Overview

Agent memory studies how AI systems preserve and use information beyond the current context, from personal facts and changing state to task procedures and spatial experience. Common approaches include retrieval over raw histories, summaries and vector or knowledge graphs, alongside methods that organize episodic, semantic, and procedural memory or learn when to update, compress, and forget. Evaluation spans conversational benchmarks such as LoCoMo and LongMemEval as well as multi-session web, coding, and embodied tasks, with growing attention to interference, stale information, provenance, privacy, and whether retrieved evidence actually improves later actions. A central tension is balancing reliable, generalizable memory with limited context, latency, and maintenance cost; strong recall on question-answering tests does not yet guarantee robust use in evolving environments.

Latest papers

208 papers26 papers in the last four weeks, down 32% on the four weeks before. 0.2% of all new papers.

Nov 15, 2026

StaleBench: Isolating Stale Retrieval in Agent Memory, and Pricing the Fix

An agent that stores facts over time eventually stores several versions of the same fact. Asked a value-agnostic question - "which team does X play for now?" - a similarity retriever cannot prefer the current version, because every version matches the entity the query names. StaleBench isolates this stale-retrieval failure on 892 real updating facts, with currency labels from the source (Wikidata validity years via TempLAMA), never from a retrieval score. Our central result is that retrieval metrics can rank memory policies backwards: a retention policy and its retain-everything control return the identical statement at rank 1 for every test query, yet differ by 29.5 and 65.6 points in reader accuracy on two readers when no date is shown. Contamination@5, the metric we add, ranks them correctly where current@1 and current@5 do not. Withdrawing the lexical anchor that statements carry costs deployed keying mechanisms tens of points of freshness; entity resolution on both the write path and the query recovers most of the loss. Three deployed systems (Mem0, Graphiti, LangMem) and a reimplemented ERASE each handle supersession differently, and no single scoring convention describes all four. We release the data, a frozen evaluator, and reference baselines.
Nov 14, 2026

Omni-Workspace: Benchmarking Omni-Modal AI Assistants on Multimodal Workspace Tasks

Omni-modal agents are expected to move beyond multimodal understanding toward completing complex tasks in realistic multimodal environments. In these settings, information is distributed across heterogeneous files and modalities, with cross-file and cross-modal dependencies requiring agents to continually coordinate perception, reasoning, and tool use as newly gathered evidence informs subsequent actions. However, existing omni-modal benchmarks primarily focus on multimodal perception and understanding, leaving complex task completion through sustained interaction with multimodal workspaces underexplored. We introduce Omni-Workspace, a benchmark comprising 380 deep-research-style tasks across four multimodal workspace types and two difficulty levels. These tasks require agents to inspect and process workspace files, retrieve external information when needed, integrate evidence across files and modalities, and produce artifacts satisfying explicit requirements. Evaluating 18 representative models reveals limitations in long-horizon multimodal workspace execution, with the best model scoring only 65.93 on average. Further analysis identifies multimodal context inflation and task-state drift as recurring challenges. Motivated by these findings, we further propose OmniFocus, a lightweight approach combining multimodal working-memory management with explicit task-state tracking to improve performance and efficiency. Omni-Workspace advances the evaluation and development of omni-modal agents toward autonomous completion of complex tasks in multimodal workspaces.
Nov 12, 2026

CoReMem: Cost-Internalizing Memory for Successive Coding Tasks with Prospective Valuation

Coding agents tackle successive tasks on an evolving repository, carrying forward edits and writing memory before the next task is known. Selecting memory for unknown next tasks requires balancing future usefulness against the costs of writing and reading it. The actor must also decide when acting on available memory saves effort as the task unfolds. We introduce Coding-Repository Memory (CoReMem), a cost-internalizing framework that guides memory design and actor adaptation through measured memory value on the next task. Prospective segment valuation compares runs of the next task with and without individual trajectory segments from the same inherited repository state, guiding a compact memory built around anchors: repository locations and executable checks. Actor adaptation estimates on-policy memory value within rollout groups with and without memory, using a reward that prioritizes resolution and penalizes step count in successful runs. Provenance-gated value credit assigns the additional value term to steps identified as using memory-supplied anchors, while every step retains outcome credit. On ChainSWE, CoReMem raises the 27B actor's resolve rate from 21.0% to 25.7%, with 17% fewer steps and 11% fewer total cache-aware tokens, including memory-module calls, relative to the untrained actor model without memory.
Nov 12, 2026

