a short, no-latency draft from the base model.<n>On NQ-Open, TriviaQA, and PopQA, TARG consistently shifts the accuracy-efficiency frontier.
  arXiv  Detail & Related papers  (2025-11-12T23:09:52Z)
• REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning [64.08293076551601]
  We propose a novel method of using a learned measure for identifying positive pairs. Our Retrieval-Based Reconstruction measure measures the similarity between two sequences. We show that the REBAR error is a predictor of mutual class membership.
  arXiv  Detail & Related papers  (2023-11-01T13:44:45Z)

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.