Meriem Yacoubi, Pia Schmidt, Nenad Petrovic +3cs.CL cs.LG
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-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.
Large language model (LLM) agents need durable, faithful memory of everything a user or organization has said and stored, yet most memory systems commit to a single organizing structure (a fact store, a vector index, or a knowledge graph) and inherit its blind spots. We present Agent Zero Memory, a provenance-aware long-term memory system that distils a user's conversations, files, and connected sources into three parallel memory systems, each capturing a different facet of the same history: an episodic Memory Events timeline that makes when and what changed first-class, an associative entity-event knowledge graph that links people and projects across sessions, and a semantic, curated, citation-locked Hierarchical Documentary Memory (HDM) of durable facts. A retrieval turn runs an intent gate (so self-contained turns add no latency), a source router, and three concurrent agentic searches, one per system, each a tool-using loop over hybrid (embedding + lexical) search under agent-controlled filters; their grounded, cited answers are integrated into one answer with a single confidence. We formalize the reading discipline: every learned item is a provenanced item carrying its origin, timestamp, and evidence pointer, and every answer is read under a citation lock, so it may cite only evidence its reader actually opened; fabrication is structurally excluded and the system abstains rather than guesses. On two public benchmarks the system sets a new state of the art: 95.60% on LongMemEval and 93.60% on LoCoMo, improving over the strongest prior systems by +0.73 and +1.10 points. A controlled study across eight backbone LLMs characterizes the accuracy-cost-latency frontier: accuracy varies by only 3.4 points while per-query cost varies by ~30x, with near-state-of-the-art quality at up to 20x lower cost per query, the signature of memory-driven, rather than model-driven, quality.
Knowledge graphs have been proposed as a structured alternative to flat retrieval-augmented generation for long-term agent memory, on the assumption that representing conversations as entities and relations improves recall. We evaluate that assumption directly. Our framework extracts each conversational turn into typed nodes and attributed edges, answers questions from a two-hop subgraph, and periodically prunes nodes that score low on a weighted combination of recency, access frequency, degree centrality, and age. On LongMemEval, the graph does not outperform a flat vector baseline at a matched candidate-generation budget of five retrieval roots: token F1 is $0.417$ against $0.468$, and a paired bootstrap over 500 questions gives $Δ= -0.050$ (95\% CI $[-0.085, -0.016]$). The gap is widest on questions that require recalling a specific prior assistant turn, where judged correctness falls from $0.911$ to $0.607$, suggesting that decomposing a turn into entities discards the surface form these questions depend on. The forgetting module is more successful. Applied once to a persistent 27{,}021-node graph, it removes 9.8\% of nodes and 9.5\% of stored bytes; token F1 is unchanged ($+0.001$, 95\% CI $[-0.015, +0.016]$) and judged correctness falls by $1.6$ points, with the 95\% interval bounding any loss at $3.8$ points ($[-0.038, +0.006]$). Because our extractor is a single small model evaluated on one benchmark, these results characterise this extraction-based pipeline rather than graph-structured memory in general. Code: https://github.com/skhanzad/Selective-Amnesia
Organizing long-term memory for multimodal agents remains challenging because existing methods either suffer from expensive question-agnostic offline summaries or naive embedding similarity matching that introduces incomplete and redundant context. To address these issues, we propose GraphMemix, a combinatorial-optimization graph memory framework that models memory organization as query-aware evidence-forest construction. Specifically, our method consists of three key components:(1) candidate graph construction, which expands multi-view seed memories through schema and semantic relations to acquire query-aware original context; (2) evidence utility and activation costs, which decouples direct memory support from anchor-conditioned relation verification to suppress redundant or conflicting information; and (3) forest optimization, which jointly selects a forest-format memory context under a maximum evidence budget and its reliable relational structure. By organizing memory into a query-relevant subgraph, the method avoids substantial lifecycle cost and recovers low-similarity complementary evidence. Experimental results across four long-term multimodal memory benchmarks demonstrate significant improvements with different foundation models and establish a new Pareto frontier between accuracy and lifecycle cost.