Discovering Effective Agent Memory Designs through Program Evolution

Program evolution provides a promising approach to discover agent memory designs and study the choices underlying their effectiveness. We introduce MAPE, a framework that evolves whole memory programs from minimal seeds through a standardized lifecycle interface and an iterative diagnosis-proposal loop. Experiments on LoCoMo and LongMemEval yield an absolute accuracy gain of up to 12% over manually designed baselines at 35% of the serving cost, with further evaluations supporting transfer across serving backbones and benchmarks. Empirical analyses and ablations identify and validate two recurring design patterns: retaining raw conversations as retrievable evidence preserves details omitted from extracted memories, while composing retrieved evidence according to query intent helps the answering model use it effectively. Transplanting the composition module into five existing memory systems improves accuracy across all five. Beyond these patterns, the search objective shapes where computation goes: optimizing serving cost alongside accuracy shifts computation from LLM-based memory construction to selective processing at query time while retaining competitive accuracy. Together, these findings offer empirical lessons for agent memory design. Code is available at https://github.com/ash-ding/MAPE.
Nov 12, 2026

Remember What Changes the Odds: Critic-Gated Event Memory for Long-Horizon Manipulation

In long-horizon manipulation, a robot may need to take different actions under identical observations, depending on task progress and the outcomes of earlier attempts. We refer to this ambiguity as decision aliasing. Resolving it requires the policy to maintain memory of its execution history. To reduce the cost of processing full observation histories, recent methods build compact event memories using perceptual, semantic, or kinematic cues. However, these criteria may miss events that matter for task success. We instead propose an outcome-grounded principle: remember events that substantially change the predicted probability of eventual success. Following this principle, we introduce CGEM, a critic-gated event memory that uses a critic to select events with large estimated changes in success probability. Positive and negative changes are encoded as progress and failure records, respectively. Failure records are discarded once the corresponding subtask is completed. In a ten-subtask diagnostic environment with exactly computed success probabilities, CGEM achieves 88.0% success, compared with 0.0% for both a 36-step observation window and a kinematic event memory. Removing failure records reduces success to 1.7%.
Nov 11, 2026

Can Agents Relive Past Experiences? Diagnosing Event-Affect Decoupling in Affective-Episodic Retrospection

As memory-augmented agents increasingly support long-term and personalized interactions, reliable recall of emotional experiences while preserving their associated affect becomes necessary. However, existing evaluations usually assess emotion accuracy and factual memory grounding separately, overlooking event-affect correspondence. In this work, we formulate Affective-Episodic Retrospection (AER) as a task that explicitly evaluates the recovery of past events, associated affects, and their correspondence, and define Event-Affect Decoupling as a failure mode where the correct emotion is recalled but associated with the wrong episode. To diagnose Event-Affect Decoupling, we propose EM-TRACE, a stage-wise framework that decomposes AER into retrieval, affect recovery, and realization. On a controlled GoEmotions-based benchmark, Emotion-only retrieval achieves 28.65% affect recovery but retrieves the target episode for only 4.44% of queries, yielding a UAR of 24.21%. Further analysis reveals that event retrieval and affect assignment introduce distinct binding failures. These findings show that reliable AER requires grounded recall of emotional experiences, where episode retrieval, affect recovery, event-affect binding, and generation quality should be evaluated jointly. Our code is available at https://anonymous.4open.science/r/A412/.
Nov 10, 2026

Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents

External memory enables LLM agents to improve from experience by distilling trajectories of past tasks into concise lessons for new tasks. However, memory can also lead to memory-induced degradation, where an agent fails on tasks it would solve without memory, often because it follows a lesson that is incorrect, or misapplies or misreads a valid one. This is because lessons are inferred from trajectories labeled only with task success or failure, yet are typically provided without the trajectories they came from, leaving the agent no way to check them. To address this, we introduce WikiTrace, an evidence-linked memory system designed to let agents check each lesson against its original trajectory. Specifically, motivated by the finding that a trajectory often still holds the evidence needed to catch an erroneous lesson, WikiTrace stores each lesson as a concise insight linked to a summary of why its trajectory succeeded or failed and to the raw trajectory itself. Then, on a new task, the agent starts from all insights and, whenever one lacks details needed to act, conflicts with another, or comes from a failed task, descends through its links with terminal tools to fill in missing details or correct the insight before acting. We validate WikiTrace on five agentic benchmarks, showing that it consistently outperforms existing memory approaches and a baseline given the same insights alone, while also reducing memory-induced degradation. Our code is available at https://github.com/yukyeongleee/wikitrace
Nov 9, 2026

