Parametric Memory

Large Language Models (LLMs) perform well on reasoning benchmarks, but it remains unclear whether this reflects genuine contextual reasoning or reliance on facts memorized in their parameters. We investigate this by distinguishing two possibilities: a broad \textit{memorization bias}, where familiar content improves reasoning performance, and the \textit{Strong Parametric Shortcut Hypothesis}, where models skip reasoning entirely and recall stored answers. To test these effects, we introduce \textbf{MemoReason}, a human-curated benchmark that pairs factual reasoning tasks with structurally identical \fictitiousterm{} versions where real entities like people, companies, or dates are systematically replaced by \fictitiousterm{} ones of the same type. This \scorerevision{preserves task structure and specified reasoning operations} while varying the familiarity of the context, allowing controlled measurement of how the parametric memory affects reasoning. \revision{Our evaluation of recent LLMs reveals consistent and statistically significant performance drops of up to 15.7% in the fictitious setting, demonstrating a clear memorization bias.} However, a targeted analysis of \revision{questions failed in the fictitious setting} shows that models rarely respond with the corresponding factual answer, indicating that direct parametric shortcuts are not the dominant failure mode. These findings suggest that parametric memory influences reasoning through mechanisms more complex than simple factual recall. \textbf{MemoReason} provides a controlled framework for studying these mechanisms and for extending paired factual-fictitious{} evaluation to broader reasoning settings.

Gradient updates on different data generally do not commute: training a language model on two data sources in opposite orders gives different weights, even with the same data and total exposure. Loss or benchmark deltas show that the models differ, not where. We ask whether this path dependence leaves a parametric training-history memory: a weight component that flips sign when the two sources are swapped, is localized in output space, changes the held-out loss gap between the two orders under targeted interventions, and reveals which trained model came from which order. For one small SGD step of size $η$ on each of sources $A$ and $B$, the weight difference $θ_{AB}-θ_{BA}$ is, to leading order, $η^2 b_{AB}$, where $b_{AB}=H_Bg_A-H_Ag_B$ is the Lie bracket of the two gradient fields at the base model. We define commutator memory by projecting the bracket through the logits into one score per vocabulary token; the scores sum to the bracket's prediction of the gap. The scores are localized: on three models, the same readout of the measured $θ_{AB}-θ_{BA}$, or of a bracket from disjoint batches, shares 82-99% of the original top-20 tokens, versus 35-49% for norm-matched random directions. They are causally actionable: in Qwen-3-4B SFT, downweighting the ten tokens with the largest predicted share of the gap closes a median 32% of the measured gap, while frequency-matched tokens with near-zero scores have almost no effect. The weights themselves carry the component: projecting the difference between the two trained models onto $b_{AB}$ identifies which came from which order in 92% of cases across four LLMs (chance 50%). Controlled tests also cover matched-batch DPO, a frozen-rollout GRPO-style objective, and an AdamW endpoint check. The memory is defined per source pair, not per example, and its projection on $b_{AB}$ decays with further training.

At test time, large language models (LLMs) can encode historical information in activation memory (i.e., KV caches) and parametric memory (i.e., updated parameters). While activation memory is generally considered effective for factual recall and parametric memory for learning new tasks, their interplay remains unclear. In this work, we systematically investigate the role of memory in few-shot learning through controlled experiments. We find that activation memory is superior for recalling facts, whereas parametric memory does not consistently outperform activation memory in task learning. Moreover, our experiments show that the composite task, Conditional Arithmetic, requires the synergy of both memory types. Through neuron-level analysis, we find that the model activates distinct sets of neurons when accessing the same historical information through activation versus parametric memory. When both memory types are combined, the model recruits neurons from both sets, which is crucial for solving Conditional Arithmetic. These findings suggest that neither memory mechanism alone is sufficient for this composite task, highlighting the importance of their collaboration.