Scaling video generation to long durations reveals a critical bottleneck: current models lack robust long-term memory. This deficiency can be studied along two critical aspects: object permanence, the ability to precisely reproduce the appearance of objects upon re-entry; and memory capacity, the ability to process ultra-long context and use information from distant history. Robust long-term memory requires both: object permanence without sufficient context handling limits the temporal scope, while long context length without permanence fails to maintain identity. To address this, we present Ring Forcing, an autoregressive video diffusion framework designed to robustly construct and precisely utilize long-term memory. Our ring-structured training strategy enforces retrieval from distant history, effectively reconciling the trade-off between strict historical adherence and generative diversity. To expand memory capacity, we introduce a compression and timestep composition strategy. Under fixed sequence length constraints, this method extends the effective historical span to minutes-long durations and achieves a comprehensive receptive field over the entire history. Furthermore, we present a sparse RoPE mechanism to enable flexible, scalable memory adaptation while fully exploiting pre-trained priors. Extensive experiments demonstrate that Ring Forcing achieves superior minutes-long coherence and object permanence, significantly outperforming state-of-the-art methods.
We measure tablet-2, a production long-term memory engine for language models, on the text benchmarks the field already uses and on cross-lingual retrieval of photographs stored with no text at all. Its retrieval path contains no lexical matching, no keyword scoring, and no language model of its own. On LongMemEval-S (500 questions) it scores 95.7% [93.4, 97.1]; on BEAM-1M (700 questions, 2.21M stored memories) 67.5% [64.8, 70.2]. Those are question-sampling intervals, not the run-to-run spread, which is an order of magnitude narrower. Most of the paper is about how little they mean alone. Holding engine, corpus, settings and judge fixed, changing only the reader moves LongMemEval-S by 2.0 points; changing only the re-ask budget moves BEAM-1M by 8.9. Neither is stated in the reports we compare against, and the second exceeds most gaps there, so we give that table as a placement and not a ranking. For the multimodal axis we run two controls. Against BM25, configured as strongly as we could, we reach 95.2% mean recall@5 over 70 store-and-query language cells where BM25 reaches 19.0% and is exactly zero in 54. On captionless photographs a lexical method has no document to score at all. Open dense baselines on 300 Crossmodal-3600 photographs in 14 languages show that density confers no language independence: one scores 91.0% on English and 4.7% on Russian from identical image vectors, and a multilingual variant collapses on Telugu and Swahili. Our spread across languages is 14.0 against their 27.5 and 27.7. Three results run against us and are reported at equal weight: low-resource languages degrade sharply (Swahili 53.0%, Telugu 64.0%), attaching captions lowers cross-lingual retrieval by 11.4 points, and one setting omitted into one stage of our own retrieval cost 37 points of Korean top-1 accuracy while leaving nine languages untouched.
Long-term memory is crucial for personalized responses and long-horizon agent interactions. Existing methods often rely on LLMs to compress or rewrite dialogue histories and use the transformed memories as retrieval evidence. Despite the progress in organizing fragmented contexts, two major drawbacks persist: (1) information loss from compression, which discards fine-grained but later useful details, and (2) semantic drift from rewriting, which erodes the original tone and situated context. In this work, we propose a novel Human-profile Enhanced Retrieval Optimization framework for long-term agent memory (HERO). Specifically, HERO converts the dialogue history into a traceable heterogeneous memory graph that preserves raw dialogue text as evidence for reasoning, thereby mitigating information loss. For retrieval, HERO extracts initial anchors from the current query and incorporates human profiles via an iterative graph traversal; these anchors and profiles provide guidance signals that adaptively activate the most informative regions of the graph. Experiments on two benchmark datasets show that HERO outperforms strong baselines on both factual and personalized reasoning, while providing more faithful access to raw dialogue evidence.
Large language models increasingly serve as persistent conversational assistants, requiring memory that preserves relevant experience and maintains continuity across interactions. Existing methods improve access to conversational history through long-context processing, selective retrieval, and structured memory organization. However, most systems treat memory access as retrieving relevant past information without first determining which prior interaction state the current turn resumes. This limitation becomes particularly important when conversations interleave multiple tasks, people, and plans that may be interrupted and later revisited. We introduce ArborMem, an online memory framework that represents a long-running conversation as a navigable forest of interaction states. Each branch preserves a locally coherent trajectory, while the forest maintains multiple trajectories that may later be resumed. For each new input, ArborMem localizes the relevant state, restores its branch-local context, and augments it with reusable evidence retrieved across branches, preserving interaction continuity without conflating semantically related but structurally distinct trajectories. Existing long-term memory benchmarks cover diverse memory and reasoning capabilities but do not explicitly isolate branch-structured challenges. We therefore introduce BranchMemEval, a controlled diagnostic benchmark for interleaved and resumable interaction trajectories. Experiments on LongMemEval, LoCoMo, BEAM 100K, and BranchMemEval show that ArborMem outperforms the strongest baselines by 3.36 to 10.31 percentage points on the three established benchmarks and by 5.0 points on BranchMemEval. Its advantage grows under constrained read budgets, while complete memory queries remain below half a second.