MIRIX-2.0: Multi-Agent Memory System

Long-term memory lets LLM agents personalize, stay consistent, and reuse what worked before. Parametric memories need training, consolidation can lose details for good, and keeping every record leaves a growing store to search. We present MIRIX-2.0, a multi-agent memory system designed to be practical, accurate, and efficient at once. It is the most accurate of the compared systems on four of five QA benchmarks. It reaches 91.4% on LoCoMo and 72.6% on LongMemEval-S, where it leads the strongest baseline by 14.3 points, and with AutoDream disabled it gains 31.0 and 22.0 points over HyperMem on single-hop and multi-hop document QA. As procedural memory, it yields the highest mean success among the compared memory methods on ALFWorld and WebShop and reaches 49.2% on MetaClaw-Bench, against 44.0% for MetaClaw's skill library. Six typed memory agents keep complete records as the system of record, and a provenance hypergraph indexes episodic and semantic records with n-ary frames that cite their rows. Retrieval runs under explicit budgets, so the evidence a question inspects does not grow with the history. AutoDream merges duplicate anchors outside the write path without rewriting any record, and it distills task sessions into skills. With AutoDream disabled, MIRIX-2.0 answers faster than HyperMem on all five timed benchmarks. It needs no fine-tuning, runs with closed and open models, and its code is public.
Nov 9, 2026

Correct Answers from Insufficient Histories: A Controlled Study of Agent Memory Evaluation

An answer can match the reference for a complete agent history even when the reader's visible history does not determine it. We study this distinction using executable device logs. Our protocol separates reference agreement, certified evidence sufficiency, and context-appropriate behavior. Insufficiency requires two legal histories yielding byte-identical visible contexts but different answers; public chronology and query cutoffs certify sufficient prefixes. On 80 confirmation histories, Qwen3-32B matches 87 hidden references among 203 insufficient raw-prefix instances, with only seven appropriate abstentions. A fixed-input DeepSeek-V4-Flash replication matches 85 and abstains on 21 of the same 203 instances. Each reader makes 1,600 requests. Compact CSV's estimated appropriateness effects remain inconclusive: +3.16 percentage points, clustered 95% interval [0.00,6.57], for Qwen and +2.46, [-1.84,6.94], for DeepSeek. A separate held-out judge study achieves 99.38% correctness but retains support errors and truncations; a deterministic baseline solves all constructed cases. These results support an evaluation diagnosis across two hosted reader configurations, not gains for a general memory system or natural-language evidence assessment.
Nov 5, 2026

Persistent Retrieval for Conversational Agents: A Study of Retrieval Efficiency

Conversational agents can retrieve information directly or delegate retrieval to a subagent. This design choice affects how retrieval history is maintained, what context each model call receives, and what information must be re-retrieved in follow-up questions. We compare three designs: skill-based retrieval in the main agent, a non-persistent retrieval subagent that generates a findings response, and our persistent retrieval subagent, which maintains retrieval history across turns and returns retrieved evidence directly to the main agent. Our approach also allows the main agent to request corrections from the same subagent. We evaluate the three designs on enterprise questions posed independently, within shared conversations, and as dependent follow-ups. Across five multi-turn settings, our approach uses 43.3% fewer recorded agent-model tokens and incurs 45.0% lower estimated API cost than skill-based retrieval, while reducing average response time by 9.1%. Compared with non-persistent retrieval, it reduces response time by 15.6 seconds per question, while using 65.1% more tokens and incurring 29.1% higher estimated API cost. Our approach shifts the retrieval subagent from producing synthesized responses to maintaining retrieval state and supplying evidence that the main agent can directly evaluate and use for answer generation.
Nov 3, 2026

Prospective Memory for Proactive LLM Agents

Most memory systems for LLM agents are retrospective, preserving and retrieving past information to inform current decisions. Proactive agents, however, also require prospective memory: retaining future-directed intentions and realizing them when appropriate opportunities arise, even without explicit requests. Crucially, remembering the right intention does not guarantee acting at the right time: a related observation may call for waiting, while a later cue may make the same intention actionable. Inspired by cognitive theories of human prospective memory, we introduce Pro-Memory, a memory framework that separates maintaining future intentions from deciding when and how to realize them. Pro-Memory preserves pending objectives linked to their supporting evidence, assesses new observations against their original goals and activation conditions, and coordinates appropriate contributions with the agent's ongoing actions. It further updates intention states based on actions actually issued or evidence of resolution, while an experience memory distills feedback from completed episodes into guidance for future decisions. Experiments on two benchmarks spanning delayed-intention tasks and open-ended proactive assistance demonstrate consistent improvements in proactive task performance over representative memory approaches across multiple LLM backbones, while limiting unnecessary interventions.
Nov 2, 2026