Long-running LLM agents require memory that persists and evolves across sessions. Text-based memory retrieves and reconstructs past interactions at every query, making long-horizon performance increasingly dependent on retrieval quality and contextual reasoning as histories grow. Parametric memory encodes experience directly into model computation, but existing approaches provide limited support for cross-session memory evolution. Their coupling to a specific backbone further restricts memory reuse after model replacement. We introduce RPMem, a two-stage architecture that compiles each session into a model-independent latent memory through forward computation and selectively integrates it with retained memory via a task-trained recurrent gate. The consolidated memory is then mapped to backbone-specific low-rank adaptation (LoRA) parameters, allowing the encoding capability to transfer when the backbone is replaced. Evaluation across three long-term memory benchmarks and five diverse backbones demonstrates broad generalization with near-constant update cost and memory footprint. With Qwen3-8B on PERMA, RPMem reaches 85.52%, outperforming the strongest parametric and text-based baselines by 5.32 and 12.98 percentage points, respectively. Ablations validate the complementary roles of session compilation and cross-session consolidation, while dynamics analyses reveal that the gate acquires task-specific memory integration strategies. These results establish RPMem as a lifecycle-independent parametric memory framework that maintains evolving cross-session memory that remains reusable across backbone replacements. Our implementation is available at https://github.com/Quark-Medical/rpmem/tree/main.

Large language models (LLMs) offer a scalable approach to social simulation, but their credibility depends on how agents are constructed. Existing methods can partially reproduce population-level patterns, yet often fail to capture human-like diversity. Our analysis shows that static-profile agents exhibit stronger demographic separation and within-group compression than humans, a pattern consistent with identity essentialism: demographic labels can encourage models to treat group-average tendencies as individual traits, homogenizing responses within groups. We argue that this limitation arises from two related factors: sparse, static agent representations and the limited ability of prompt-only memory to persistently integrate experience. Inspired by complementary memory systems, we propose LifeMem, a longitudinal memory framework that combines structured life-event retrieval with agent-specific parametric memory for experience integration. Experiments on Understanding Society with three LLMs show that LifeMem improves alignment with human data in terms of response distributions, overall and within-group diversity, and patterns of within-person response change across life stages. These findings highlight the value of longitudinal life-event memory for constructing more faithful and dynamically evolving social agents.

Gist-based context compression---summarising older conversation history into compact representations---is a common approach in long-horizon language model agents, yet its effect on different types of memory retrieval is poorly understood. We use Salience-Weighted Consolidation (SWC), a biologically-inspired compression framework motivated by sleep-based memory consolidation, as a diagnostic probe to study when gist compression helps and when it hurts. SWC scores conversation history by salience, partitions it into priority tiers, and applies structured gist abstraction to mid-priority content. Evaluating four conditions on all ten LoCoMo conversations---1,935 matched text-only questions in total, 1,501 used in the primary aggregate after excluding Category 5 (adversarial) questions---at temperature 0, we find a consistent task-type interaction: gist compression substantially outperforms truncation on multi-hop reasoning and single-hop factual questions, but temporal questions remain substantially harder under compression, with compressed conditions scoring well below the full-context reference on the conversations where both are evaluated. We trace this failure to a specific mechanism: the gist abstraction prompt preserves relational and event structure while discarding dates and times. A preservation analysis across all ten conversations confirms the mechanism: an approximately 20-fold increase in temporal expression preservation (3.05% to 62.39%) with a one-sentence prompt modification, while named entity and event preservation rates barely change (x1.02 and x1.11), demonstrating that the fix is a precision instrument. The prompt modification recovers +0.314 [0.254, 0.375] judge accuracy on category-2 (temporal) questions in the matched set. Code and results: https://github.com/kyrkewood/sleeping-agent.

