Long Short-Term Memory

Long-term language-model agents rely on external memory across interactions. Atomic memories are particularly useful: their fine-grained semantic boundaries enable precise retrieval and direct comparison between observations. Yet accumulating atoms inevitably become redundant, overlapping, or conflicting. Existing methods often ask an LLM manager to add, update, delete, or rewrite memories directly, coupling semantic interpretation, storage decisions, and content generation in one error-prone operation. We introduce ROAM, a relation-guided framework that uses atomicity for management while allowing richer answer-time representations. ROAM classifies incoming--stored atom pairs as independent, equivalent, directionally subsuming, or conflicting, then organizes observations into active Primary and supporting Evidence roles. Fusion subsequently combines complementary details and temporal changes into compact, potentially non-atomic views. Only Primary views are retrieved for answering, preventing redundant or outdated atoms from competing independently. Across models and evaluation settings, ROAM improves answer accuracy by up to 29.8 percentage points. Ablations show complementary benefits from different relations and consistent gains from fusion beyond role organization. Mechanism analysis further finds 15.6-point higher answer-critical source recall and an 11.5-point lower confounder-token share. ROAM remains robust across manager scales.

Enterprises managing large X.509 certificate inventories face a prioritization problem: deterministic analysis tools that precisely identify standards violations are indispensable for remediation, but applying them exhaustively across millions of certificates is operationally impractical. We present X-amine509, a two-stage triage system that uses machine learning to rapidly rank certificates by predicted risk and route only the highest-risk items to full deterministic analysis. Certificate risk is quantified as a composite score derived from 177 defect checks grounded in CA/Browser Forum Baseline Requirements, NIST IR 8547/SP 800-57, and cryptographic strength criteria, weighted by security severity across four tiers ranging from cryptographic breaks to minor compliance deviations. We collected 1,027,714 X.509 certificates from Fortune 500, .gov, and .edu domains and scored each using this rubric. On a held-out test set of 201,976 certificates, our best model (Extra Trees) achieves $R^2$ of 0.993 with MAE of 2.26, while Decision Tree scores $R^2$ of 0.986 at 3.7 million certificates per second on a single machine. Ranking quality confirms the triage value: aggregate NDCG exceeds 0.997, and severity-tier classification reports 99.76% accuracy with 98.90% recall on critical-tier defects. Thirteen months later, we retrieved another 571,374 certificates to test our models' durability over time, and the Extra Trees and Decision Tree models maintain MAE below 6.8, $R^2$ of at least 0.915, aggregate NDCG above 0.988, severity-tier accuracy of at least 99.52%, and critical-tier recall of at least 97.03%. Feature importance analysis identifies validity period, Extended Key Usage configuration, negative serial number encoding, and self-signed status as the strongest risk predictors, providing coarse interpretability at the triage stage.

Accurate citations are the foundation of academic writing, tracing intellectual origins and substantiating core claims. However, manually navigating the growing volume of scientific literature is increasingly difficult, prompting reliance on automatic citation recommendation. While modern retrieval-augmented architectures have largely mitigated the fabrication of non-existent papers, current systems relying on semantic similarity struggle with misattribution, often citing authentic papers that fail to logically support the author's claim. To address this challenge, we argue that accurate citation requires a shift from similarity-based search to active, claim-level reasoning. We propose ReCite, a decoupled agentic framework that orchestrates location perception, intent-aware query planning, and reflective verification. Trained on synthesized reasoning trajectories, our agent verifies claim-evidence consistency and triggers self-correction loops when retrieved candidates lack logical support. Experiments demonstrate that our lightweight framework outperforms state-of-the-art massive generative models in strict citation accuracy. By grounding literature matching in verifiable logic rather than semantic overlap, ReCite establishes a reliable foundation for automated academic writing.

Long horizon Large Language Model (LLM) agents rely on external memory systems to preserve user preferences and task knowledge across extended interactions. Conventional retrieval mechanisms optimize semantic compatibility rather than downstream utility, frequently introducing outdated, misleading, or conflicting evidence into the active context. We present MeClear, a task conditioned memory clearance framework that identifies memories featuring negative downstream utility through cooperative attribution and selectively suppresses them from agent execution. MeClear combines Leave One Out screening with sampled cooperative Shapley attribution to distribute utility across interacting evidence, effectively resolving redundant conflict masking where single removal evaluations fail. Utilizing attribution rankings, MeClear executes a query scoped minimal clearance strategy over a nested filtration, verifying task recovery on the cleared context without permanently altering the persistent memory bank. Comprehensive experimental evaluations across ten long dialogue memory pools demonstrate that MeClear achieves a target recall of 85.9% and an overall task recovery rate of 82.3%, representing a 25.5 percentage point improvement over Leave One Out (LOO) baselines.

Language-guided robots need persistent scene memories to follow instructions, revisit objects, and resolve references to objects encountered over time. While much of language-guided scene-memory retrieval has emphasized spatial or relational references, many everyday object references specify objects by multiple persistent attributes, such as category, material, size, or surface appearance. We formalize this problem as attribute-compositional retrieval, where a fixed object-centric scene memory is queried with natural language to retrieve the object satisfying the requested attributes. To investigate this capability directly, we introduce a controlled evaluation protocol with fixed scene memories and attribute-defined targets, separating retrieval from perception and annotation ambiguities. We then propose FRAME, which turns language into query-relevant attribute weights, uses learned readouts to estimate per-attribute evidence from object embeddings, and ranks objects by aggregating this evidence according to the query. Across held-out scenes and object assets, FRAME outperforms representative scene-memory retrieval baselines while reducing post-decomposition object scoring to lightweight matrix-vector computation. These results position attribute-compositional retrieval as a complementary scene-memory capability for language-guided robots, showing that persistent object attributes can be exposed as composable evidence for accurate and efficient multi-attribute retrieval.

Large Language Model (LLM) agents are evolving from single-session tools toward long-term personal assistants that must adapt to individual users across tasks, contexts, and interactions. This shift makes memory a core requirement for personalization, since user preferences, goals, constraints, relationships, and past experiences are accumulated gradually and often change over time. Graph-based personalized memory provides a structured way to model such user information through explicit relations, temporal context, and evidence links. Such representations can model not only what an agent remembers about a user but also how memories are connected, revised, and retrieved to support personalized decisions. However, existing work remains fragmented across personalized agents and generic graph memory frameworks, making it difficult to understand the design space as a whole. This survey develops a lifecycle-oriented view of graph-based personalized memory for LLM agents. We organize existing studies around memory representation, memory evolution, memory retrieval, and memory evaluation. We further compare key design choices, discuss current evaluation practices, and open challenges in building reliable long-term personalized agents. This survey aims to clarify how graph-based memory can support adaptive, controllable, and user-centric LLM agents.

Personalized memory helps LLM agents deliver stable, tailored assistance by storing and reusing user-specific data across interactions. In multi-user scenarios, however, retrieval must consider not only semantic similarity but also whether the current requester matches the identity associated with the stored memory. We propose Bio-Memory, a biometric-aware memory architecture that conditions memory retrieval on both semantic similarity and biometric matching. Built on top of A-Mem, Bio-Memory augments each atomic memory note with a biometric embedding and uses biometric matching to form the retrieval candidate pool before semantic ranking. We evaluate Bio-Memory on LoCoMo in a 10-user shared-agent setting over 7 face benchmarks and 10 palmprint protocols. Across datasets, Bio-Memory consistently separates owner and non-owner queries. Under face-based personalization, the largest average gap reaches 27.29% / 21.15% in F1 / BLEU-1 on CALFW; under palmprint-based personalization, the corresponding gap is 25.75% / 19.22% on MS_Blue. These results support biometrics as a practical control signal for personalized memory retrieval in shared environments.

Long-term memory is a core capability for personalized LLM agents. To support it, existing memory systems organize information using various criteria such as topic segments or summary hierarchies. However, we identify two major limitations in these designs. First, they lack scene awareness: memories from unrelated life scenes share the same retrieval space, which inflates the search space and introduces cross-scene interference. Second, they encode each memory from a single perspective, making it difficult to retrieve complementary views of the same event. In this paper, we propose the CreaMem architecture, which enables scene-aware memory organization by partitioning memory into several Life Scene Memories to reduce cross-scene interference at retrieval. To go beyond the single perspective and achieve cross-memory synergy, entries are dual-coded from both episodic and trait-based perspectives within each memory. We further devise a permemory balanced sampling strategy at retrieval time. Extensive experiments on two long-term memory benchmarks show that CreaMem improves QA accuracy across all evaluation metrics, with particularly large gains on multi-hop reasoning performance, validating scene-aware partitioning and cross-memory synergy. To enhance reproducibility, we release our code in a public GitHub repository.