What Is This Memory Useful For? Measuring Task-Conditioned Utility in Long-Term Agent Memory

A stored experience may answer one future question and offer little help with another. We measure this task-conditioned utility rather than assigning each memory a single importance score. A task-blind writer stores a memory without seeing the later task; a frozen reader then answers that task with and without the memory, using identical filler. A cost ledger records the resources used to form, store and expose the memory. On single-call factual-recall tasks built from LongMemEval-V2 web-agent memories, the same memory helps more when it contains information needed for the answer. Its mean paired reward gain on these answer-bearing task pairs exceeds that on matched-control pairs by +0.33+0.33 (95% interval +0.21+0.21 to +0.46+0.46). The tested task-blind summaries and structured records yield smaller gains than Raw, including at fixed total context; a budget sweep is consistent with retention of answer-bearing content contributing to the difference. The bearing--control contrast remains positive in a new session with randomized memory position and under a second reader, although individual memory--task labels change. Generic retrieval performs above chance but misses most screen-defined answer-bearing memories. The factual-recall gains do not extend to the tested software-engineering and scientific-coding benchmarks, where even raw memories have no measurable effect. We provide a public, versioned Conditional Memory Utility Dataset of paired measurements and costs. The practical takeaway is to evaluate memory compression by the task utility it preserves alongside its costs. Task-conditioned measurements make this comparison possible; their stability must also be checked.
Nov 2, 2026

A State Change Is Local, Its Consequences Are Not: Dependency-Aware State Revision for Long-Term Agent Memory

Long-lived agents rely on persistent memory of users, tasks and decisions, and this memory must stay consistent with a world that keeps changing. When an upstream fact changes, however, memory systems can revise the contradicted memory itself while the beliefs, plans and actions derived from it remain accepted, even though they have lost their support. We therefore formulate dependency-aware state revision, which asks not only what changed but also which dependent states should no longer be trusted. To address it, StateGraph maintains an evolving state dependency graph whose edges are recovered from interaction histories. Its core design is counterfactual verification: each candidate edge is tested by asking whether the dependent state would survive the loss of its premise, which separates support dependence from semantic relatedness, and revision then invalidates a dependent state only when a strict dependency fails and no independent support path survives. To test this design, we introduce StateChangeBench, a controlled benchmark of 50 author-constructed cases annotated with cascade depth, hard negatives and action consequences. On it, StateGraph's Impact-F1 margin over a CUPMem reimplementation is 6.9 percentage points at depth 1 and 26.0 at depth 3+. On public long-term memory benchmarks, its point estimates are comparable to or higher than those of the evaluated baselines on most datasets. These results provide initial evidence that explicit dependency tracking can improve selective memory revision under changing conditions.
Nov 1, 2026

Delivered, Not Used: Evaluating Agent Memory at Its Point of Use

Task success, retrieval quality, and cost do not show whether an LLM agent used a delivered memory or what followed from that use. We introduce MemUse, which evaluates memory at its point of use in recorded trajectories: each memory delivery is compared with what the agent could already see and followed through the agent's later actions and their consequences. An agentic judge rates each delivered entry's relevance, accuracy, novelty, influence, and observed effect; programmatic checks enforce complete reading of cited evidence, and fixed rules aggregate the ratings into verdicts linked to memory histories and delivery cost. On 8,000 SWE-bench Verified episodes from three memory systems, resolve rates stay within 0.4 percentage points of a no-memory baseline, yet MemUse shows that most delivered entries were irrelevant, most relevant entries went unused, and in two systems most deliveries restated content the agent could still see. It also surfaces effects that outcomes hide: 23.2% of episodes with beneficial memory use still failed, and 5 of 16 with harmful use still succeeded.
Oct 31, 2026

CivicBench: A Benchmark and Memory Framework for Web-Based Civic Data Analytics

Municipalities publish service requests, geographic boundaries, weather observations, demographic estimates, and operational guidance through independently maintained Web portals. Civic analysis must combine these sources while preserving their schemas, source links, spatial and temporal scopes, and interpretive limits. Tool-using language agents can perform this integration, but existing task benchmarks rarely test whether a computed claim remains supported by the records used. We present CivicBench, a 400-task benchmark over four cities and two years that materializes civic Web data into frozen bundles for reproducible evaluation. Executable contracts score computation, source linkage, coverage, scope, qualified answers, and refusal when the requested conclusion is not supported. We also introduce Task-State Memory (TSM), which compiles tool observations into typed assertions, reconciles records only within compatible scopes, and retrieves a bounded state organized around unresolved constraints. Across nine completed model pairs, eight yield positive mean-score differences with 95% semantic-contract-cluster bootstrap intervals excluding zero; the ninth interval crosses zero. The benchmark and memory framework make the records behind a claim inspectable at the point of decision.
Oct 30, 2026