Graph RAG connects facts no single passage states, but implementations pay three times: in infrastructure, keeping vector store, graph database and document store in sync; in quality, because a pipeline that never refuses extractor output stores edges that assert nothing; and over time, because a graph that only accumulates treats superseded and current facts alike. post-graph-rag is an open-source engine addressing all three. Chunks with embeddings, a canonical entity graph and community summaries live in one PostgreSQL database, with pgvector for search and edge tables for traversal. Extraction output is validated before writing: vague predicates, pronominal names and bare quantities are rejected, predicates normalise onto an optional vocabulary, entities resolve to one vertex per canonical name, and denials keep the positive predicate under a negation flag. A bi-temporal layer records when a relation held and when the system believed it, superseding incompatible earlier assertions from document order. Against LightRAG on three corpora with extraction and embedding models fixed, it builds a denser graph everywhere, up to $2.4\times$ the relations per entity, and a more queryable one: 0.46-0.58 distinct edge labels per relation against 0.77-1.33. It supersedes 13 and 8 relationships where the baseline, having no temporal model, supersedes none. On LongMemEval, 500 questions of long-horizon chat memory, it scores 85.8 percent with gemini-3.6-flash against 71.2 for Zep's gpt-4o and 60.2 for a full-context baseline, leading on all six question types. The largest single contribution is temporal grounding in the prompt: carrying each relation's validity period through to synthesis moves temporal reasoning from 0.496 to 0.881, ablated paired on one graph per instance. Code: post-graph-rag https://github.com/crajah/post-graph-rag; post-graph https://github.com/crajah/post-graph
Humans effortlessly perceive the present while remembering the past, yet streaming VLMs often trade off real-time perception against long-term memory. Prior work shows that shortening the context can sharpen current-scene perception at the expense of long-range recall. To reconcile these abilities, we introduce StreamTTT, which writes long-range history into online-updated fast weights outside the attention context. This leaves a short sliding key-value cache dedicated to recent evidence, mitigating attention dilution. We train StreamTTT jointly on offline long-video QA and a newly constructed real-time QA corpus. On OVO-Bench, StreamTTT-4B outperforms SimpleStream-4B by 1.4 points in real-time perception and 3.7 points in backward tracing. It also remains competitive with the larger SimpleStream-8B on the Real-Time Visual Understanding (RTVU) subset of StreamingBench. Our code will be released.
LLM-based agents increasingly rely on external memory to support long-horizon reasoning and interaction. However, the main bottleneck is not simply storing past experience, but recovering the right set of evidence when relevant information is distributed across many interactions. Existing approaches struggle with this access problem. Full-context methods require noisy long-context search, flat retrieval often returns isolated and incomplete records, and graph-based memory systems can be expensive to construct while compressing rich event context. We introduce RippleMem, a long-term memory system that replaces one-shot retrieval with adaptive associative recollection. Inspired by cue-dependent episodic retrieval and associative completion, RippleMem stores interaction history as cue-rich episodic memory units and organizes them in an event-centric memory graph. Given a query, it first recalls relevant memory anchors through hybrid cues, then expands from these anchors along semantic and structural associations to recover missing supporting evidence. In this way, initially recalled memories serve not only as answer context, but also as cues for completing the evidence needed to answer. Experiments on LoCoMo and LongMemEval-S show that RippleMem achieves the best overall performance across evaluated settings, improving LLM-as-a-Judge accuracy by 3.95% on LoCoMo and up to 11.87% on LongMemEval-S, while reducing graph construction cost by about 30x.
