Agent Memory Management

Personalized presentation generation requires more than conditioning on a current prompt or template: agents must preserve stable user preferences across tasks, retain newly introduced preferences and constraints during multi-turn revision, and carry out local edits reliably. We propose MemSlides, a hierarchical memory framework for personalized presentation agents that separates long-term memory from working memory and further divides long-term memory into user profile memory and tool memory. User profile memory stores intent-conditioned profiles for round-0 personalization, working memory carries active preferences and session constraints across revision rounds, and tool memory stores reusable execution experience for reliable localized editing. MemSlides pairs this memory design with scoped slide-local revision, so targeted updates act on the smallest affected region instead of repeatedly regenerating the full deck. In controlled experiments, user profile memory improves persona-alignment judgments on a multi-persona, multi-intent profile bank, tool-memory injection improves closed-loop modify behavior in diagnostic matched-pair settings, and qualitative cases illustrate working memory's ability to carryover preferences. Taken together, these results suggest that effective personalization in presentation authoring depends on separating persistent user profiles, session-level working memory, and reusable execution experience across generation and localized revision.

A personalized AI agent needs a user memory: a persistent model of who the user is, built across many conversations and consulted on each new one. Today this memory is almost always stored as unstructured text, a knowledge graph, or a flat store of facts, and consulted by retrieval -- fetching the entries most similar to the current request. Such "bag-of-facts" memory recalls individual facts well, but because storing a fact and acting on it are separate steps, it struggles to resolve contradictions, aggregate over many records, or enforce rules. We argue that user memory should instead be executable. We introduce User as Code (UaC), a paradigm in which an agent's model of a user is a living software project: typed Python objects hold the user's state and ordinary Python functions encode the rules that govern it, so representing and reasoning about the user happen in one medium an interpreter can run. The enabling mechanism is a two-phase pipeline: an append-only log that never discards a fact, periodically checkpointed into typed code. This changes what memory can do. On standard long-term conversation benchmarks, UaC matches both a full-context upper bound and the strongest prior memory systems on recall (78.8% on LOCOMO). Its advantage emerges where representation matters most. On aggregate questions over a user's history -- "how many international trips did I take last year?" -- retrieval-based memory collapses (6-43%) while UaC stays near-perfect (99%), because the answer is a one-line computation over typed state rather than a search over text. And because its rules execute deterministically whenever the state changes, UaC can surface unsolicited, safety-critical alerts -- such as a newly prescribed drug that conflicts with an allergy recorded months earlier -- a capability query-driven memory cannot provide.

Long-horizon agents rely on memory mechanisms to compress interaction history, but optimizing memory writing faces a distinct credit assignment challenge: a memory update may be rewarded or penalized due to downstream tool failures, noisy observations, or reasoning errors rather than its own contribution. We propose HiMPO, a Hindsight-Informed Memory Policy Optimization framework for assigning less-entangled credit to memory-writing actions in long-horizon agents. HiMPO first estimates the local utility of a memory update by comparing the task-relevant information recoverable from the previous and updated memories under the same pre-write state. It then uses hindsight relevance as a bounded retrospective filter that attenuates memory credit when local utility is not supported by the target outcome. The resulting memory-specific advantage is applied only to memory tokens, while trajectory-level rewards optimize the rest of the agent's behavior. Across judge-based open-domain tasks and objective compressive-memory QA, HiMPO improves over strong memory-based and RL-based baselines while preserving compressed-context efficiency. Controlled interventions and live replay studies further show that HiMPO reduces blame leakage from tool-induced errors, assigns memory credit that aligns with the functional impact of memory writes, and remains robust to noisy training targets.

Where an LLM sits in an agent memory pipeline -- between the recall plane that retrieves stored facts (extensively benchmarked) and the control plane that mutates them via supersede, release, purge (largely untested) -- shapes which forgetting failure modes the system recovers. Comparing thirteen system configurations on a 385-case adversarial surface, we observe three placement regimes with partly complementary coverage: deterministic primitives suffice for lexical/temporal categories but fail canonicalization (5% on identifier-obfuscation, 0% on cross-lingual); inscribe-time LLM recovers canonicalization (100%) but cannot help intent-aware deletion (0% on prefix-collision and compound-fact); a mutation-time hook recovers intent-aware deletion (78-85%) and brightens nearly all categories simultaneously (91.7-93.2% overall, $0.17 per 385-case run, 2.3s/case mutation latency vs. 64-191ms/case deterministic, recall path unchanged). We expose the trade-off via ForgetEval, a 1000-case templated suite plus a 385-case adversarial layer (132 hand-crafted + 253 LLM-drafted oracle-validated) scored by deterministic substring match, paired with a six-method Adapter Protocol with honest N/A scoring that lets heterogeneous memory stores enter in 130 lines. Admission is corroborated by 10-annotator IAA (Fleiss' kappa = 0.958) and a 77-case external-authored subset (four blind contributors) that replicates the canonicalization asymmetry and amplifies the joint-placement lift (+27.8 pt). Production failures are predominantly forgetting failures rather than recall failures, yet existing benchmarks measure only recall. ForgetEval and all adapters are released under MIT.