Large language models (LLMs) and vision-language models (VLMs) have significantly advanced zero-shot task planning for embodied agents. However, most LLM- and VLM-driven methods struggle to generate safe high-level actions due to a lack of physical risk awareness, particularly under partial observability, where hazards lie outside the immediate field of view. To address this challenge, we propose a novel safe task-planning framework, SafeMem, which constructs and maintains a long-term semantic graph memory of the open and dynamic environment. Based on egocentric observations, the proposed framework incrementally accumulates knowledge about surrounding objects and their relationships with a graph. Then, an LLM-based risk predictor evaluates candidate actions using the graph memory, triggering a conservatism-modulated replanning loop with explanations for detected hazards. Extensive experiments on the IS-Bench benchmark and a real-world robot platform demonstrate that the SafeMem framework substantially improves safe success rates compared to state-of-the-art VLM-driven task planners. Video results are available on our webpage: https://sites.google.com/view/safemem.

Agent memory systems must discard stored information when their history exceeds a fixed token budget. Existing budget-accuracy frontiers quantify the resulting loss in accuracy, but do not distinguish irreversible losses caused by eviction from recoverable retrieval failures. We introduce the restore counterfactual, a per-question paired intervention that reinstates the question's gold evidence in the read-time context and reruns the same reader. Combining the change in correctness with whether the evidence was retained after eviction classifies each oracle-answerable error as recoverable, irreversible, or residual; in the residual case, the answer remains incorrect after restoration. We evaluate FIFO, random, redundancy-aware, and LLM-importance eviction on LongMemEval-S at three budgets and under two retrieval regimes, using GPT-4o-mini as the primary reader and judge and GPT-5.4-mini as a robustness reader. Under top-k retrieval at an 80k-token budget, the irreversible share among errors corrected by restoration is 0.67-0.73 for FIFO, random, and redundancy-aware eviction, compared with 0.60 for LLM-importance. At 8k tokens, it reaches 1.00 for all four policies. Recoverable errors occur under top-k retrieval at 80k tokens but are absent under forced-gold injection by construction, so budget-accuracy results are not directly comparable unless the retrieval regime is reported. An exploratory matched-accuracy analysis detects no difference in irreversible rate among accuracy-matched policy pairs at a resolution of 1.2-6 percentage points. The same analysis detects the deliberately destructive control. To our knowledge, this is the first per-item, per-question restore-counterfactual audit of eviction for external agent-memory stores on a standard conversational benchmark.

Agent memory systems have demonstrated significant potential in long-term dialogue, personalized assistants, and video understanding. However, continuously accumulated memory introduces substantial storage and retrieval costs during inference. To address this issue, we propose \textbf{MemForest}, a general memory compression framework adaptable to various agent memory systems. Specifically, MemForest partitions historical memory into event-centric units by leveraging global semantic similarity and local temporal continuity. For each unit, it constructs a maximum spanning tree, termed an EventTree, and progressively merges redundant memory nodes by selecting high-weight edges, reducing storage overhead. Furthermore, we introduce an anchor-guided propagation retrieval mechanism that retrieves relevant memory nodes from the temporal neighborhoods of key nodes, improving retrieval accuracy. Extensive experiments demonstrate the effectiveness of MemForest. Under the unimodal Mem0 framework, MemForest retains \textbf{97.1%} of the original performance while compressing \textbf{50%} of historical memory across three benchmarks (LoCoMo, LongMemEval, and PersonaMem), achieving a \textbf{1.89x} retrieval speedup. Under the multimodal M3-Agent framework, it preserves \textbf{99.7%} of the original performance with a \textbf{50%} compression ratio across two benchmarks (M3-Bench-robot and M3-Bench-web), achieving a \textbf{2.24x} retrieval speedup. \textcolor{RoyalBlue}{\textit{Our code is available at https://github.com/Celina-love-sweet/MemForest.}}

Long-running language-model agents depend on persistent memory. Many agent-memory systems preserve history through soft revocation: a contradicted fact is marked invalid and retained rather than deleted. However, whether that mark is enforced at retrieval time is unexamined. In this paper, we measure five such systems: we load each with a revoked policy and its replacement, track whether the revoked fact is returned at retrieval and whether the agent then acts on it across nine policy scenarios and nine models, and score every trial under six defense conditions. We find that no system enforces revocation by default: the revoked fact is returned wherever the revocation label is visible to the retrieval layer, outranks its replacement, and leads agents to the unsafe action. Based on these findings, we develop a guard that sits between the agent and any memory backend and withholds records that are revoked or conflict with their replacement.

Detailed routing remains a dominant runtime bottleneck in physical design due to increasing complexity of design rules. Modern routers can struggle to resolve persistent violations under dense operating conditions. While recent work leverages reinforcement learning (RL) to dynamically select costs for each routing iteration, we find that this technique struggles with high-density designs where routing solutions are significantly harder. To address this, we present a history-aware offline RL policy which predicts iterative cost weights in these dense regimes to improve convergence across placement densities by utilizing readily available features from the router. Our policy uses conservative Q-learning similarly to prior work; however, our key insight is that addition of a lightweight LSTM architecture and additional features can retain sequence context and improve routing convergence across multiple densities and route guide qualities. Our policy can be integrated into any cost-based router with minimal pipeline changes, as it does not interfere with the core search algorithm. We evaluate our policy on held-out density and adjustment settings, including difficult operating points induced by dense placement and low guide quality. Our policy reduces design rule violations (DRVs) by an average of 92% over the top public baseline while simultaneously reducing runtime by 10%.

VLMs have shown promise for autonomous driving, yet still suffer from hallucination, weak spatio-temporal perception, and limited generalization. Recent methods improve reasoning and decision-making through CoT explanations, retrieval-augmented generation or the static injection of tool outputs. Although these mechanisms enrich the context, the model neither proactively perceives scene information nor accumulates experience after answering. To overcome these limitations, we present, to our knowledge, the first synergistic framework that tightly couples hierarchical memory with proactive tool invocation in a closed reasoning loop. Our contributions are threefold. (i) Hierarchical Driving Memory: a scene-level short-term memory maintains the dynamic scene state, and an evolving long-term memory retrieves reusable experience and tool strategies. (ii) Memory-Tool Synergistic Reasoning Framework: guided by the scene state and retrieved experience, the model adaptively invokes tools to refine its reasoning at inference time and consolidates reusable experience into a long-term memory pool offline. (iii) Data Generation and Two-stage Training Pipeline: verified memory-tool trajectories built by multi-step teacher rollout are used to train with SFT and GRPO. Our 7B model reaches an overall reasoning score of 80.03 and MCQ accuracy of 79.09% on DriveLMM-o1, surpassing the strongest baseline by 7.74 MCQ points and generalizes strongly across benchmarks. Notably, ablation and analysis studies validate the effectiveness of each component and further reveal the complementary roles of hierarchical memory. Short-term memory strengthens spatio-temporal understanding, improving STSBench accuracy by 24.2 points, while offline long-term memory consolidation yields an additional 3.57-point MCQ gain with all parameters frozen, demonstrating continual self-evolution through accumulated driving experience.

Dynamic layer routing reduces the inference cost of Large Language Models (LLMs) by learning to skip layers for individual tokens. Existing methods, however, treat each routing decision as a local operation conditioned solely on the current hidden state which is a formulation that overlooks the sequential, path-dependent nature of routing across depth: earlier decisions shape the representations seen by downstream routers, and the layer-usage objective couples all decisions jointly. We propose History-Aware Routing (HeRo), a dynamic routing framework that resolves this mismatch by introducing a router memory mechanism to maintain an explicit routing state across model depth. The memory is constructed via linear attention, incrementally aggregating preceding routing scores and their induced residual updates into a compact history representation. At each routed layer, the router conditions jointly on this accumulated state and the current hidden representation to select the executed branch. Instantiated for token-wise FFN routing, HeRo trains only lightweight routers and adapters on a frozen backbone, requiring no modification to pretrained parameters. Across Llama 3.1-8B, Llama 2-7B, and Llama 2-13B, HeRo consistently achieves the highest aggregate performance retention among ten baselines. On Llama 3.1-8B, it bypasses 26.87% of model parameters while achieving 100.24% of dense model performance across seven benchmarks, and retains 97.01% while bypassing 38.82% of model parameters under a tighter computation budget. Ablation studies confirm that removing routing history consistently degrades performance, most notably on multistep reasoning and code generation, validating that explicit routing memory enables more accurate and adaptive dynamic routing than solely conditioning on hidden state.