Weitao Chen, Hu Jiaxin, Xie Tianyidan +15cs.CV cs.AI
Recent advances in Multimodal Large Language Models (MLLMs) have led to substantial progress in video understanding, accompanied by a growing number of long video benchmarks. However, existing benchmarks rely predominantly on web-sourced videos that lack inter-clip spatiotemporal continuity, making it difficult to assess whether models can maintain consistent memory across days or weeks of real-world experience. We introduce EgoMonth, the first month-level egocentric video understanding benchmark. EgoMonth comprises over 300 hours of first-person daily-life recordings from 20 participants spanning 20 to 120 days, paired with 1,443 human-crafted multiple-choice question-answer pairs. We design a cognitively grounded 14-task evaluation framework organized into three hierarchical cognitive levels: Schema Consolidation, Episodic Indexing, and Cascading Reasoning. Evaluation of state-of-the-art open-source and closed-source MLLMs reveals that even the best-performing model, Gemini 2.5 Pro, achieves only 71.8% macro-average accuracy, remaining 22.4 percentage points below the corrected human baseline of 94.2%. Several models perform near or below the 25% chance level on tasks such as Route Reasoning, Cross-view Spatial Reasoning, and Direction Judgement, while even the strongest closed-source model remains substantially below human performance. These results indicate that current MLLMs function as lossy summarizers rather than faithful memorizers, highlighting the need for architectures with genuine long-term spatiotemporal memory.
Long-horizon LLM agents must preserve information from past interactions to support future tasks. Existing memory systems typically rely on eager consolidation, invoking LLMs after each interaction to extract, summarize, or update memories. This design makes memory construction increasingly costly as conversations grow. Coarse summarization can reduce construction cost but risks discarding fine-grained contextual evidence, whereas larger retrieval contexts or multi-hop LLM reasoning shift the overhead to query time. We present LycheeMemory V2, an efficient long-term memory framework that replaces turn-level consolidation with semantic segment-level consolidation. Instead of consolidating every interaction, LycheeMemory batches multiple exchanges into segments and encodes each finalized segment into context-independent typed memory records. Segment-level batching lowers LLM encoding frequency, while semantic boundary detection helps preserve coherent event-level and temporal evidence compared with fixed-window batching. The resulting records are organized with lightweight structured indexes for query-planned evidence retrieval. Experiments using GPT-4.1-Mini show that LycheeMemory achieves state-of-the-art performance, reaching 89.22% on LoCoMo and 92.20% on LongMemEval-S. Compared with A-Mem, it reduces construction tokens by 86.0% on LoCoMo and 75.9% on LongMemEval-S without increasing query-time token usage. More broadly, our results suggest that the accuracy--cost trade-off of long-term agent memory depends not only on what information is retained, but also on the granularity at which it is consolidated.
Copying short-term memory (STM) into a slower store can preserve state across a context boundary, but persistence alone does not ensure that the retained state influences subsequent memory access. We test this distinction in a Phasor Memory Network (PMNet) using Consolidator, a shared slot-local operator that transforms routed STM before accumulating it into long-term memory (LTM), without replaying the source tokens. After each consolidation, the KV cache and STM are cleared. The retained LTM can still be read and is also fed into the hierarchical router, thereby conditioning which explicit-memory slots subsequent inputs access. We evaluate this mechanism on a two-segment modulo-10 mapping task in which the second segment updates the mapping at the same memory address. Following a second consolidation and reset, a held-out query must recover the updated mapping from LTM. The backbone and memory interface are frozen, leaving only 12.35K Consolidator parameters trainable (0.041\% of a 29.95M model). Across five paired runs from the same STM-pretraining checkpoint, direct LTM routing raises updated-mapping recall from $44.38\pm1.94\%$ to $87.02\pm1.76\%$ ($+42.64\pm1.10$ percentage points), while immediate STM recall remains 89.90\% in both conditions; both train separate Consolidators and retain the same LTM read paths. Learned consolidation outperforms forced identity accumulation by $21.40\pm1.91$ percentage points without routing and $68.70\pm1.76$ with routing. Thus, on this task, consolidated LTM serves as both retrievable content and an access state that shapes subsequent slot selection.