When the Past Shapes Action: Understanding Embodied Memory

Recent advances in generative foundation models have expanded the capabilities of embodied AI, enabling increasingly general navigation, manipulation, and long-horizon task execution. However, effective interaction with dynamic environments requires more than only strong perception and reasoning: agents must act with partial knowledge and retain, retrieve, and update information from past observations, actions, and experiences. This survey examines embodied memory as a mechanism for preserving decision-relevant information beyond the current observation. We organize existing approaches along two complementary dimensions: six fundamental memory requirements, spanning world-state persistence, task progress, belief maintenance, and experiential learning; and eight architectural categories, including recurrent states, fast weights, visual and symbolic representations, spatial memory, and experience-based systems. We analyze their capabilities and limitations, and examine how existing benchmarks evaluate memory-dependent behavior, distinguishing genuine use of historical information from general task performance. Finally, we identify open challenges in selecting relevant experiences, maintaining consistent beliefs in changing environments, and consolidating knowledge across episodes. Our analysis provides a framework for understanding memory as an essential component of reliable, adaptive, and lifelong-horizon embodied intelligence.
Oct 26, 2026

When Retrieval Is Not Enough: Obsolete Facts in Agent Memory

Memory-agent benchmarks often collapse retrieval and answer generation into one score, making it hard to tell whether a failure comes from missing an update or from not using an update that was already retrieved. We examine this distinction on the single-hop FactConsolidation task of MemoryAgentBench. With Qwen2.5-7B-Instruct on 6K-history BM25 accuracy drops from 45% to 32% when the retrieved evidence budget grows from 64 to 512 tokens, even though a gold-assisted post-hoc audit finds the newest statement in every retrieved set. Most of the errors occur on questions that also contain an obsolete statement version. Under a frozen prompt and equal four-statement evidence size, replacing one unrelated statement with the obsolete competing statement reduces accuracy from 100% to 44.6% for Qwen2.5 and from 100% to 87.8% for Qwen3-14B, with all 50 harmful paired flips classified as stale. A 32K-history replication likewise favors BM25-64 over BM25-512 (69% versus 58%). These results suggest that retrieving the correct fact is not enough. An obsolete competing statement can be more harmful than an unrelated piece of evidence of the same size.
Oct 26, 2026

Adaptive Memory Index Evolution for Agents

Long-horizon agents continually accumulate experience, yet retaining a memory does not guarantee access when it is needed. Existing systems can adapt both memory content and access; we isolate persistent access updates as a separately controlled adaptation layer. We formulate this target as Memory Index Evolution and instantiate it with Adaptive Memory Index Evolution (AMIE), a lightweight plug-in layer that evolves per-memory access state from deployment retrievals without modifying stored content or retraining the host memory system. AMIE distils a semantic teacher's keep/suppress judgments into a retrieval-conditioned policy and accumulates its selective actions into bounded state that reweights subsequent host retrievals. Surprisingly, even a zero-call policy that simply accumulates retrieval frequency can match or outperform semantic policies in several settings, revealing retrieval traffic itself as a strong signal for access adaptation, while learned selectivity improves robustness when frequently retrieved memories remain useful. Across five retrieval-based hosts and three benchmarks, trained AMIE improves downstream F1 or accuracy in all 15 comparisons, by 0.70--3.37 percentage points (up to 25% relative), and improves retrieval in all 10 comparisons. Controlled analyses show that persistent competitor suppression can expose previously unseen evidence, while suppressing repeatedly useful memories creates the complementary failure mode. Together, these results establish persistent memory access as a practical adaptation layer, distinct from the content it serves, in retrieval-based agent memory systems.
Oct 26, 2026

BehaviorMem: Building and Evaluating User Memory from Real-World E-Commerce Behavior Streams