Updating a language model's knowledge through fine-tuning is essential for keeping its outputs current, yet can also induce factual forgetting and new hallucinations. Prior work shows that long-tail knowledge is harder to acquire and newly memorized long-tail facts are difficult to retain during later fine-tuning. We study a complementary question: among facts that a model has encoded correctly, which are most vulnerable to collateral corruption during other updates? To investigate this question under a realistic factual distribution, we construct a large-scale graph FACTPROP of verified Wikipedia facts by linking triples that share head or tail entities, thereby preserving connections among factual knowledge. We fine-tune models on factual statements and measure correct-to-incorrect facts after each update. Our results reveal a pattern distinct from prior findings on long-tail vulnerability during acquisition and retention: among facts that models already answer correctly, those associated with highly connected entities are more likely to be corrupted by neighboring updates, and updates to such facts propagate errors more broadly. Structural popularity therefore predicts both vulnerability and downstream damage. Inspired by this finding, we propose Popularity-based Anchoring (PopAnchor), a lightweight rehearsal strategy that preserves a small set of popular facts and reduces forgetting.

Tool-using language agents can delegate and revoke permissions while acting through external services. We show that two authorization histories can have identical current permissions and identical all-pairs reachability yet require opposite decisions after the same direct-edge revocation. We formalize the information needed to preserve such distinctions as a residual authorization state. We prove that exponentially many future-distinct states can share one fixed transitive closure, and give exact or tight asymptotic bounds on the state required by an exact monitor as delegation redundancy varies. ResidualAuth compiles these constructions into paired language-agent episodes. Across four open-weight models, a fixed 256-token summary solved 0-2/16 pairs, sham reads solved 0/16, and authenticated current-query reads solved 15-16/16. In a separate held-out online-memory diagnostic, exact ledger serializations fit all 128 four-coordinate pairs at both 768 and 1,024 tokens. At either cap, factually supported model-written memories sufficient for every prespecified continuation solved at most 1/128 pairs per model. A hard gate reduced eight observed unauthorized effects to zero without changing the preceding attempts. These results distinguish required authorization state, usable decision information, online state maintenance, and effect mediation.

Associative Recall (AR) is the cognitive ability to learn and retrieve links between items in memory. In NLP, AR is used as a benchmark for evaluating the in-context memory capacity of architectures such as Mamba, and has been found to strongly correlate with language modeling performance. This paper explores AR from the perspective of mechanistic interpretability, aiming to reverse-engineer the exact internal algorithm used by Mamba to perform recall. Our key insight is that Mamba performs recall by implicitly learning linear hash functions, and we identify the low-level circuit that enables this behavior. Building on these findings and inspired by theoretical tools in similarity-preserving hashing, such as the Johnson-Lindenstrauss lemma, we develop a theoretical framework for analyzing AR, which we term Recall Scaling Laws. Given the vocabulary size and the number of facts in context, this framework allows us to (1) predict the embedding and state dimensions required for Mamba to achieve perfect recall, (2) predict recall success probability given the model dimensions, and (3) analyze multi-layer models and multi-head SSM patterns. Empirical results show that our theoretical findings are accurate and predictive, offering insights into how AR capacity scales with vocabulary, state, embedding size, and architecture.

Long-running LLM agents rely on external memory to store and reuse information beyond a single context window, yet there is a fundamental tension between the continuous accumulation of interaction trajectories and the limited context capacity. The key challenge in agent memory is therefore not only to retrieve relevant records, but also to select necessary evidence under a given budget and organize it in an appropriate modality. Existing memory readout methods mainly use textual or visual forms. Text preserves high fidelity, but its linear token representation makes contents with different importance compete for the limited context at nearly uniform unit cost. Visual readout renders text into document-like images, which can use two-dimensional layouts to expose structure and emphasize key information, but it may lose fine-grained details during rendering and compression. To address this issue, we propose MEMO, a multimodal evidence memory organization method for LLM agents. MEMO first uses a trained evidence extractor to select relevant memory blocks and form evidence units with source information and presentation requirements. A trained query-conditioned memory manager assigns each unit to a textual, visual, or dual-channel carrier and selects a layout that matches the evidence structure. A deterministic memory construction module then generates the textual package and visual pages. The memory manager is trained with feedback from an offline reader that measures the utility of the guided memory plan, so that retention and presentation decisions align with downstream usage. We evaluate MEMO on four benchmarks, HotpotQA, 2WikiMultiHopQA, LoCoMo, and ALFWorld, with multiple reader backends. The results show that MEMO presents memory more efficiently with fewer memory tokens, improves downstream task performance, and builds more effective working memory under constrained budgets.

Methods for streaming language models are often discussed alongside long-context and memory systems, although they solve different problems. An attention sink can stabilize autoregressive generation over an indefinitely long stream while the model remains unable to use content that has left its recent-token cache. We argue that this distinction should be explicit in system claims and evaluation. We introduce three horizons: the stability horizon, over which predictive behavior remains well behaved; the access horizon, over which past content can still causally affect the output; and the utility horizon, over which a task retains acceptable performance. We show constructively that the stability horizon can be infinite while the access and utility horizons are finite. We then propose ThreeH, an evaluation contract that measures all three horizons under a common state and compute budget. Applying the framework to attention-sink streaming clarifies its strength, constant-memory, stable generation, without treating anchor tokens as semantic memory. The framework exposes roles for cache policies, recurrent state, retrieval, and external memory. Experiments on 128K-token streams, delayed binding recall, and delayed decisions show that attention sinks preserve local modeling but not content beyond the active cache; recurrent and retrieval state extend the semantic horizon.

Retrieval-augmented generation (RAG) enables large language models (LLMs) to answer questions by accessing external knowledge and has been widely adopted for long-term conversational memory question answering. However, existing methods suffer from two key challenges: (1) fragmented evidence scattered across temporally distant sessions, and (2) noisy content within retrieved sessions that triggers the lost-in-the-middle effect. To address these challenges, we propose MemLoc, a unified Retrieve-Localize-Generate framework for long-term conversational memory QA. For retrieval, MemLoc decomposes each session into multi-granularity memory units and performs query routing via an inner-memory graph with entropy-based granularity selection. It further models cross-session semantic and temporal dependencies through a cross-memory graph, enabling coarse-to-fine retrieval of top-K relevant memory candidates. For localization, we introduce a reasoning-based evidence locator trained with Self-reflective Hint Policy Optimization (SHPO), which performs progressive refinement by extracting query-relevant fragments within memory units to suppress noise and reranking across candidates to remove redundancy, producing a compact evidence set with lightweight location IDs. For generation, these IDs act as precise grounding signals that guide the LLM to the correct memory positions, mitigating the lost-in-the-middle effect while preserving original contextual integrity. Extensive experiments on four benchmarks demonstrate that MemLoc achieves state-of-the-art retrieval accuracy and response quality while maintaining efficiency. Our code is available at: https://github.com/Nikol-coder/MemLoc.

Proteins perform diverse cellular functions, and even single amino-acid substitutions can alter stability, activity, or molecular interactions. Protein language models (PLMs) provide a scalable approach for modeling such sequence--function relationships from unlabeled sequences, but increasing the size of dense Transformer backbones often brings substantial computational cost without consistently improving mutation-sensitive prediction. We introduce ProtLingo, an efficient PLM framework that augments a pretrained single-sequence backbone with conditional local memory and sparse expert routing. ProtLingo maps contextual residue representations into route-specific discrete codes, composes centered local windows into latent $N$-gram addresses, and retrieves reusable residual signals associated with recurring local sequence contexts. In parallel, selected feed-forward blocks are upcycled into sparse Mixture-of-Experts layers with shared and routed experts, enabling residue-dependent computation while activating only a subset of parameters. Experiments on protein fitness prediction, FLIP benchmarks, and supervised contact prediction show that ProtLingo achieves competitive performance with a 150M-scale backbone, including strong parameter efficiency on mutation-effect prediction and preserved long-range structural representations.

