arXiv AI
Engram Injection: A Study of Temporal Validity in Parametric Language-Model Memory
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Oct 28
Beyond Update Counts: A Control Map for Evaluating Test-Time Model Updates
The paper introduces the Control Map, an evaluation framework for test‑time model updates that records the specific updates made before each answer and separately assesses acquisition, retention, locality, and performance in new settings. It demonstrates that update scheduling can dramatically affect accuracy, that learning an edit does not guarantee lasting or contained changes, and that no single editor consistently outperforms others across models and benchmarks. The authors argue that evaluations should report update histories and assess these dimensions separately.
arXiv AI
6d ago
CALM: Conflict-Aware Lifecycle Memory Governance for Long-Horizon Language Agents
CALM is a conflict‑aware lifecycle memory governance framework designed for long‑horizon language agents. It transforms heterogeneous records into evidence‑grounded memory cells, updates their validity and lifecycle states using support, conflict, and dependency signals, and admits query‑appropriate evidence through training‑free or learned gating based on temporal applicability. Experiments on LongMemEval‑S and LoCoMo with Qwen and GPT backbones show that CALM outperforms state‑of‑the‑art baselines, improves evidence selection, suppresses erroneous memories, and preserves superseded records for accurate earlier‑state reasoning.
arXiv Computation and Language
Oct 16
TEM: Temporal State Tracking Memory for Large Language Model Agents
The paper introduces Temporal State Tracking Memory (TEM), a training‑free framework that stores facts as versioned records linked to their sources and retrieves the relevant versions in source order, labeling historical records before passing them to the answer model. TEM incorporates event memory and original dialogue turns to fill gaps in structured facts. Evaluations on 420 questions from 600 sessions with 60 personas show high key‑entity hit rates (75.71–97.62%) and significant improvements when historical labels are added, while keeping evidence compact (94–118 tokens per answer).
arXiv AI
Jun 17
MemTrace: Probing What Final Accuracy Misses in Long-Term Memory
arXiv:2606. 17328v1 Announce Type: new Abstract: LLM agents increasingly maintain long-term memory of user facts across sessions.
arXiv AI
Sep 11
What Should an Agent Forget? Separating What Is Stored from What Is Used
The paper introduces RD-Forget, a training‑free framework that separates what a persistent language agent stores from what it uses at answer time. It keeps a source archive of all observations while a query‑conditioned memory view filters evidence relevant to the current question, using a frozen language‑model curator to group facts into semantic slots and preserve multi‑hop relations. The approach employs rate‑distortion principles to stay within a memory budget and demonstrates improvements across conversational memory, knowledge updating, fact consolidation, long‑context reasoning, and personalization tasks.
arXiv AI
Oct 5
What Should World Models Forget? Stratified Retention for Continual Adaptation
The paper argues that continual learning for world models must differentiate between knowledge that should never be revised—such as physics and object permanence—and knowledge that should be updated when the environment changes. It critiques existing forgetting metrics and benchmarks for failing to capture this distinction, and proposes a differential retention approach that tracks invariant regression testing and revision latency throughout the adaptation process.