User memory helps personalized systems build on their understanding of users over time. In e-commerce, users convey their preferences and needs through both explicit language and implicit interactions with products. We study memory built from logs of these interactions, examining how it can remember concrete evidence and established interests, and use that evidence to infer underlying needs and preferences that inform judgments beyond well-observed product domains. Existing memory methods primarily target language-based interactions, and evaluations offer limited real behavioral data and limited separation of these capabilities. This leaves open how to jointly support and separately evaluate remembering and inference from behavioral logs. We formulate the problem of continual behavioral user memory around these joint requirements and develop a dedicated evaluation framework and memory method to address them. BehaviorMemBench is a benchmark built from real e-commerce logs covering 1{,}194 users and 17{,}462 behavioral batches over more than three years, with automatic future-behavior labels and a task-independent memory interface to separately evaluate remembering and inference under a common protocol. BehaviorMem is a memory design that organizes explicit behavioral facts and inferred user characteristics across long-term and short-term scopes in a two-axis state, with evidence-grounded formation, continual maintenance, and query-independent readout. Experiments across two builders and two task readers show that BehaviorMem leads the evaluated agentic memories on remember and infer, and reveal different method rankings across the two capabilities and competitive statistical baselines. Validation on a public dataset further supports its usefulness for downstream tasks based on behavioral histories.
Oct 22, 2026

Subgoal-aware Memory Graph for GUI Agent

GUI agents aim to automate complex user tasks by interacting with mobile interfaces, but ef- fective decision-making in long-horizon set- tings requires reusing prior experience rather than relying solely on the environment ob- servations. Existing memory-based methods typically store experience either at the single- action level or as entire trajectories. Single- step actions are often too fine-grained to carry meaningful semantics, since the success of an individual action does not necessarily imply progress towards the overall goal. In contrast, whole trajectories are often too coarse-grained and difficult to reuse across different tasks. We propose a subgoal-aware memory graph that distils past trajectories into structured, reusable evidence at the level of subgoals. We define a subgoal as consecutive actions shar- ing a single intent, the granularity at which progress toward the task becomes meaning- ful. To reduce redundancy and support cross- task reuse, we organise subgoal experiences as nodes in a graph, where related memories can be merged, extended, and retrieved based on the environment observation. On SPA-Bench, our method improves success rate by 11.11% over the baseline.
Oct 22, 2026

The Value of Memory in Language Agents

Language agents carry information from past experience into future tasks whose demands may be unknown or change over time. We develop a decision-theoretic account of the capability available in history, retained in storage and realized through use, together with the costs of recovery and revision. Drawing on comparison of statistical experiments, information acquisition and the value of computation, we express these values in units of avoided task loss. Recovery and revision define attainable risk-cost profiles and preservation across uses. A cost-aware simulation condition and five minimal counterexamples establish how information timing, access, computation, feedback and demand shape these comparisons; a pointer with zero answer mutual information can reduce the cost of exact recovery. Allocation and recovery criteria identify when gains pay for estimation, selection and evidence access. Complete-split studies on LoCoMo, LongMemEval-S and PersonaMem cover 3,075 questions and two readers. They show complementary value from saved state and recovered evidence, task-dependent performance orderings, and the role of reuse in amortizing construction costs. Multi-project workflows connect correction to preservation and validation costs. Together, the theory and studies support decisions about what to retain, which recovery options to preserve, and how to adapt memory as evidence and objectives evolve.
Oct 21, 2026

ProactEgoMem: Benchmarking Proactive Memory in Streaming Egocentric Video

Today's multimodal assistants are typically prompted to interpret the visual evidence presented to them. To offload the cognitive burden of remembering across long horizons, wearable assistants should instead proactively acquire and maintain useful memory as the user's surroundings evolve. Doing so on the user's behalf requires identifying what matters, understanding the scene in real time, and initiating memory maintenance in the background while the user stays focused on their activities. We introduce ProactEgoMem, a benchmark that evaluates proactive memory in streaming egocentric video. Three tasks ground the evaluation in ambient environmental needs: Information Capture (IC) preserves transient yet dense visual information, State Tracking (ST) follows changing object states, and Location Tracking (LT) records object movements. The benchmark defines its protocol at two levels of proactiveness: the Notification Level asks for a single timely notification that satisfies the user's intent, while the deeper Intervention Level asks the agent to maintain memory on the user's behalf through an active start-to-stop tool lifecycle. Parallel ProactEgoMem-Daily and ProactEgoMem-Sci tracks contain 300/100 clips covering daily and scientific use cases, paired with 1000/500 questions in ProactEgoMem-QA, which measures the quality of the proactively acquired memory. Across proprietary, open-source, video-language, and streaming baselines, even the strongest models fail to capture memory both timely and accurately. ProactEgoMem provides a rigorous evaluation foundation for proactive multimodal assistance and for video agents that co-exist with their users.
Oct 21, 2026

Remembering Through Change: Provenance-Preserving Hypergraph Memory for Multimodal Agents