This paper studies adaptive recommendation under intent drift, where feedback from each recommendation outcome can reveal whether the relational evidence used for ranking is useful, missing, or misleading. While Knowledge Graphs (KGs) provide essential semantic structure to handle these shifts, traditional KG-enhanced systems treat the graph as a static retrieval substrate, making it brittle to evolving intents, noisy metadata, and recurring failure patterns. This paper proposes CGM-Rec, a continual graph memory framework for adaptive recommendation. CGM-Rec treats the graph state as a writable memory and maintains two complementary components. Therein, a Semantic Graph Memory is updated conservatively through quality-gated typed operations for storing stable and high-confidence relational knowledge. Meanwhile, an Episodic Lesson Memory acts as a fast reactive memory that learns recent outcomes, failure cases, and corrective hints. During testing, model parameters remain frozen and adaptation occurs only through memory writes. We evaluate CGM-Rec under a frozen-parameter, one-pass reranking protocol, where encoders and prompts remain fixed during testing and adaptation occurs only through memory writes. Experiments across multiple recommendation settings show that CGM-Rec improves over evaluated neural and LLM-based baselines on most metrics. Particularly, under sampled-candidate reranking, CGM-Rec improves HR@1 by up to 29.58% over the strongest LLM baseline on Bundle, and outperforms K-RagRec on metadata-rich ML-100K with HR@5 of 0.5941 versus 0.4746.

Long-horizon multimodal agents should remember not only what happened but also who participated. This capability depends on linking recurring faces, voices, names, person-associated objects, events, and social relations to consistent identities over time. Existing long-video and multimodal-agent benchmarks measure broad memory question answering, but they do not isolate the ability to maintain recurring person identities and reason over their cross-time relations. We introduce ICM-Bench (Identity-Centric Memory Benchmark), which, to the best of our knowledge, is the first benchmark specifically designed to evaluate identity-centric reasoning over long video memories in multimodal agents. The benchmark contains 839 synthetic clips spanning 141 minutes and 1,217 open-ended questions about six recurring adults in a one-year life album. A theme-configurable pipeline generates the video collection and associates each question with its target identities and traceable supporting evidence. We compare direct caption-memory baselines, memory-augmented agents, and graph-retrieval systems. Gemini 3.1 Pro achieves the highest overall accuracy of 74.0%, yet its score falls to 60.3% on questions that require long-term identity profiles. The results show that current systems recover many event-level memories but remain less reliable when evidence must be accumulated around a stable person.

Gaps remain in our understanding of how large language models (LLMs) acquire knowledge during pre-training. We posit that auxiliary views, reformulations of knowledge, are causally helpful for learning. We design controlled experiments to isolate this. First, we confirm that repetition is necessary for acquisition and clarify that paraphrasing helps only at smaller batch sizes. Second, holding the token budget fixed, allocating tokens from document repetition to auxiliary views improves learning, counterintuitively, even for factual recall. Third, the effectiveness of auxiliary views is not contingent on the strength of the teacher model that generates them. Fourth, we identify forms of knowledge, contextual and foundational, that aid learning in the presence of prior knowledge gaps. Finally, we examine how these effects manifest mechanistically via layer-wise biases and compression. Together, our findings suggest that auxiliary representations of knowledge, which arise naturally in large pre-training corpora, are a key factor in the success of pre-training and offer a plausible explanation for why data diversity matters.

Dense semantic segmentation allocates computational resources uniformly across the entire image, regardless of scene complexity or task relevance. Inspired by biological vision, we investigate whether semantic understanding can be achieved more efficiently through digital foveated perception. We introduce a lightweight active-vision pipeline that combines saliency-driven fixation selection, high-resolution foveal observations, low-resolution contextual information, semantic accumulation, and adaptive computation. Beyond conventional dense prediction metrics, we use object-level evaluation to measure semantic understanding under sparse observations. On ADE20K-Object, a single foveated observation achieves 95.9% of the baseline Top-1 accuracy and 96.9% of the baseline Top-3 accuracy while requiring only 4.7% of the computational cost. At the scene level, semantic accumulation recovers 90.6% of the baseline object recall while using 58.6% of the computation. These results suggest that substantial semantic understanding can emerge from sparse observations when computation is allocated selectively, highlighting active vision as an efficient alternative to uniform dense processing and motivating evaluation protocols beyond conventional pixel-wise segmentation metrics.

Question answering agents in long-term conversations must reason over massive, temporally dispersed dialogue histories. However, existing memory mechanisms primarily treat past information as \textit{passively} stored facts, leading to semantic gaps and unreliable reasoning. To address this limitation, we propose RuleMem, a rule-based memory framework that induces reusable logical rules from historical interactions to \textit{actively} guide both evidence retrieval and reasoning. Specifically, RuleMem constructs natural-language Horn clauses from conversations and validates them via a Rule Perplexity Consistency (RPC) mechanism. These induced rules enable the retrieval of semantically distant evidence while providing an explicit logical structure for answer generation. We conducted a comprehensive evaluation of RuleMem on two long-term conversational benchmarks, LoCoMo and LongMemEval_s*. In a rigorous comparison against 14 baselines on LoCoMo, RuleMem achieved the highest accuracy, exceeding the baseline average by 27.47 points (a 54.3% relative improvement).

Retrieval Augmented Generation (RAG) is a key component for generating accurate and hallucination free answers using Large Language Models (LLMs). LLMs are improving at handling long context, but still suffer from "lost in the middle" problem. Thus, precise and accurate retrieval is important. Current retrievers chunk long context into length-based manageable chunks - in the process throwing away rich and informative semantic global structure in the corpus. We introduce a novel retrieval system STAIR that empowers an LLM to exploit global structure in a corpus such as a Table of Contents (ToC) to efficiently store and retrieve information from its model parameters. Our thorough and careful ablation studies with a finetuned Differentiable Search Index (DSI) system show that ToC helps build a low hallucination (less than 0.05%) generative Information Retrieval (IR) system and can generalize to examples where very few training samples are available. To further research in this novel direction of ToC based retrieval we release SearchTome - a diverse benchmark created from 18 books across 6 diverse domains to further research in this novel direction. STAIR achieves a high Recall@1 score of 82.6% on SearchTome as compared to DSI (76.9%), where the difference is found to be statistically significant. STAIR easily beats other strong baselines such as BM25 (59.5%), DPR (68.7%) and out-of-the-box Mistral (13.8%).

World models have progressed from compact latent dynamics to generative, controllable, and interactive simulators of embodied environments. However, high predictive likelihood and visual fidelity do not necessarily ensure that a model preserves the evidence required for safe decision-making. This perspective identifies three structural mismatches in current world modeling: likelihood versus risk, prediction versus intervention, and finite-horizon prediction versus accumulated consequences. We propose the Risk-Informed World Model (RIWM) as a decision-centric research direction for safety-critical embodied systems. RIWM organizes world modeling around consequences, intervention, epistemic uncertainty, and recoverability, and integrates four interdependent capabilities: decision-relevant representation, counterfactual reasoning, safety-critical episodic memory, and runtime safety assurance. It distinguishes physical, social, and operational consequences while using epistemic uncertainty to qualify the evidence supporting action. We further discuss open challenges in identifying consequential futures, validating counterfactual reasoning, maintaining revisable safety memories, translating learned consequences into executable constraints, and determining when evidence is sufficient to act. This perspective argues that future world models should move beyond predicting likely futures toward identifying which futures matter, revising judgments through experience, and recognizing when to act, revise, sense, defer, or abstain.

Multi-agent debate (MAD) improves the reasoning capabilities of large language models by having multiple agents iteratively refine their responses through discussion. However, MAD suffers from a critical vulnerability known as shared misconception: when a majority of agents initially converge on an incorrect answer, the debate process tends to amplify rather than correct the error. Existing methods primarily address peer skew but leave the agents' inherently biased concept priors unaddressed. To mitigate this systematic weakness, we propose R$^2$-MAD (Remember and Reweight for Multi-Agent Debate), a framework that equips agents with an experience memory accumulated from past debates. R$^2$-MAD intervenes on both failure modes through two complementary mechanisms: A debate-state-aware retrieval policy dynamically calibrates the concept prior by retrieving relevant historical evidence based on the current consensus level. Then these retrieved experiences provide a basis for estimating per-agent reliability, yielding confidence weights to modulate peer influence. Experiments on various benchmarks show that R$^2$-MAD achieves consistent improvements over existing single-agent and MAD baselines.

Large language models (LLMs) are increas- ingly deployed as long-horizon conversational agents, motivating growing interest in mem- ory systems. However, existing benchmarks primarily evaluate memory through QA-style probing rather than in-situ conversational usage. We introduce LOCOMO-CONV, a conversa- tional memory benchmark derived from Lo- CoMo with four query styles: dialog, implicit, counterfactual, and composed. Across five rep- resentative memory systems, we evaluate both retrieval recall and end-to-end response qual- ity. Our experiments show that conversational framing exposes substantial retrieval gaps over- looked by QA benchmarks, especially on im- plicit and composed queries, which multi-facet query rewriting narrows for raw-turn mem- ory but not abstractive memory. We further find that strong retrieval does not fully trans- late into response quality, and that implicit queries exhibit silent grounding, where mem- ory improves contextual grounding without ex- plicitly surfacing the gold fact. These results point to reasoning-based memory elaboration as a promising direction, and we release aux- iliary supportive_memory annotations captur- ing conversationally useful context beyond the original gold evidence.