The next generation of AI agents is increasingly moving beyond systems that answer isolated questions toward persistent personal assistants that can understand, remember, and continuously learn from users' experiences. Such assistants require long-term memory to accumulate and leverage user-specific experiences over time, yet existing benchmarks remain inadequate for realistic mobile settings, where experiences are heterogeneous, multimodal, evolving, and deeply personal. We introduce MobileMem, a benchmark and framework for studying on-device long-term memory, grounded in a year-scale collection of mobile experiences. MobileMem employs a knowledge-grounded synthesis pipeline to construct coherent and temporally consistent long-horizon trajectories from user-app sessions. It provides complementary text and multimodal settings covering multi-hop and temporal reasoning, knowledge updating, and implicit preference inference. Specifically, MobileMem enables agents to remember the past, understand the present, and adapt to the future. By modeling experiences rather than isolated facts, MobileMem moves memory beyond information retrieval toward experiential intelligence for continuous personal learning.
Previous studies have shown that people can develop shared symbols, partner-specific expressions, personal idioms, inside jokes, and other parts of a relational microculture. Recent work has also examined how humans and conversational AI negotiate and revise symbolic meanings. However, long-term human-AI systems still lack a clear design model for recording how a dyad-specific expression gains meaning, checking whether both sides still accept that meaning, and safely reusing the expression in later sessions. This concept-and-prototype paper introduces Private Etymology, a machine-representable relational provenance that records how a dyad-specific symbolic expression is proposed, interpreted, negotiated, repaired, reused, revised, stabilized, contested, forgotten, or retired over time. I also propose relational reuse: reactivating a dyad-specific expression in a later session without fully explaining its meaning again. The contribution is not the invention of shared symbols or relational microcultures. Instead, this paper integrates prior ideas into persistent, revisable, and evidence-grounded symbolic units for human-AI relationships. I present a lifecycle model, an illustrative machine-readable schema, a working Apple Watch prototype, and a longitudinal research agenda. In the prototype, a language model classifies discrete conversational evidence, while deterministic local code decides whether a Shared Symbol can be updated. This prevents a free-form model confidence score or an AI proposal by itself from directly updating the persisted symbol. Private Etymology is proposed as infrastructure for conversational agents to participate in changing relational microcultures without inventing their origins or treating relational meaning as a fixed memory value.
Hakeem Hannoon, Andrew Zhao, Mihir Narayan +2cs.AI cs.CL
Conversational assistants increasingly rely on persistent long-term memory to personalize responses across sessions. However, when stored user information is reintroduced into the model context, it can also influence responses in inappropriate or unrelated settings. We study two such failure modes in memory-augmented LLMs: cross-domain leakage, where memories from one life domain affect responses in another, and memory-induced sycophancy, where stored user beliefs make models more likely to agree with the user rather than respond truthfully. We apply a simple inference-time modification to how memories are presented to the model, without changing the model or the memory contents. Across seven models on PersistBench, we compare the commonly used all-in context format, where memories are injected as an unstructured list, with structured formats that partition memories by domain. This simple modification consistently reduces cross-domain leakage while preserving utility, with our strongest method reducing leakage by $8.8\%$ on average relative to the baseline.
Persistent memory helps long-term agents retain knowledge, yet a single update error can repeatedly distort future retrieval and reasoning. Most existing systems reduce memory updating to a binary Write/Hold decision, which cannot distinguish whether new information should be added, ignored, used to revise an outdated belief, rejected as unreliable, or deferred for verification. These choices may share the same binary label while producing fundamentally different memory states. We introduce TARL, a memory state update framework that maps each statement to one of five executable actions. TARL identifies the affected memory, resolves its temporal scope, compares source reliability, and updates accepted, pending, and rejected ledgers. It is further trained by comparing the memory states produced by alternative update operations, encouraging the model to select the operation that leads to the correct result. We also introduce TARL-Mem, a benchmark with fine-grained action labels and next-state targets. Across in-domain, cross-source, temporal, counterfactual, and sequential evaluations, TARL improves action prediction and state recovery, reduces memory pollution, preserves conflicting evidence, and limits cumulative corruption. The complete model implementation is provided in the supplementary material.
Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history. However, existing memory systems typically process heterogeneous dialogue content through a uniform summarization and retrieval pipeline, leading to either excessive token consumption or irreversible loss of fine-grained evidence. We argue that historical dialogue content should be handled differently according to its compressibility, temporal dynamics, and fidelity requirements. Based on this insight, we propose LeanMem, a lightweight long-term memory framework. LeanMem first filters out low-value content, then stores informative segments as compact profile memory, temporally structured event memory, or source-grounded record memory, depending on the nature of the information. During maintenance, only dynamically evolving event memories are selectively updated, avoiding redundant consolidation of stable profiles and immutable records. During inference, LeanMem dynamically selects memory types and allocates retrieval budgets according to query-specific evidence demands, assembling relevant evidence on demand. On LoCoMo and LongMemEval-S with GPT-4.1-mini and Qwen3-8B, LeanMem improves accuracy over the strongest memory-based baseline in every setting, by up to 15.1 points, at the lowest or near-lowest construction cost, inference tokens, and latency. The code and datasets are included in the supplementary materials.
Jong Wook Kim, Byoungjae Min, Kennedy Edemacu +3cs.CR cs.CL cs.LG
Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected attributes even when they are never stated explicitly. We formalize this threat as adaptive transcript privacy and introduce DP-MemView, a differentially private interface that privately selects public response-conditioning views and exposes those views---rather than raw memory---to the response LLM. Each private selection is charged to every protected attribute whose memory group intersects the read set. Per-attribute ledgers block any selection that would exceed its cap and return a fixed generic view instead. Under an explicit interface contract, we prove pure B_a-DP for the entire adaptive transcript. We also extend the result to stores that differ across multiple protected groups and bound how much observing the transcript can change an adversary's prior odds. We evaluate the online and preallocated modes with three response LLMs on a controlled adjacent-store benchmark and a public-corpus transfer track. Both modes keep transcript distinguishability near chance while preserving target-required personalization and overall response quality. Further diagnostics show that removing key safeguards causes mismatched output support, missing ledger charges, revealing side channels, or growing long-horizon leakage.
Long-term memory is essential for language agents operating across extended interactions and evolving tasks. Existing memory-augmented agents mainly focus on storing and retrieving past experience, but the quality of stored memories may degrade over time. In particular, previously distilled insights can become outdated, over-generalized, or harmful under new task contexts, causing memory pollution when repeatedly reused. To address this issue, we study insight-level memory maintenance for long-term language agents and propose a failure-aware memory maintenance framework based on an editable insight graph. Each insight node tracks positive evidence, negative evidence, and an activation state, enabling the agent to distinguish reusable insights from conflicting or invalid ones. We further introduce a utility-aware retrieval mechanism and a graph controller that updates the memory graph after task execution by keeping reliable insights, archiving invalid ones, revising outdated ones, and adding newly discovered reusable insights. Extensive experiments show that our method consistently outperforms representative memory-based agent baselines across different backbone models. Ablation studies further demonstrate that append-only memory is insufficient for long-horizon tasks, while evidence-aware retrieval and graph-level editing improve memory reliability and downstream task performance.
Long-term memory is critical for LLM agents operating over long-horizon interactions. However, several persistent limitations of existing memory systems can be traced to two recurring misalignment patterns in long-term interaction settings: Temporal-Structural Misalignment (TSM) and Delayed Utility Manifestation (DUM). TSM arises when temporal proximity does not reliably align with topical or event-level relatedness, whereas DUM arises when write-time salience does not reliably predict future query utility. To mitigate these misalignment patterns, we propose MemSIF (Memory with Structured Interactions and Facts), a structured interaction-to-fact memory framework. Structured Interaction Memory organizes raw interactions into Topical Segments that preserve local topical coherence and Event Trajectories that maintain cross-time event continuity. Dual-Track Fact Memory uses two complementary tracks: CoreFact memory consolidates stable, schema-guided information at write time, whereas ActiveFact memory forms facts on demand and promotes those supported by multiple historical sources and recurring query demand for reuse. Experiments on LoCoMo and LongMemEval-S across five backbone LLMs show that MemSIF achieves the highest Total ACC in all settings, outperforming the strongest baseline by 2.29%-8.79% on LoCoMo and 2.87%-6.15% on LongMemEval-S. These results support the effectiveness of combining Structured Interaction Memory with Dual-Track Fact Memory to mitigate TSM and DUM. Code is available at https://github.com/luoyufeihaha/MemSIF.