Omnimodal language models (OLMs) enable unified audio-visual understanding, but processing long joint token sequences makes inference computationally prohibitive. While recent token compression methods attempt to alleviate this burden, compressing modalities in isolation often destroys the temporal cross-modal anchors necessary for coherent reasoning. We introduce Omni2LoRA, a two-stage framework for efficient parametric memory compression via coherence-preserving context distillation that bypasses the token bottleneck entirely. First, a Perceiver hypernetwork processes intermediate representations from a frozen OLM to encode the multimodal context into a full-rank Low-Rank Adaptation (LoRA) adapter in a single forward pass. To prevent the resulting parameter footprint from scaling linearly with recording length, we optimize a discrete rank allocation policy via Group Relative Policy Optimization (GRPO) that uses a modality-ablated counterfactual reward to explicitly penalize the loss of audio-visual coherence, forcing the model to allocate its fixed sub-linear rank budget to synergistic cross-modal anchors rather than isolated visual features. Across three omnimodal backbones, Omni2LoRA operating at a 30% rank budget outperforms direct full-context inference and strong token-compression baselines (OmniZip, OMAC, O-MARC) on four audio-visual question answering benchmarks, improving average accuracy by 8-12% over the strongest baseline and remaining stable under compression ratios as tight as 75%, where token-pruning methods degrade sharply. By converting multimodal memory into a fixed-budget, reusable parameter state, our method drives answer-time multimodal-token load to zero, cutting per-query Time to First Token (TTFT) by up to 12x relative to full-context inference and amortizing to under 0.5s after a handful of queries.

Decoder-only language models entangle long-term memory and reasoning in a single parameter set, making it difficult to scale memory capacity independently. Memory Decoder introduces a parametric long-term memory module but only studies it at a relatively small scale. In this work, we present Memory Decoder at Scale, scaling memory models up to 6.9B parameters and pretraining them on 300B tokens. At this data scale, the combined cost of indexing and search makes a standard Faiss pipeline infeasible. We address this bottleneck with a distributed pipeline for Faiss indexing and retrieval, together with sparse, batch-wise loading of kNN distributions. Across model scales, we find that allocating more parameters to memory yields a better parameter-performance tradeoff than scaling the base model alone. On 17 benchmarks, pairing a 6.9B general memory with Pythia-410M raises its average score from 29.86 to 37.34, surpassing Pythia-12B (37.24) with 39% fewer total parameters. For Qwen3 Base models ranging from 0.6B to 14B, 1.7B domain memories improve the average score across the three domains by more than 9 points at every scale. Overall, our results demonstrate that independently scaling pretrained memory offers a more parameter efficient path to improving language model performance.

Large language models (LLMs) have demonstrated strong capabilities in knowledge acquisition and reasoning, yet their ability to retain previously acquired knowledge under repeated updates remains insufficiently understood. Existing evaluation paradigms primarily focus on single-step reasoning or static knowledge editing, which fail to capture the temporal dynamics of knowledge retention and degradation during continual model modification. In this work, we propose ForgetBench, a benchmark designed to systematically characterize forgetting behavior in LLMs under continual knowledge editing. ForgetBench introduces two complementary evaluation paradigms, namely concept-based QA and scenario-based QA, to disentangle isolated factual retention from structured relational knowledge preservation. Building upon a sequential editing framework, we construct temporally ordered knowledge streams and evaluate model behavior across multiple editing stages. To quantitatively analyze long-term retention dynamics, we further introduce a unified evaluation framework that models knowledge evolution over time, enabling the measurement of temporal decay, retention strength, and cross-instance stability. Extensive experiments across diverse models and editing methods demonstrate that existing approaches fail to strike a balance between long-term retention and generalization quality. Our findings highlight the need for more robust memory mechanisms that can effectively acquire, update, and preserve knowledge over time in future LLMs. Code will be released upon acceptance.