Long-term memory for multimodal agents remains challenging, as it must preserve fine-grained visual evidence while tracking entity evolution across sessions. Existing abstraction-based memories compress images into text, often discarding visually discriminative details, whereas pixel-preserving memories retain raw observations but struggle to reliably associate diverse observations with persistent entity identities and track their evolving states. To address these limitations, we propose MHG-Mem, a multimodal hypergraph memory that jointly organizes entity identity, state evolution, and provenance to visual evidence. Specifically, MHG-Mem represents distinct entity mentions and their observed facts as individual nodes, grouping identity-consistent mentions and facts through occurrence hyperedges. It then synthesizes aspect-specific evolution states from these grouped observations and links them to supporting entities, facts, and source evidence through evolutionary and evidential hyperedges. To navigate this structured memory, we introduce hypergraph-based agentic search, which adaptively selects an entry layer, traverses typed hyperedges across memory levels, and inspects source observations when fine-grained verification is required. These designs support both detailed visual verification and reasoning over cross-session state changes. Extensive experiments across three benchmarks demonstrate the effectiveness of MHG-Mem, improving performance by 8.20-9.98% over the strongest baseline.
Oct 19, 2026

ProMemAgent: Long-Horizon Proactive Assistance with Context-Aware Prospective Memory from Sensory Perceptions

Large language model (LLM) agents are moving beyond reactive responses toward proactive assistance that anticipates user needs without explicit requests. However, existing proactive agents primarily address immediate needs, while many everyday situations involve delayed intentions that can only be acted on hours or days later. Humans handle such intentions through prospective memory, the ability to remember to act on an intention when the right moment arises. In this paper, we introduce ProMemAgent, the first proactive agent to incorporate prospective memory over everyday sensory contexts for long-horizon proactive assistance. ProMemAgent organizes past sensory perceptions (e.g., egocentric video and audio) into context-aware memory, generating prospective cues and linking earlier events with subsequent developments for future retrieval. Given the current context, it retrieves relevant past events and performs memory-augmented proactive reasoning to determine whether assistance is needed. We further introduce CPMBench, the first benchmark for evaluating long-horizon proactive assistance over sensory contexts, comprising 1,000 instances across eight everyday categories. Extensive experiments show that ProMemAgent achieves the best memory retrieval performance and consistently outperforms all baselines on long-horizon proactive assistance.
Oct 19, 2026

REM: What to Store, When to Recall, What to Forget in Experience Memory for Coding Agents

Large language model (LLM) agents now autonomously complete long-horizon tasks, such as repository-level coding, through hundreds of think-act steps, yet the experience each run produces is rarely reused on the next. Prior memory systems concentrate on retrieval, finding the most relevant past trajectory. Retrieval cannot observe the running agent, so it cannot decide whether the agent needs an experience, at which point, or for how long. We introduce REM (Reusable Experience Memory), a framework that manages the memory lifecycle from inside the agent's think-act loop through three explicit decisions. What to store: each completed trajectory is consolidated into a phase-structured document, two orders of magnitude smaller than the trajectory. When to recall: the document is injected at the start of the task; the costlier implementation record is withheld until an in-loop gate detects the agent struggling. What to forget: the record is evicted after a single exposure. On repository-level bug fixing (SWE-ContextBench Lite), REM retrieves the related trajectory more accurately than every state-of-the-art memory system (68.7% vs. 55.6% match@1) and improves, in every replicate, end-task resolution (27.6% vs. 24.9%) at 17% lower cost. Injecting the same experience as a summary or raw trajectory, even when oracle-retrieved, does not. Ablating any of the three decisions reduces resolution. Altogether, these results demonstrate that the bottleneck in experience reuse is not retrieval fidelity but how experience is stored and governed across its lifecycle, opening a control-theoretic perspective on agent memory.
Oct 19, 2026

Procedural Memory for Language Agents: A Neurosymbolic Perspective on Explicit Goal Structure

Large language models remain unreliable on long-horizon tasks requiring procedural reasoning. We argue that a key cause is the absence of explicit procedural memory: accessible, modifiable knowledge of how tasks are accomplished, distinct from semantic and episodic memory. Goal-Oriented Graphs offer such a representation, encoding goals and prerequisite dependencies as inspectable symbolic structure. We examine their construction, the challenges they pose, and principles for integrating them with neural reasoning.
Oct 18, 2026