Long-term memory is essential for LVLM agents to maintain consistency and integrate information across extended multimodal interactions. Existing agent memory systems, however, often reduce visual experiences into textual summaries or rely on static retrieve-then-reason pipelines, which are inefficient at query time and brittle when questions require image-text binding, temporal updates, or visual details. We propose Prospective Multimodal Memory Compilation, a framework that shifts part of the memory reasoning process from query time to memory consolidation time. Given accumulated multimodal interactions, a Questioner predicts future question candidates, a Planner compiles question-conditioned multimodal memory programs, and a Doubter verifies whether the planned evidence path can support the predicted answer. The verified question-program pairs form a structured question bank for efficient query-time routing and evidence retrieval. Experiments on multimodal long-term memory benchmarks show that our method improves answer quality and visual evidence recall while reducing query-time token and latency costs. Extensive ablations analyze the effects of self-feedback, dynamic planning, raw-image access, and question bank coverage.
LLM agents increasingly rely on long-term memory to support multi-session interaction and personalization. However, existing agent memory systems are designed around forward-only evolution, continuously accumulating, consolidating, and overwriting knowledge, with no principled mechanism to inspect, version, or revert prior states. This makes agents brittle under corrections, concept drift, and memory corruption, particularly after they have already been exposed to subsequent information. We present ChronoMem, a semantic version-control layer for agentic memory integrated into the production-ready, open-source Agent Development Kit by Google. ChronoMem commits whole-memory snapshots at each memory write, maintains structured version histories, and supports natural-language rollback requests by mapping undo intents to concrete historical versions through hybrid lexical and semantic retrieval, rank fusion, and reranking. We further introduce a post-exposure evaluation protocol that tests whether an agent can behave counterfactually after rollback by answering queries and summarizing history as if future updates had never occurred. On long-horizon conversational benchmarks augmented with evolving memory states and rollback tasks, ChronoMem substantially improves rollback-consistent question answering and history summarization relative to prompt-only and retrieval-only baselines, while achieving strong performance in semantic version selection. To our knowledge, ChronoMem is the first open-source system and benchmark for systematic semantic global memory rollback in LLM agents.
Deployed LLM agents increasingly keep their long-term memory as a filesystem: a directory tree of markdown files that the agent itself reads, writes, and reorganizes through generic file tools. Yet research has largely passed over this medium: prior systems design bespoke memory representations and study retrieval over them, leaving the default's two working assumptions untested: that an agent can keep a growing store organized as memories accumulate, conflict, and go stale, and that this organization pays. We present the first systematic exploration of filesystem-based memory for LLM agents. We formalize the setting as three roles around one memory filesystem: a management agent integrates and organizes incoming content, a search agent answers queries with cited sources, and an execution agent supplies task trajectories that are distilled into skills, unifying declarative memory and skills in a single store. Across long-conversation benchmarks and embodied tasks, we vary memory shape (agent-organized hierarchy, verbatim dump, chunk retrieval), stream scale, tool harness (sandboxed shell, memory-tool-style functions, varied search tooling), and the strengths of the management and search agents, tracking answer quality, cost, and store health as memory grows. What organization reliably buys is search economy: organized stores roughly halve retrieval cost where material is large. Today's agents, however, fall short of the default's promise: in our growth study, organization erodes for all but the strongest management agent, and no agent we measure converts organization itself into better answers. And the model is not the only lever over a store's shape: changing the tool set alone reshapes the store as strongly as swapping the model. The study turns the filesystem default from an assumption into a design space for agent memory.
Long-term memory systems store what a user says in an external store and retrieve it when a related query arrives. This interface rests on an assumption so natural that it is rarely stated: a memory that is needed will resemble the query that needs it. World knowledge breaks the assumption. A tree-nut allergy should change the answer to a macaron request through their almond-flour ingredient, yet the two texts share no cue a retriever can see. We call this failure mode the implicit-association blind spot and introduce InMind, a 125-task, expert-verified benchmark spanning ten life domains, with 113 tasks grounded in citable public sources. Its paired controls separate three explanations that existing evaluations conflate: the fact was never stored, the model lacks the bridging knowledge, or the fact was stored and never surfaced. The verdict is clean. With the decisive memory placed in context, the backbone answers 84.0 percent of indirect queries; when the same memory must be retrieved, six vector, graph, and agentic memory systems reach at most 14.4 percent, even though they recall the same facts on demand at up to 100 percent. An embedding with eight times the dimensionality raises answer-blind target recall for every system yet leaves the gap essentially intact. A minimal diagnostic probe that keeps memory visible before the query arrives recovers most of the gap, locating the failure in the query-conditioned interface itself and pointing to routing, deciding which facts must stay visible, as the open problem InMind is built to score.