Memory is essential for LLM agents to accumulate task experience and reuse task-specific execution strategies. However, real-world deployment over boundary-agnostic and evolving task streams exposes a fundamental stability-plasticity dilemma. External retrieval-based memory can rapidly absorb new evidence, but it often fails to internalize recurring execution patterns and incurs inference-time retrieval overhead. Parametric memory enables stable and efficient execution once learned, but typically relies on explicit task boundaries and fixed parameter budgets. Inspired by the human brain, which balances plasticity and stability through complementary episodic storage and gradual consolidation, we propose UniMem, a self-routing framework for autonomous memory management. UniMem uses learnable routing tokens as memory controllers, enabling adaptive coordination between complementary memory pathways: novel or sparse tasks are retained in an episodic buffer for retrieval-augmented execution, while recurring and reliable patterns are consolidated into expandable parametric memory. By decoupling task identification from task execution with routing tokens and parametric memory blocks, UniMem expands memory on demand without task labels during deployment or uncontrolled parameter growth. Experiments on long-horizon streaming task sequences show that UniMem consistently outperforms baselines while maintaining execution fidelity, achieving an average gain of 4.0 EM points across three backbone models.

Adapting Large Language Models (LLMs) to specialized domains often incurs an alignment tax, as fine-tuning on domain-specific tasks can cause catastrophic forgetting and substantially degrade performance on general tasks. We propose MemSFT, which mitigates the alignment tax by decoupling domain specialization from backbone parameter updates through a plug-and-play parametric memory. The memory is trained to imitate the behavior of a non-parametric retriever operating over domain data, thereby memorizing knowledge and patterns that would otherwise be accessed through retrieval. Once trained on a specific domain, the memory can be reused across LLMs of different sizes. During generation, a learned router dynamically fuses the output distributions of the memory and backbone at each decoding step, allowing domain expertise to be invoked selectively. Across biology, geoscience, and law, evaluations with models ranging from Qwen3-8B to Qwen3-235B-A22B show that MemSFT consistently improves domain performance with negligible degradation in general performance, whereas full SFT suffers severe forgetting on general tasks. Overall, our results demonstrate a practical path to decoupling general model capabilities from domain-specific knowledge at the parameter level, thereby equipping LLMs with new specialized capabilities without compromising their general capabilities.

With the rise of parametric memory, LoRA-based External Parametric Memory (EPM) has emerged as a modular solution, but existing routing methods often introduce additional training, deployment, and maintenance overhead. This raises a natural question: can a LoRA-based EPM bank be routed without maintaining an additional routing component? However, existing zero-shot LoRA routing methods still face two problems under the EPM setting: (1) their evaluations are scattered across different task settings rather than organized around EPM access, and (2) their routing signals lack a unified perspective to guide systematic improvement. To address these problems, we organize PMD-Bench, covering document-level, domain-level knowledge, and task-skill, and propose Parametric Memory Decoding (PMD), the first framework designed to systematically improve zero-shot LoRA routing by reframing it as decoding activations over external parametric memory. Based on PMD, we further instantiate PMDRouter, which scores each LoRA by its response magnitude from a single base-model prefill. Experiments on PMD-Bench show that PMDRouter achieves the strongest internal-signal performance across multiple zero-shot routing settings. These results demonstrate the feasibility of zero-shot LoRA routing and suggest that PMD can serve as a general framework for improving zero-shot routing methods. Sources: Github (https://anonymous.4open.science/r/Parametric-Memory-Decoding-872A/)

Limited Memory Language Models (LMLMs) externalize factual knowledge to a database to enable deletion-based unlearning without retraining. Existing evaluations measure post-deletion correctness in aggregate and cannot tell whether a deleted fact persists through residual parametric memory, alternative retrieval paths, or near-neighbor retrieval artifacts. We propose a causal auditing framework that holds the model fixed and varies the database state at inference time across three interventions: FULL, DEL-ON, and DEL-OFF. The framework decomposes post-deletion behavior into parametric leakage L(f), retrieval-mediated correctness R(f), and a retrieval artifact rate grounded in the inference-time retrieval trace. We apply it to 12,228 alias-closure deletions across thirteen databases, including four adversarial topologies (Base, Alias, Noise, Collision) we construct in three domains, and six prompt formulations. Parametric leakage is near zero in every variant and every prompt style: the model rarely returns the deleted answer in the absence of retrieval. The residual that does survive lives in the retrieval graph: retrieval-mediated correctness and the retrieval artifact rate match within rounding everywhere, so post-deletion correctness is, in our audit, predominantly reconstituted from near-neighbor retrieval. This residual ranges from 0.7% on the released LMLM database to 13.6% on the most adversarial variant, and prompt formulation does not independently control how much of a deleted fact survives. These results suggest that, for this class of LMLM and deletion procedure, the unlearning boundary is drawn primarily by the database administrator rather than by the model.