A model that inherits one-line memories may pull one archived source record before acting; a directive in the store can steer that pull: a pointer, a criterion or both. Across sixteen registered studies (179,352 attempts) we measured where the request goes under each form; every result is descriptive, with registered intervals, no mechanism claim. A length-matched criterion exceeded a bare id on six direct-provider models (D) and failed its registered superiority rule on a nine-model OpenRouter panel (E). On generated worlds (K2-K5): the two registered signatures held on Opus 5 and Fable 5.1, Fable 5 followed the same sign, Haiku 4.5 reversed, and Sonnet 5, the GPT-5.6 endpoints and GPT-6 Astra lay near zero (K2). With a defensive adapter at five gains, the 70B rule for a gain-dependent change of the composite - criterion contrast was not met (K3 and K4); under the 8B attenuation rule (0.95 intervals: slope below zero; change beyond the margin), the 8B change of -17.5 [-26.7, -8.1] did not meet it on 36 families (K4) and at registered power on 337 families -16.6 [-19.4, -13.8] did (realised one-sided error at the margin 1.8 to 3.2% per corner of a finite grid, nominal 2.5%, not a uniform-error guarantee; K4's status stands; K5, first ladder), while a second SecAlign++ adapter under the imposed Meta-SecAlign template did not (-11.8 [-14.3, -9.3]; K5, second ladder); no NOT-MET is a statement that the contrast was unchanged; their difference (+4.7 [+2.3, +7.2]) describes two fixed execution paths, licenses no superiority, equivalence or 'significant difference' claim; nothing follows from the statuses differing (K5). Intervals describe family-reweighting stability conditional on the execution, not reproducibility across engine executions; audit replays were neither substituted for nor averaged into outcomes; no missingness gate fired and directional completions changed no status.

Large language models achieve superior performance on tasks that require extended reasoning, but long chains of thought make the KV cache a severe memory bottleneck. Existing KV cache compression methods share one paradigm: score each cached token by some estimate of how much it will matter later, and keep the top-scoring ones. We show that the selection signal contributes almost nothing. Random Attention keeps the prompt and evicts uniformly at random within each attention head, computing no score at all; across four models and six reasoning tasks it matches the strongest prior evictor while serving 32-43% higher throughput than it in vLLM deployment. Controlled experiments explain this by showing that 1) the prompt is the fragile part of the cache, and most of the gap between selectors is just whether their selection signal happened to keep it; 2) the reasoning trace protects itself against eviction with redundancy at two levels, in the text (the model restates what it still needs as it works) and across attention heads (each keeps its own copy of the trace), so once the prompt is safe, a random draw retains enough copies of what the model still needs, and no score is required to pick them. Our code is publicly available at https://github.com/SalesforceAIResearch/Random-Attention.

LLM-empowered paper-code discrepancy detection has received growing concern since the scaling of research submissions exceeds the manual review capability. However, the limited context capacity and one-sided discrepancy detection of existing single-agent LLM paradigms lead to an inferior recall performance in detecting discrepancies. In this paper, we propose Dude, the first Dual-Detection Multi-Agent System for paper-code discrepancy detection. We discover that the granularity asymmetry of the paper-language and code-language introduces over-interpretation and over-reporting challenges in a multi-agent system design for discrepancy detection, resulting in increasing false positives. To address this, we propose a granularity-aligned negotiation and a two-stage salience-filtering mechanism in Dude, which effectively prevents agents from falsely reporting discrepancies. Experimental results in real-world paper-code discrepancy datasets showcase Dude's significant recall and precision improvement by up to 22.8%, increasing F1 score by up to 18.7% compared to baseline methods.

Distributed LLM-agent teams can read the latest shared facts and still act on an obsolete plan. A planner may derive an action from requirement $r_3$, another agent may commit $r_4$, and an executor may receive $r_4$ without replacing the plan derived from $r_3$. We call this \emph{stale-plan execution}: state freshness does not establish that the plan authorizing an action remains valid. We introduce PlanFence, a dependency-scoped action-validation protocol. Plans cite the exact public records they used, and an executor validates only the records that can affect the pending external action, replanning once or blocking when validation is incomplete. In 30 controlled live workflows with a post-plan revision, a freshness-only executor acts on the obsolete plan in every task, whereas PlanFence completes all tasks without an invalid action. Controlled replay reveals two conditional boundaries: proactive synchronization yields lower coordination stall at low churn, while PlanFence avoids repeated update-path coordination as churn grows and avoids validating unrelated state as the shared keyspace grows. These are controlled safety and systems-cost results, not general task-accuracy gains.

Tamil spell and grammar correction is challenging because Tamil is an agglutinative low-resource language with rich verbal morphology, complex sandhi (phonetic transformation) rules at word boundaries, and a script of 247 distinct letters. Prior work targets word-level surface errors with rule-based methods, statistical n-gram models, Minimum Edit Distance, or hybrid pipelines with a transformer re-ranker; such methods cannot reliably handle contextual errors - subject-verb agreement, tense consistency, or cross-word sandhi - which require sentence-level understanding. We propose an end-to-end sequence-to-sequence formulation and fine-tune mT5-small and mBART-50 on a synthetic corpus of up to 657,720 noisy-clean Tamil sentence pairs spanning ten error categories. Both backbones follow the same four-stage progressive schedule, each stage targeting one weakness: surface noise (v2), contextual grammar (v3), single-site sandhi (v4), and multi-site cross-word sandhi (v5). On a 1,000-sentence balanced diagnostic set verified disjoint from all training data, our best model, mBART-50 v5, reaches 69.3% top-1 exact-match accuracy, with 87.5% on sandhi and 43.5% on subject-verb agreement. The schedule is what produces these gains: subject-verb accuracy rises from 1.0% to 52.5% once contextual pairs are introduced, and sandhi from 0% to 87.5% once multi-site sandhi pairs are. We additionally quantify a precision-recall trade-off this literature has not reported: sandhi recall is paid for monotonically in identity accuracy. Finally, Tamil-LLaMA-7B-Instruct reaches 19.0% zero-shot and 24.7% with three demonstrations against a 20.0% copy baseline, showing that a Tamil-adapted instruction model does not transfer to specialised sentence-level correction without task-specific supervision.

Long-term LLM agents must preserve information across interactions while distinguishing repeated evidence, historical states, updates, and unresolved contradictions. Existing textual memory systems retrieve semantically relevant memories efficiently but often leave these relationships implicit, whereas richer structured approaches model them through global graphs, hierarchical abstractions, or reflection at greater complexity. We introduce MemoryLACE (MemLACE), a lightweight memory framework that explicitly models the lifecycle of textual evidence through sparse merge, supersession, and contradiction relations while preserving atomic natural-language memories and their provenance. Rather than retrieving memories independently, MemLACE reconstructs relation-aware evidence units that expose current, historical, supporting, and conflicting evidence for downstream reasoning. Across BEAM and StructMemEval, using open-weight and proprietary LLM backbones, MemLACE achieves the highest overall performance in same-backbone comparisons while reducing end-to-end runtime on BEAM by 66.6% relative to Hindsight, the strongest reported reflective-memory baseline. Ablation studies identify lifecycle expansion and temporal awareness as the principal contributors to these gains. Together, the results demonstrate that explicitly modeling the local lifecycle of textual evidence is sufficient to substantially improve long-term memory reasoning without requiring comprehensive knowledge graphs or global reflection.

Long-context reasoning for large language models (LLMs) is becoming increasingly important, but training over long sequences remains challenging due to massive memory and communication requirements. Sequence parallelism has emerged as an essential technique for addressing bottlenecks in long sequence LLM training. However, we observe that existing sequence parallelism methods are batch-agnostic and apply uniform sequence partitioning across all batch sizes, resulting in inefficient communication. In this paper, we introduce Batch- Aware Sequence Parallelism (BASP), a sequence parallelism approach that leverages batch structure to reduce communication overhead. BASP exploits batch structure by partitioning GPUs into disjoint sequence-parallel groups according to the micro- batch size. This design reduces the all-to-all communication group size, thereby localizing communication and improving training efficiency. Experimental results on an NVIDIA A100 cluster show that BASP improves end-to-end training time by up to 1.17 - 1.31x in Llama and Qwen models compared to standard sequence parallel baselines, while preserving identical model accuracy and memory usage.

