The paper introduces Dual-Path Parametric Memory (DPPM), a method for long‑term personalization of language models that leverages interaction history without requiring it in the inference context. DPPM uses two complementary paths: an Evidence path that pools historical representations to retain earlier evidence, and a Delta path that sequentially updates an associative state to capture changes. By fusing these outputs into history‑conditioned LoRA adapters, DPPM achieves superior performance on PersonaMem‑v2 (54.22%) and PrefEval (86.79%) compared to existing baselines.
arXiv:2608. 16168v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly use external memory systems to support personalization by drawing on long and evolving interaction histories, in which user preferences may be distributed across time, change with context, and conflict with earlier evidence.
DyadMem introduces a new benchmark for evaluating how long‑term agents remember user‑specific relational information, called User‑conditioned Relational Agent Memory (URAM). The dataset contains 3,065 episodes, 50,961 sessions, and 61,210 QA pairs, with detailed annotations for memory capture, update, and recall across multi‑session trajectories. Experiments on 20 models show strong performance in a gold‑memory setting but a significant drop in full‑pipeline QA, highlighting gaps in current LLM memory capabilities.
arXiv:2608. 03463v1 Announce Type: new Abstract: Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history.
arXiv:2609.14168v1 Announce Type: cross Abstract: Context parameterization enables large language models (LLMs) to internalize contexts into reusable model parameters, avoiding repeated processing ac...
arXiv:2608. 08300v1 Announce Type: new Abstract: Conversational assistants increasingly rely on persistent long-term memory to personalize responses across sessions.
The paper investigates how long‑horizon language model agents encode memory‑management signals before taking actions. By examining hidden states just prior to each action, the authors find that the model already signals the need for compression and recall, independent of context length or interaction progress, and that these signals vary across model depth. They propose the Preaction Memory with Evidence Retrieval (PaMER) framework, which uses state‑guided compression and selective evidence retrieval to reduce context consumption while preserving task performance.
arXiv:2610.33047v1 Announce Type: cross Abstract: Long-running assistants often interpret follow-up requests whose referents, constraints, and active goals were established many turns earlier. The ce...
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).
PRAGMA is a benchmark designed to evaluate personalized guidance in long‑term conversations. It includes curated longitudinal conversation histories, evidence annotations, and guidance scenarios that reflect evolving user contexts and incorrect assumptions. Experiments show that current retrieval, memory, and long‑context models struggle to recover relevant conversational evidence and to use it effectively for personalized guidance.
The paper introduces ConMem, an algorithm that uses counterfactual causal inference to improve long‑term memory management in large language model agents. It builds a benchmark called MemAlign with 1,079 curated memory cases that capture various misalignment issues such as over‑generalization, misattribution, and privacy concerns. ConMem generates counterfactual interaction scenarios to audit retention decisions, leading to higher accuracy (75.16%) and better balance than existing methods while preserving personalization.
The paper introduces T$^2$Mem, a Test-Time Memory construction framework that defers memory building to inference, allowing large language models to adaptively retrieve and organize episode-level metadata and raw interactions during reasoning. By extracting lightweight metadata offline and progressively constructing query-specific memory at test time, T$^2$Mem reduces overhead and improves performance on long-horizon tasks. Experiments on LoCoMo and LongMemEval demonstrate consistent gains over strong baselines across various backbone LLMs.
arXiv:2605.01688v2 Announce Type: replace-cross Abstract: Long-horizon memory systems increasingly improve how evidence is stored and retrieved, yet the generator must still reason over fragments who...