Large tabular models (LTMs), i.e., tabular foundation models leveraging in-context learning (ICL), achieve state-of-the-art performance on tabular tasks. While LLMs are known to unintentionally memorize training data, the memorization dynamics of LTMs remain largely unexplored. We investigate the potential for parametric memorization in tabular ICL. We introduce ICLMEM, a probing framework designed to separate context-based predictions from parametric memorization. Our zero-information multiple-choice context strips away valid contextual patterns to force the model to fall back on its parametric memory. Our controlled fine-tuning setup establishes membership ground truth and accounts for common pitfalls, e.g., distribution shift, feature contamination, base-rate fallacy, and the pre-trained base model acts as reference to calibrate for sample difficulty. Our controlled evaluation on a leading real-world-trained LTM detects moderate memorization signals in 8 out of 10 tasks ($\text{AUC}$ up to $0.67$ and TPR at $1\%$ FPR $>0.1$). Notably, memorization signals are strongest for low-cardinality and binary tasks. However, they largely vanish under realistic training conditions. Our findings show LTM memorization signals under specific circumstances (single-task fine-tuning with fixed samples across many epochs and small query size). To protect sensitive data, appropriate measures must be taken, which we discuss.

Large language models answer knowledge-intensive questions using both parametric memory and retrieved evidence, but neither source is uniformly reliable. Retrieval can fill knowledge gaps, yet distracting passages may override correct closed-book answers. We study this post-generation conflict as answer-level source arbitration: given Direct and RAG answers from the same frozen model, decide which source to trust. We propose TRUSTMARGIN, a training-free, plug-and-play arbitration layer that scores the two existing candidates with the model's own likelihoods. It combines a parametric-prior margin, which tests whether memory accepts the retrieved answer, with an evidence-binding margin, which discounts passage-only salience and measures question-specific support. TRUSTMARGIN selects between Direct and RAG without fine-tuning, external judges, or additional generation. Across 2WIKIMQA and CWQA with three LLaMA scales, TRUSTMARGIN consistently improves over Direct generation and BM25-RAG, recovers part of the Direct/RAG oracle gap, and generalizes to multiple training-free RAG pipelines.

Parametric retrieval augmentation encodes document information into lightweight, document-specific modules such as LoRA adapters, reducing the need to include all evidence as input context. However, it remains unclear how this parameter-side memory interacts with context-side memory stored in the KV cache. We study this interaction in document-level question answering by progressively evicting document key-value states and measuring when a document LoRA contributes beyond the retained context. We find that document LoRA adds little when the KV cache is largely intact, but becomes increasingly useful under aggressive compression, recovering 13-21 ROUGE-L points when no document context remains. The gain is largest when the base model encodes the document, and the adapter is applied only during answer generation, suggesting that document LoRA is better understood as decoding-time parametric memory than as a document encoder. Finally, QA-style supervision produces substantially stronger adapters than raw-context next-token-prediction. These results position document LoRA as a complementary memory channel whose value emerges precisely when context-side evidence is scarce.

Existing memory-augmented LLM agents store past experience exclusively in prompt space, as textual summaries or retrieved passages, while keeping model parameters frozen throughout a rollout. Such agents can \emph{look up} what they have seen but cannot \emph{learn from} it: their policy is unchanged by experience, and any information dropped from the context is permanently lost. We introduce \texttt{TMEM}, a self-evolving parametric memory framework in which the agent not only compresses history into explicit memory but also absorbs distilled supervision into fast LoRA weights $Δ_t$ via lightweight online updates, genuinely altering its future behavior within a single episode. We formalize this as an agentic decision process with fast-weight rollout dynamics: actions are sampled from $π_{θ_0+Δ_t}$, while extraction actions produce supervision that updates $Δ_t$ for subsequent decisions. This view makes the extraction policy directly optimizable by RL: training $θ_0$ improves not only task actions but also the quality of the data used for online LoRA adaptation. We further propose SVD-based initialization of the LoRA subspace to accelerate online convergence. Experiments on LoCoMo, LongMemEval-S, multi-objective search, and CL-Bench show that \texttt{TMEM} consistently outperforms summary-based and retrieval-based baselines across different model scales.