Planning is a central capability that enables agents to decompose complex long-horizon tasks into manageable steps. Test-time search and training-based methods improve planning but incur high inference costs or require expensive training data. Self-evolving memory instead accumulates reusable experience from agent interaction outcomes into an external memory bank, so planning capability keeps improving at inference time without parameter updates. However, existing self-evolving memory methods share an inherent credit assignment problem: they rely on final task outcomes as feedback, but such outcomes conflate plan quality with execution errors and environmental factors, so the accumulated planning experience is often biased and noisy. To address this problem, we propose Credit-Aware Hierarchical Memory Evolution (CHIME), a self-evolving memory framework that maintains a separate planning bank and execution bank and follows an attribute-before-memorize principle: CHIME first attributes each task outcome to the plan, the execution, both, or neither, and then updates only the corresponding memory bank. Extensive experiments on four long-horizon agent benchmarks show that CHIME consistently outperforms state-of-the-art training-based and self-evolving memory baselines. Further analyses reveal several interesting findings. For example, CHIME accumulates effective memory with far fewer items. In addition, the learned memory values faithfully reflect downstream utility: high-quality planning memories are more valuable than execution memories. Finally, the accumulated memory effectively transfers across backbone models. Code will be released at https://github.com/ATH-MaaS/Marco-DeepResearch.

Guideline-consistent semantic segmentation requires more than category recognition, as real-world labeling policies demand fine-grained, task-specific decisions. Recent multi-agent refinement systems improve compliance with such textual guidelines by detecting and correcting errors. However, they are stateless: feedback from the critiquing agent is discarded, causing the same guideline-specific mistakes to be repeatedly rediscovered and corrected across the dataset at the cost of additional refinement. We introduce InsightSeg, an episodic memory mechanism that converts successful correction episodes into reusable, visually grounded insights. A meta-analyzer distills each qualifying episode into directive natural-language insights and anchors them to the local image regions that caused the error using patch-level visual concept vectors. On subsequent images, these concepts are matched against dense patch embeddings to retrieve relevant insights, which condition the segmenting agent before making its first prediction. This shifts the system from correcting recurring errors to preventing them, improving segmentation quality before any refinement occurs. Across Waymo and Cityscapes, InsightSeg improves both first-pass and final guideline-consistent segmentation performance while requiring fewer refinement steps, demonstrating that multi-agent refinement can become more accurate and efficient by drawing on past correction experience.

Enterprise wireless access points (APs) are promising platforms for predictive machine learning (ML), but their primary responsibility remains providing wireless connectivity and network services. Predictive inference must therefore share an AP's CPU and memory with packet processing, Wi-Fi and IoT radio operations, and client management. This resource contention creates two risks: a model that performs well on proxy hardware may be too slow on the target AP, while a model that fits in isolation may still degrade network services under load. We define \textit{network-aware deployability} using two gates: qualification of the model and its execution path on the target AP, followed by validation of its execution profile under packet-service and forecasting constraints. Our benchmarks show that edge testbeds do not reliably capture target behavior. Across matched artifacts and serving settings, five model implementations run 6.1--19.1$\times$ slower on an AP than on a Raspberry Pi5, while peak memory usage differs by up to 22%. Moreover, two forecasting foundation models of similar size differ in AP latency by 19$\times$. When serving a smaller model across 13 parallel streams at a 30s cadence under network saturation, default execution increases p99 round-trip time (RTT) by 76% and reduces throughput by 7.06%. Understanding these trade-offs is essential for live deployment if we aim to use APs for both networking and ML workloads.

Reliable attractor recall conventionally requires broad basins of attraction. However, in reservoir-computing based associative memory, temporal cues reliably recover dynamical memories despite basins dominated by unpredictable, riddled-like regions. We reveal that memory basins exhibit an octopus-like'' structure: a robust head'' near the attractor and thin, intertwined ``tentacles'' spanning state space. Initial states in tentacular regions yield near-zero uncertainty exponents, making the recalled memory effectively unpredictable at finite precision. Yet, cue-driven generalized synchronization bypasses this unpredictability, driving the system into the robust basin head. This mechanism yields a quantitative relation linking minimum cue duration, synchronization rate, and basin-head radius. Trained recurrent neural networks exhibit similar geometry, suggesting this phenomenon extends beyond reservoir computing.

Persistent memory supports personalized agents, but a stale stored fact can override current authoritative evidence without warning. We study when this harm begins as model capability changes. We evaluate a frozen, closed-set, action-scored benchmark with 2 suites that represent 2 different meanings of "no memory" (a Benefit suite, unsolvable without the stored fact, and a Safety suite, in which an authoritative tool always holds the correct value), on a same-family model-size series (Qwen3 0.6/1.7/4/8B). The Memory Trust Gap reflects over-trust rather than confusion. In the Benefit suite, models answer with the stale value 0.92-1.00 of the time at every scale. In the Safety suite, harm below the no-memory baseline under the trap conditions ($Δ_{\mathrm{mem}}$) is capability-gated, with the larger models collapsing most once a stale note is made to look current. In a $2\times2\times2\times2$ factorial, which feature triggers over-trust depends on both the feature and model scale. Removing a label amplifies over-trust at every size, and a recency feature (stale dated newer) fools the larger models harder. Source authority is weak and scale-flat, and position changes from positive to negative across the Qwen3 model-size series. We confirm these scale interactions with direct cross-size contrast tests rather than overlapping per-model intervals. Mitigation is likewise capability-dependent: exposing metadata improves accuracy for the capable models, but only pre-resolving the conflict restores accuracy for the 2 smaller checkpoints. The same pattern appears on the capable models in an independent Llama-Instruct model-size series and on 2 external datasets (RGB, MisBench). A framing control finds no consistent advantage for the memory label: at the 3 smaller scales, models trust a stale document more than a stale memory; at 8B, the difference is not significant.

Long-running LLM agents rely on persistent memory to carry state across interactions, including permissions, restrictions, and revocations. When memory misrepresents this evolving authorization state, the agent's own records can grant authority that the underlying history never permitted, resulting in misaligned behavior without any external attacks. We term this failure endogenous authorization laundering, where spurious permissions written into memory lead to unauthorized actions as their provenance is washed away. We then introduce EAL-Bench, which measures how accurately persistent memory preserves evolving authorization state and whether errors propagate to downstream unauthorized actions. We evaluate five LLMs as memory writers and two as executors across procurement, cybersecurity, and finance. We find that under incremental memory updates, writers create false authority for up to 50.2% of unauthorized requests; once false authority is present, executors act on it in 98.6% of trials. Two safeguards, requiring stored permissions to be backed by valid source events, and tracking permission changes through bounded event sourcing, substantially reduce laundering, but both also reject more legitimate actions, exposing a safety-utility tradeoff. Persistent memory is therefore not merely a performance component, but a part of an LLM agent's effective authorization policy.

As enterprise platforms transition to conversational reasoning interfaces, the stateless nature of LLM APIs creates an architectural gap. While statelessness enables horizontal scalability for AI providers, it forces client applications to manage the entire burden of conversational state and semantic memory. The work identifies the Hydration Proxy Pattern, an architecture that decouples session persistence from the reasoning engine. The framework ensures platform sovereignty over conversational data while enabling secure, multi-stage semantic grounding. We further propose the Context Stabilization Mandate to resolve the tradeoff between sovereign state management and KV caching.

The browser has become a first-class database host: applications increasingly want to store, query, and reason over structured data entirely on the client - for privacy, offline operation, local-first collaboration, and, most recently, as durable memory for in-browser AI agents. One way to get SQL in the browser, compiling PostgreSQL to WebAssembly (PGlite), inherits PostgreSQL's process model: a single backend connection that executes one statement at a time and blocks. That model cannot express concurrent transactions, and it leaves richer capabilities - graph queries, database branching - to whatever the compiled server happens to include. We present zeta-lite, the browser form factor of the Zeta database engine: a WebAssembly build that compiles the same Zeta server down to a 2.87 MB gzipped artifact. Zeta-lite keeps the engine's log-centric asynchronous MVCC core, which yields two capabilities no other in-browser SQL engine provides. First, overlapping snapshot-isolated transactions on a single thread: multiple transactions hold distinct read/commit timestamps and interleave, with snapshot-isolation conflict detection between them. Second, copy-on-write database branching - whole-database fork, merge, and rebase - is unique in a browser SQL database and rare even in servers. On top of these, zeta-lite exposes a feature-complete PostgreSQL surface (joins, CTEs, window functions, JSONB with GIN indexes, full-text search, HNSW vector search, SQL/PGQ graph queries, multi-database) and snapshot-to-OPFS durability. Across Chrome, Firefox, and a native reference runtime, zeta-lite sustains 268k-315k point reads/s and holds a mixed read/write workload flat over millions of operations. This small, fully-featured, concurrent SQL database is an especially good fit for agentic memory - where cheap branchable state lets an agent explore, inspect, and commit or discard speculative work.