MemDerive: A Diagnostic Benchmark for Agent Memory over Evolving Data

Long-running agents rely on memory of their past interactions for task state, such as what has been completed and which conditions still hold. Such state is usually a derived state. No record states it, and it must be computed by rules from multiple records of an evolving history. Existing memory benchmarks score only the final answer, with no reference for the intermediate states behind it. A wrong answer therefore cannot be traced to the state that was missed, and a state that silently became outdated goes undetected. We present MemDerive, a diagnostic benchmark for agent memory over evolving data. It specifies each scenario symbolically, derives exact gold answers with Datalog, records the gold derivation DAG and the supporting events of every query, and renders the history in natural language with fictional entities and distractors. Its 10 scenarios contain 4,692 events and 1,503 queries whose difficulty varies along access, evolution, and composition. On this ground truth, MemDerive evaluates answer reliability, diagnoses failures by probing the nodes of the gold derivation DAG, and tracks whether answers stay correct as events arrive. Our evaluation of four memory systems reveals failures that final-answer benchmarks hide. On derived state, every memory system falls behind simple BM25 retrieval, although the same answer model reaches 96.01% when given the supporting events. Most failures are ungathered, as a system holds the missing intermediate state but does not retrieve it for the question that needs it. Memory systems also rarely propagate implicit changes, which no new record states. These results suggest three principles for memory design. Gather inputs along the derivation, store rules with their versions, and maintain derived states through recorded dependencies.
Oct 18, 2026

Pre-Query Retention with Bounded Bit and Word Retrieval

An agent can retain information before receiving a future question and later retrieve evidence from an archive. Evaluating this arrangement requires accounting for both retained information and the width of each retrieval response. Decision-tree capacity bounds describe individual sets of distinguishable records, but a memory writer must encode every possible record before the query is known. We study fixed-length retention beside an immutable binary archive, with a worst-case limit on raw bit or word reads. We characterize feasible one-bit-read memory cells and construct encoders that partition the complete record space. Supporting pairwise exclusive disjunction and conjunction with one bit read is equivalent to supporting every Boolean query. For multiple reads, we combine explicit encoders with decision-tree counting and an entropy converse. The word-read bounds differ by at most two retained bits when the read budget is at most half the archive length. Under an explicit condition on word width and archive length, raw-word caching attains the exact optimum among all writers. A related condition preserves this optimum under positive average error. Exhaustive checks validate the implementations. In a matched dialogue-agent study, a categorical sufficient statistic preserves source decisions with less storage and lower decoding latency than the universal encoder. A catalogue-specific index reduces private state further and requires additional shared storage. The results characterize how response width and future query structure determine retention requirements.
Oct 15, 2026

Spatial Memory by Agents, for Agents

Spatial memory enables robots to reuse past observations for localization, navigation, and question answering. Designing such memory involves jointly deciding what to retain and how to retrieve it for diverse semantic, metric, and temporal needs. We investigate whether coding agents can automate this design process through iterative implementation and evaluation. Under a fixed development budget, a Designer Agent writes and revises code for memory construction and retrieval using feedback from a fixed Query Agent. The resulting implementations are frozen before building memories from held-out observation histories, without access to downstream questions, and evaluated across five complementary task tracks using the same Query Agent. Across three independent design searches, Codex / GPT-6 Astra averages 44.23 on the equally weighted five-track score, versus 29.32 for ReMEmbR, the strongest evaluated baseline supporting all five tracks, a 50.9% relative improvement. Qualitative analysis relates performance differences to evidence retention and retrieval, while identifying grounding and evidence-use failures. These results demonstrate the potential of coding agents to automate spatial memory design, while revealing task-dependent trade-offs in performance and computational cost. Project page: https://ba-fa-3344.github.io/.
Oct 15, 2026

Multimodal Filesystem Memory For Long-Horizon Embodied Agents

Agents operating over long horizons need an effective memory that allows them to reuse their experience throughout long interactions. If the entire history of an interaction is retained, it becomes difficult to find the relevant experience, while compressing it into summaries may result in the loss of visual and spatial details that are required later on. We present MFM, a multimodal filesystem memory architecture that keeps complementary types of agent memory. Episodic memory stores the observations, actions, and outcomes, and spatial memory associates experiences with locations. Semantic and procedural memory build up general knowledge and reusable methods of acting, and working memory holds the current plans. MFM makes use of searchable textual records to connect these different representations to the underlying multimodal episodes. The agents are able to find previous experiences by means of contextual cues and to examine the original observations in order to recover details that are missing from their textual descriptions. Through consolidation, the agents convert experience into higher-level knowledge and procedures while still keeping references to the original episodes. In the case of long-horizon Minecraft and computer-use tasks, MFM leads to improved performance with three base models. With GPT-6-Astra, MFM completes Mine Diamond from Scratch and reaches 16 out of 24 milestones on the Ender Dragon task, as against 12.7 for the best baseline. On CUABench-KiCad it attains a mean reward of 0.440, as compared to 0.400 for the best baseline and 0.267 in the case of no persistent memory.