Large Language Models (LLMs) must continuously learn and update knowledge to remain effective in dynamic real-world environments. While Low-Rank Adaptation (LoRA) is widely used for such memory updates, existing studies mainly rely on qualitative downstream evaluations, leaving the quantitative capacity limits and underlying dynamics of exact parametric memory largely unexplored. To bridge this gap, we employ LoRA as a controlled memory capacity probe within the latent space to systematically quantify exact parametric memory. We introduce the Parametric Memory Law, a robust power law linking loss reduction Delta L to effective parameters and sequence length. At the token level, fine-grained analysis reveals a deterministic phase transition, demonstrating that a prediction probability of p > 0.5 constitutes a sufficient condition for verbatim recall under greedy decoding. Driven by these insights, we introduce MemFT, a threshold-guided optimization strategy that dynamically redistributes the training budget toward sub-threshold tokens. Empirical evaluations demonstrate that MemFT can enhance memory fidelity and efficiency. Code will be released at https://github.com/zjunlp/ParametricMemoryLaw.

Generative retrieval (GR) maps queries directly to document identifiers (docids) using parametric knowledge, However, this design makes corpus expansion costly: adding new documents requires updating model parameters to encode new document-docid associations incurs repeated training and catastrophic forgetting of previously indexed documents. In this work, we revisit incremental GR as an in-context retrieval problem, where newly added documents are supplied as inference-time document-docid evidence. We propose ICICLE, an in-context indexing framework that performs source-aware docid generation over both parametric memory and context-provided document-docid pairs. ICICLE combines a [COPY]-based routing mechanism, preference-based calibration, and large context adaptation to distinguish context-grounded retrieval from parametric retrieval. Experiments on MS MARCO and NQ320K show that ICICLE improves retrieval of newly introduced documents while preserving seen-document retention without corpus-specific retraining. Our analysis further shows that high-shot degradation is mainly caused by routing failure, highlighting source-selection calibration as a key bottleneck for scaling in-context generative retrieval.

Language agents increasingly operate over streams of related tasks, yet existing memory systems struggle to convert accumulated experience into reusable knowledge. Retrieval-augmented and structured memory methods record per-session observations effectively, but often couple acquisition and consolidation into a single online process, leaving the agent without a global view across sessions to discover recurring patterns, abstract shared procedures, or prune redundant entries. Inspired by complementary learning systems theory, we propose Auto-Dreamer, a learned offline consolidator for language-agent memory. Auto-Dreamer decouples fast per-session memory acquisition from slow cross-session consolidation. Given a selected working region of a typed memory bank, the consolidator treats the region as read-only evidence, performs bounded tool-use to inspect entries and provenance-linked source trajectories, and synthesizes a fresh compact replacement set that abstracts across sessions and supersedes the original region. We train Auto-Dreamer via GRPO, using end-to-end agent performance as the reward signal to learn how to consolidate memories acquired through fast online experience. Trained on ScienceWorld trajectories alone, Auto-Dreamer outperforms fixed, RL-trained, and prompted memory baselines on ScienceWorld by 7 points while using an active memory bank 12$\times$ smaller than the strongest baseline, and continues to lead on held-out ALFWorld and WebArena without retraining -- using 6$\times$ less memory than the strongest baseline on ALFWorld.