Logit-based knowledge distillation (KD) is used to train smaller language models (LMs) via supervision from stronger teachers, but whether its benefits are consistent across training stages remains unclear. Through controlled experiments, we find that forward Kullback-Leibler (KL) distillation--the standard KD formulation--with post-trained teachers behaves fundamentally differently during mid-training, an intermediate phase of self-supervised learning on curated corpora. Surprisingly, while forward KD simultaneously improves reasoning and factual recall during pre-training relative to standard next-token prediction (NTP), it instead slows factual recall acquisition during mid-training despite continued reasoning gains. We trace this stage dependence to an asymmetry in teacher confidence across data domains and the student's evolving knowledge state: teachers are more confident on procedural than knowledge-intensive data, while students acquire low-entropy factual knowledge earlier in training. To mitigate this imbalance, we propose Switch Distillation, a simple mid-training objective that distills on tokens where the teacher is confident, using teacher predictive entropy as a lightweight routing signal, and otherwise falls back to cross-entropy. Switch Distillation consistently outperforms existing distillation objectives across teacher sizes. Relative to standard NTP, it achieves 1.61-1.71x the reasoning performance and 1.13-1.19x the knowledge and commonsense performance while preserving 96.7-96.8% of factual recall. Crucially, these benefits persist after post-training: Switch Distillation closes the factual recall gap while maintaining 1.25-1.32x and 1.13-1.20x gains in reasoning and knowledge and commonsense, respectively.

On-device mobile Large Language Model (LLM) inference is gaining significant attention. However, mobile devices operate in highly dynamic multitasking environments where users frequently switch between applications. This creates memory pressure, forcing LLM memory (model weights and KV cache) to be evicted by the operating system. When a new inference request arrives, the inference system must restore the evicted memory through slow storage reads or recompute the entire KV cache, severely degrading responsiveness. To address this, we present mzCache, an on-device LLM inference system with specialized memory management for multitasking environments. Under unpredictable memory pressure, mzCache elastically evicts LLM memory and leverages the unified memory of mobile SoCs to enable zero-wait inference on the GPU with concurrent CPU-side restoration. mzCache realizes this through restoration-oriented memory management: LLM memory is partitioned into fine-grained shared buffers to enable partial eviction and restoration with concurrent cross-processor access, while hybrid swap and backward-out eviction policies ensure low-latency restoration from any eviction state. Implemented on llama.cpp and deployed as an Android application, mzCache achieves 2.1-5.5$\times$ reduction in Time-to-First-Token compared to storage-backed partial offload and demonstrates its effectiveness in real multitasking scenarios.

MutMem V1 introduced retention-preserving, cryptographically authorized mutation for persistent agent memory but did not provide a complete portable verification contract or clean-install reproduction path. MutMem V2 closes that publication gap without introducing a second memory engine. It specifies exact canonical bytes, domain-separated object and bundle commitments, mandatory recall-evidence membership and ordering, external trust anchors, identity epochs, revocation, authorization, request receipts, ordered disclosure, and three mutation terminal types. The released protocol contains 18 versioned object schemas, 39 recall vectors, 15 mutation vectors, and 37 closed recall failure reasons. Independent Node and Python implementations agree on verdict and primary reason for all 72 structural and cryptographic terminals; a production-conformance corpus agrees on 42/42 cases across 28 required classes. A clean Node v26.8.1 installation reaches first-boot, restart, and scheduler readiness with no experimental memories. A separately scoped 120-unit Canary experiment supports only explicit-marker traversal. Every public table regenerates from a self-hashed aggregate, and an independent verifier reconstructs the statistics and claim boundaries. Historical V1 empirical results remain historical. MutMem V2 supports claims about portable integrity, authorization, traceability, conformance, and reproducibility under stated assumptions; it does not establish semantic truth, universal robustness, or independent replication.

Multimodal memory offers a scalable interface for long-video question answering, but existing methods often retrieve captions, frames, transcripts, summaries, or graph facts as isolated fragments. Although searchable, such fragments are not generation-ready: language models must reconstruct cross-modal and temporal alignments at inference time, when context is limited and attribution is difficult. We propose EM^2Mem, an event-centric multimodal memory framework that binds heterogeneous evidence to event anchors during memory construction. Each event-indexed memory cell aligns multimodal records, temporal context, graph-linked relations, semantic facts, and provenance, enabling compact evidence readout over grounded multimodal events rather than modality-specific fragments. Across three long-video QA benchmarks, EM^2Mem improves average accuracy over the strongest memory baseline by 2.0, 2.4, and 3.7 points, improves strict event-level Top-5 evidence recall by 7.0 points, and reduces per-query latency by 4.67 times and total inference tokens by 63.66% (The code will be integrated into https://github.com/zjunlp/LightMem).

Agent systems are commonly described by the model and harness that currently produce their behavior. That boundary is useful for one execution but underspecifies a long-lived agent that may change models, orchestration harnesses, interaction sessions, and host servers while retaining one identity, memory, and executable code lineage. We present a runtime-independent architecture for persistent agents. A continuity-bearing substrate $P_t=(I_t,M_t,B_t)$ contains an architectural identity representation, private durable memory, and a versioned software body. A replaceable deployment binding comprises an execution substrate $E_t=(R_t,H_t,D_t)$, which supplies a reasoner, harness, and host, and a set of interaction surfaces $S_t$, such as chat, API, or user interface bindings. A deployed execution is $A_t=P_t\triangleright(E_t,S_t)$; changing either replaceable layer is migration, not agent creation, when an authorized protocol preserves attributable lineage and transfers continuation authority within a governed deployment boundary. We define six continuity invariants and a quiesce--checkpoint--validate--bind--rehydrate--resume protocol. Enoch realizes the design as a reusable body plus private installed identity, memory, workflow state, and continuation authority, with infrastructure dependencies behind versioned provider contracts. A clean-room run of the frozen public commit passes 833 core tests and 92 provider and library tests executed separately from the core suite; deployments have exercised reasoner-version, interaction-surface, and host-machine substitutions while retaining continuity-bearing state. This evidence supports mechanical substitutability and authorized system continuity, not behavioral invariance or exhaustive pairwise evaluation. The downstream measurement question is whether an authorized continuation still recalls, composes, and enacts its identity.

Promptable segmentation foundation models such as SAM3 accept an open-vocabulary text concept and return every instance matching it, but adapting them to a specialized domain by full fine-tuning is computationally prohibitive for the organizations that would benefit most. This study applies Low-Rank Adaptation (LoRA) to SAM3 for multi-class structural defect segmentation and examines both how such a model can be supervised from conventional annotation and whether the resulting efficiency gain transfers across datasets. Two contributions are methodological. First, we describe a supervision procedure that trains a concept-promptable model directly from COCO-style class-labeled instance segmentation by using the category name itself as the prompt, requiring no prompt templates, no synonym expansion, and no learned class embeddings. Second, we identify and mitigate a failure mode specific to this setting: because a conventional annotation file yields positive prompts exclusively, the model's presence prediction decouples from the text condition and degenerates into responding to any prompt, a collapse that is invisible to every metric computed on positive prompts alone. Exhaustive hard-negative prompting, in which every dataset category absent from an image is issued as a zero-detection query, addresses this at no annotation cost. Two adapter placements were compared under an identical protocol, updating 0.121% and 1.341% of model parameters. On a purpose-built tunnel lining dataset, pixel intersection-over-union improved from 0.017 to 0.338 and instance-level recall from 0.375 to 0.672; on the independent public Structural Defects Dataset, from 0.017 to 0.855 and from 0.574 to 1.000. Improvements were directionally consistent across ten metrics on both datasets, and the largest per-category gains occurred precisely where zero-shot competence was absent.