Benchmarks for LLM-agent memory typically generate conversations first and extract answer keys afterwards -- with documented label-error and contamination problems -- and they overwhelmingly measure short interaction histories. We invert the pipeline: a seeded life-script sampler emits facts with validity intervals, volatility classes, and source channels before any text exists; an LLM renderer writes chat and email from per-event fact manifests; a fidelity verifier confirms every planted fact; and questions are instantiated mechanically from the script, so gold answers are script-valid by construction and separately validated for answerability. The synthetic, fictionalized corpus (~380 questions, 15 types) embeds features absent from the benchmarks we survey: per-fact validity intervals, sent/received trust distinctions, injection probes in a benign harness, and as-of-date question sets. Benchmarking five memory architectures against a no-memory control (fixed answerer, versioned LLM judge, three replicates, two horizons), we find backend rankings invert with history length: the budgeted curated-map memory that leads at three weeks loses recall of evicted content by nine weeks (96% to 72%) while a provenance-typed graph rises to 90%; the inversion is positive for all six users under complete cross-family re-judging (exact p=0.031). A full-rendered-history baseline ties or exceeds the best memory system at the short horizon but shows no judge-independent advantage at nine weeks, at about twice the read cost. Write-stage quality strongly correlates with downstream quality (weakly-written facts fail 24% vs 2%), and injection resistance tracked whether provenance boundaries survive representation. A layered architecture performs best among the memory systems in both regimes (96.8% short-horizon) and is released as Veracium, an open-source library, with the corpus generator and harness.
Elizaveta Shevtsova, Inna Glebkina, Mark Baushenko +2cs.CL cs.AI
The ability to handle long-term memory in LLMs is becoming increasingly critical, yet existing benchmarks remain English-centric and rely on aggregate retrieval metrics, failing to capture interactions between long-range context, temporal information, and reasoning. To address this, we introduce RUMBA (Russian User Memory BenchmArk) - a new benchmark for long-term conversational memory that provides a fine-grained taxonomy of memory-centric question types and a unified methodology accounting for semantic type, session scope, temporal reasoning, and the explicitness of temporal expressions. RUMBA consists of timestamped user-assistant dialogues with QA pairs requiring retrieval, combination, and reasoning across sessions. While designed for Russian, we also provide an aligned English subset under the same methodology. We evaluate contemporary memory systems and long-context models, and show how RUMBA serves as a diagnostic tool to analyze model behavior across benchmark slices and identify strengths and failure modes of different memory mechanisms.
Maksim Sheverev, David Finkelstein, Sergey Nikolenkocs.LG cs.AI
Long-term memory is becoming a core component of LLM agents, but most memory benchmarks evaluate conversations or compact summaries, while research agents need to restore evidence from full scientific papers. We introduce two full-text scientific-memory benchmarks, Public AI Memory (PAIM; 81 papers, 66 questions) and Public Transformers (PTr; 252 papers, 98 questions). We evaluate eight memory/retrieval systems, including our own proposed Theoria, plus a no-retrieval baseline. Our results show that memory leaderboards are not interpretable without the full protocol: ingestion granularity, raw-text preservation, retrieval budget, retrieval modality, rubric audit, and judge choice all affect the outcome. For example, on PAIM Graphiti wins convincingly but uses 2.6M characters of retrieved context per query, and after controlling for retrieval budget the lead disappears. On PTr, for the systems where BM25 retrieval can be added cleanly, the sparse-dense hybrid is the single most significant intervention: hybrid variants of Simple RAG, Mem0, and Theoria tie for the lead within 0.03 points. Multi-judge and human side-by-side calibration show that LLM-as-a-judge rankings are consistent across frontier judges and agree with human evaluation, with an effective resolution of roughly one point on a ten-point scale. We argue that scientific memory should be evaluated as budgeted, modality-aware context restoration rather than as an unconstrained architecture leaderboard, and we release the datasets, harness, raw outputs, judgments, and scripts to reproduce our results and serve as tools for such evaluation. Our code is available at http://gitlab.com/quantellence/research/scientific-recall-bench , and the datasets are available at http://huggingface.co/datasets/quantellence/srb-data .