Deep learning models in medical imaging typically operate as parametric memory, diagnosing patients by recalling fixed knowledge learned during training. This contrasts sharply with clinical practice, where physicians employ analogical reasoning to diagnose new cases by referencing similar records from past exemplars. While In-Context Learning (ICL) frameworks such as Tabular Prior-Fitted Networks (TabPFN) offer a promising diagnosis-by-reference paradigm, they are designed with tabular-specific inductive priors and rely on non-differentiable preprocessing pipelines, leading to manifold mismatch and gradient fracture when applied to heterogeneous multimodal data. To address these limitations, we propose PromptDx, a novel diagnosis-by-reference framework that leverages a pre-trained TabPFN as an ICL engine while enabling seamless integration with multimodal representations. Our core contribution is a Differentiable Prompt Tuning (DPT) mechanism that aligns a Masked Multimodal Modeling module with the pre-trained ICL engine. By training a lightweight adapter as a differentiable surrogate for the engine's non-differentiable preprocessors, we enable an end-to-end optimization of multimodal prompts within the ICL paradigm. We validate our method on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset using 3D MRI and tabular biomarkers. Experiments demonstrate that our approach outperforms traditional parametric baselines. Notably, our method achieves superior performance using only 1% context samples compared to 30% in standard ICL, demonstrating exceptional manifold condensation ability. We further validate the generalizability of our DPT framework across six tabular datasets with diverse scales. Overall, our method offers a more data-efficient and clinically aligned paradigm for Alzheimer's Disease diagnosis.

Token communication has emerged as a promising framework for efficient wireless transmission by representing source data as compact semantic tokens. However, transmitting full semantic tokens still incurs considerable communication overhead. In this paper, we propose an evolving semantic token communication system with a parametric memory network over MIMO fading channels. Specifically, only an equal-length prefix of each semantic token is transmitted, which reduces transmission cost while preserving a consistent token structure for receiver-side recovery. At the receiver, a parametric memory network is introduced to reconstruct the missing suffix information from the received token prefixes, where semantic memory is stored implicitly in the network parameters. To realize this design, full semantic tokens are first organized into a codebook, and truncated tokens are paired with the codeword labels of their corresponding full tokens. Based on these token-label pairs, kNN-based teacher distributions are constructed to fine-tune a pretrained GPT-2-based recovery module, which learns to infer the codeword distribution of each incomplete token and recover the corresponding complete semantic token. In addition, an online evolution strategy is developed to periodically update the parametric memory network and the entire system using newly observed test samples, thereby improving adaptability under distribution shifts. Experimental results demonstrate that the proposed method consistently outperforms the existing evolving memory benchmark under different channel conditions and channel bandwidth ratios, with up to 1.09 dB PSNR improvement.

Generative information retrieval (GenIR) consolidates retrieval into a single neural model that decodes document identifiers (docids) directly from queries. While this model-as-index paradigm offers architectural simplicity, it is poorly suited to dynamic document collections. Unlike modular systems, where indexes are easily updated, GenIR's knowledge is parametrically encoded in its weights; consequently, standard adaptation methods such as full and parameter-efficient fine-tuning can induce catastrophic forgetting. We show that sequential adaptation improves retrieval on newly added documents but substantially degrades performance on earlier slices, exposing a pronounced stability-plasticity trade-off. To address this, we propose post-adaptation memory tuning (PAMT), a memory-only stabilization stage that augments an adapted model with a modular parametric memory head (PMH). PAMT freezes the backbone and attaches a product-key memory with fixed addressing. During prefix-trie constrained decoding, decoder hidden states sparsely query PMH to produce residual corrections in hidden space; these corrections are mapped to score adjustments via the frozen output embedding matrix, computed only over trie-valid tokens. This guides docid generation while keeping routing and backbone parameters fixed. To limit cross-slice interference, PAMT updates only a fixed budget of memory values selected using decoding-time access statistics, prioritizing entries frequently activated by the current slice and rarely used in prior sessions. Experiments on MS MARCO and Natural Questions under sequential, disjoint corpus increments show that PAMT substantially improves retention on earlier slices with minimal impact on retrieval performance for newly added documents, while modifying only a sparse subset of memory values per session.