Vision Transformers provide strong visual representations but typically rely on slowly updated parameters, limiting their ability to organize newly acquired information across different memory timescales. This work proposes \textit{Hierarchical Hebbian Memory}, a three-level memory architecture composed of rapid Working Memory, persistent Routed Episodic Memory, and slower Semantic Memory. A learned controller regulates memory contribution, read and write routing, plasticity, retention, and consolidation. A causal read-before-write lifecycle ensures that the current outcome cannot influence the prediction it supervises. The architecture is evaluated on Omniglot 5-way 1-shot recognition and CORe50 continual object recognition. With Swin-Tiny, the hierarchical model reaches 97.39% accuracy on Omniglot and 95.37% final accuracy on CORe50 when combined with experience replay. Learned multi-bank retrieval reaches 47.50% delayed-association accuracy, compared with 24.17% for a single persistent bank and 25.00% without memory. After intervening distractors, Episodic Memory retains approximately 0.96 cosine similarity with stored associations, while Working Memory falls to approximately 0.05. These results show that Hebbian association and learned memory routing can jointly organize online visual experience across rapid, persistent, and consolidated memory timescales within Vision Transformers.

We investigate how vision-language models (VLMs) handle context-memory conflicts; that is, situations in which the model is given information in context that differs from what was stored parametrically during training. We document asymmetric biases: models tend to prefer in-context information about entities which appear in text, but prefer parametric information about entities which appear in images. We relate this asymmetry to the late representational alignment across modalities, showing that the longer processing time associated with resolving visual entities prevents the suppression of the model's usual factual recall mechanism, thus resulting in more parametric answers. Chain-of-thought reasoning does not appear to resolve the gap, but increasing the amount of visual information in the context does show an effect. These results illustrate the complexity of ensuring consistent behavior as models become increasingly multimodal and retrieval-augmented.

Agent working memory is heterogeneous. Objects such as instructions, artifacts, tool outputs, and agent-generated state play different semantic roles and exhibit different size, retention, and representation profiles. Recent work has begun to explore memory-management mechanisms that account for such heterogeneity. This work focuses on semantic heterogeneity and studies how it should shape the management and evaluation of working memory in coding agents. Across 55 archived coding-agent trajectories, we find that semantically different working-memory objects exhibit distinct retention and compression behavior. This heterogeneity motivates semantically informed memory management. We study two semantically informed strategies: an object-aware compression policy and a retrieval-based policy. Their evaluation shows that calibration gains may not transfer to held-out tasks, and that equal token budgets do not imply equal delivered context or management cost. A real-system replay further exposes serving limits that nominal budgets alone do not capture. Together, these results show why semantic structure matters for agent working memory and why evaluating memory-management strategies requires more than a nominal token budget. We organize these lessons into four levels: stored state, delivered context, management work, and task or process outcome.

Stream learning is commonly evaluated through predictive performance and adaptation to concept drift. However, sustained operation of a stream learner also requires predictable and bounded resource usage even on long streams. This requirement becomes even more critical when learning moves from servers to near-sensor embedded systems where memory and processing are scarce resources. In state-of-the-art stream learning, however, we perceive a strong focus on concept drift adaptation, whereas resource usage is often an evaluation byproduct. To close this gap, we benchmark seven representative stream classifiers on 13 real and synthetic streams under model-size budgets from 128,KiB to approximately 8,MiB. Our benchmark comprises a total of 6,463 experiments. We measure failure-aware accuracy, peak model size, time to budget exhaustion, and prediction-plus-update latency. The results reveal two distinct resource failure modes. Adaptive ensembles can exceed small budgets almost immediately because of their initial footprint, even when their size remains stable thereafter. Incremental trees can fit initially but grow throughout a long stream, with HoeffdingTrees (HT) and Extremely Fast Decision Trees (EFDT) increasing by median factors of 7.37 and 5.87. Explicitly compact methods remain the only viable option under the smallest budgets, but are usually overtaken as larger budgets make adaptive ensembles competitive. Hence, many state-of-the-art methods are only partially applicable in embedded systems or for long-running systems. We therefore call on the stream-learning community to make bounded resource usage a first-class design objective alongside drift adaptation, and propose concrete steps toward this goal, including an API through which stream learners can explicitly expose and respect resource budgets.

Language models can answer from precomputed memory, a model's saved reading of a body of material, reused across requests instead of read again at each. This paper maps where that practice preserves correctness and the conditions under which it fails. Across experiments on Llama-3.1-8B-Instruct using both saved key-value caches and trained compressions of them, precomputed memory degrades when assembled from separately prepared parts, stays current only through rebuilds costing a large fraction of full preparation in our measurements, and ignores corrections served beside it conditional on phrasing. If precomputed memories can be served alongside one another, be cost-efficiently rebuilt, and be superseded by new information arriving in real-time, they can serve as a way to avoid re-feeding context to a model over repeated queries. The implication of our results for a deployed system that deals with a variety of queries is that precomputed memories are best rebuilt on the cadence at which new information changes what the memory was originally computed from. Both warm-rebuilding trained compressions of key-value caches and serving specifically-phrased updates beside a memory, as pasted text or injected cache state, show particular promise for keeping precomputed memories current, the latter as an interim measure between rebuilds, and we measure the cost and name the remaining questions associated with each.

Multimodal Emotion Recognition (MER) systems often suffer from missing modalities in real-world scenarios. Existing methods usually generate, align, or distill missing modalities as a whole, overlooking the heterogeneous nature of the information carried by each modality. Such holistic treatment mixes inferable shared semantics with uncertain modality-specific details, yielding unstable representations and degrading robustness. To address this issue, we propose the Primitive Memory Distillation (PriMD) framework. Unlike existing methods, PriMD takes an intra-modal perspective and focuses on how different types of information within a modality differ in recoverability within each modality. PriMD first disentangles cross-modal shared semantics from modality-specific representations, and then discretizes the latter into learnable semantic primitives to construct modality-specific memory banks. When modalities are missing, PriMD is a teacher-student framework that the student model uses the shared semantics of available modalities as queries to dynamically retrieve primitives. It compensates for missing modality-specific information within a constrained memory space and aligns with the teacher model. Extensive experiments on IEMOCAP, CMU-MOSI, and CMU-MOSEI demonstrate that PriMD achieves state-of-the-art performance and consistently stronger robustness across a wide range of missing-modality settings, while mitigating the instability caused by holistic feature inference. Our code and project website are available at https://github.com/JiaqiZhang-Sengoku/PriMD and https://jiaqizhang-sengoku.github.io/PriMD/, respectively.

Long-term memory is increasingly important for conversational agents, yet existing benchmarks primarily measure memory through pointwise factual recall: whether a system can recover isolated facts or event-level details from prior interactions. Real-world memory use, however, often requires a more demanding capability: integrating distributed, implicit, and noisy evidence across extended interaction histories into coherent, task-oriented outputs. We call this capability memory utilization. Here, we introduce UtilMem, a diagnostic benchmark comprising 1,717 instances across five domains, designed to evaluate four underexplored aspects of memory utilization: reasoning over dense histories, identifying implicitly relevant memories, synthesizing distributed evidence into summaries, analyses, or plans, and resisting interference from semantically similar distractors. Evaluating a diverse set of retrieval-based and memory-augmented systems, we find that strong performance on conventional factual-memory benchmarks does not reliably translate into effective memory utilization. Moreover, retrieval alone is insufficient: even when relevant evidence is successfully recovered, systems frequently fail to integrate information across sessions or to distinguish useful evidence from plausible distractors. These findings expose a substantial gap between accessing stored information and using it effectively, and suggest that progress in long-term conversational memory will require architectures that explicitly support evidence integration and robustness to retrieval interference. Code is available at https://github.com/peijunallin/UtilMem.

Cognitive language agents have achieved substantial progress by equipping language models with memory, tools, and decision-making procedures, enabling agents to reason and act in interactive environments. Existing frameworks largely cast these agents as systems for solving user-specified, bounded tasks. An increasingly important goal is for language agents to provide persistent assistance in long-lived settings where user needs, context, and service procedures persist and change, and to remain useful across the broad range of tasks that arise over time. Yet we still lack a framework to characterize persistent AI agents, organize existing work, and guide future development. To this end, we propose a Perception-Centered Architecture for Persistent Agents (Pera). Pera describes a persistent agent organized around perception and control components that continually perceive service-relevant signals from episodic task executions, internal context, and changes in the surrounding environment, and use these signals to construct lifecycle tasks. These tasks drive the ongoing operation and adaptation of the agent's service procedures. We use Pera to retrospectively organize recent work, examine a detailed case study, and offer forward-looking insights for building more capable persistent agents. Just as software engineering moved from programming in the small to programming in the large, Pera frames the evolution of language agents as an analogous architectural transition toward long-lived, adaptive intelligence systems.