Long-term memory is essential for conversational agents to remain coherent across extended dialogues, follow through on commitments made many sessions earlier, and adapt their behaviour to each user. Current LLM-backed long-term conversational memory, however, is reachability-bounded by the similarity between a query and stored content, both lexical and dense-vector. The approach is effective when query and memory share surface features such as wording or named entities (we call this descriptive). But it misses another, equally valuable class of cases, where query and memory do not share surface features and are tied only by a latent semantic arc (associative). On this regime prevailing long-term memory systems collectively fail. Covering this other half is what allows an assistant, for the first time, to actively draw on past dialogue as a semantic asset. On the memory side, this is the engineering counterpart of what cognitive science calls episodic future thinking: rehearsing past experience for the future contexts under which it will need to be found. We call these write-time rehearsals triggers. We propose T-Mem, the first long-term conversational memory architecture that covers both descriptive and associative recall. At each of two evidence granularities, single facts and full exchanges, T-Mem instantiates one descriptive trigger family and one associative trigger family, so that every memory remains reachable from both surface-similar and relevance-bound queries. As empirical validation, T-Mem reaches state-of-the-art on both LoCoMo and LoCoMo-Plus.

Large language model reasoning leaves no trace once it is done. The steps of a chain of thought disappear when the context window closes, a pruned search branch is just gone, and memory buffers cannot be diffed, merged, or audited. Code, infrastructure, and experiments are all version-controlled. Reasoning is not. GitOfThoughts stores an agent's reasoning tree as a git repository. Every scored thought becomes a commit, scores become notes, outcomes become tags, and retrieval is just git log over the agent's own history. We use this to test something simple. Does giving an agent memory from past problems actually make it more accurate? We tried five memory stores (none, a markdown file, a vector database, a graph, and git) across two benchmarks, two model sizes, and several pre-registered repeat experiments. The answer, on new problems, is no, including one promising early result that did not hold up when we repeated it. Memory only helps once the problem being solved is nearly identical to something already in memory (cosine similarity above about 0.8); below that, it does nothing. In other words, the model is finding the answer rather than learning the method. Even a model 4.5x larger still cannot pull a reusable method out of a worked example; it just gets better at spotting near-copies. The only thing that reliably helped on new problems was generating several answers and picking the most common one (self-consistency). So the case for using git as the memory store is not that it retrieves better. It is that it gives auditability, history, and the ability to merge two agents' memories, at no cost to accuracy.

Graphical User Interface (GUI) agents are increasingly used to automate complex computer tasks across applications, websites, and operating systems. To improve their reliability, recent work has introduced experiential memory, where agents retrieve prior trajectories to guide decision-making in similar states. More recent approaches further extend this idea to visual memory by storing and retrieving screenshots from past interactions, providing agents with richer contextual information than text-only memories. However, the effect of visual memory in GUI agents remains insufficiently understood: it is unclear which failures visual memory mitigates, or which failures it exacerbates. To systematically analyze the effect of visual memory, we introduce a taxonomy of four GUI agent failures (i.e., cognitive failure, visual state misunderstanding, hidden operation blindness, and grounding error) that map to distinct stages of the perception-reasoning-action pipeline. We find that prepending full-image memory has a divergent effect on the failure distribution: it reduces state-level failures but worsens action-level ones, and increases hidden operation blindness and grounding error. Motivated by this finding, we propose Action-Grounded Visual Memory (AGMem), an action-grounded memory framework for GUI agents. The core idea of AGMem is to store image crops that capture the local GUI region closely related to a successful action or a recovery, rather than storing full screenshots. Experiments on OSWorld show that AGMem improves task success rates by 33.3 % over full-image memory. These results demonstrate that AGMem is an effective representation for visual memory in GUI agents.

Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world deployment is inherently dynamic, requiring agents to continually align their knowledge, skills, and behavior with changing environments and updated task conditions. To address this gap, we introduce EvoArena, a benchmark suite that models environment changes as sequences of progressive updates across terminal, software, and social domains. We further propose EvoMem, a patch-based memory paradigm that records memory evolution as structured update histories, enabling agents to reason about environmental evolution through changes in their memory. Experiments show that current agents struggle on EvoArena, achieving an average accuracy of 39.6% across evolving terminal, software, and social-preference domains. EvoMem consistently improves performance, yielding an average gain of 1.5% on EvoArena and also improving standard benchmarks such as GAIA and LoCoMo by 6.1% and 4.8%. Beyond individual tasks, EvoMem further improves chain-level accuracy by 3.7% on EvoArena, where success requires completing a consecutive sequence of related evolutionary subtasks. Mechanistic analysis shows that EvoMem improves evidence capture in the memory, indicating better preservation of complete evolving environment states. Our results highlight the importance of modeling evolution in both evaluation and memory for reliable agent deployment.

Large language model (LLM) agents are increasingly expected to operate over long-term interactions, where information from past dialogues must be preserved and recalled to support future tasks. However, as interactions accumulate, the memory store grows without bound and fills with redundant entries that inflate storage cost and degrade retrieval by crowding out the most useful evidence. Furthermore, this is especially limiting on resource-constrained platforms with hard memory budgets, motivating us to formulate storage-budgeted memory management, the task of keeping an already constructed memory store within a fixed budget while preserving information useful for future interactions. To this end, we then propose MemRefine, an LLM-guided framework that, since surface similarity poorly reflects factual value, uses similarity only to propose candidate pairs and defers delete, merge, and preserve decisions to an LLM judge based on factual content, iterating until the budget is met. Across multiple memory frameworks and long-term conversation benchmarks, MemRefine consistently meets target budgets while preserving downstream performance and outperforming rule-based baselines under tight budgets.

Long-running LLM agents accumulate interaction histories far larger than any context window, forcing a standing decision: what to encode deeply, what to forget, and what to retrieve under a fixed memory budget. Production systems answer with semantic similarity or recency -- both mis-specified for the forgetting decision, which is made at consolidation time before the future query is known. We propose a multi-factor memory value function V(m)=\sum_i w_i f_i(m) over seven interpretable factors (emotional intensity, goal relevance, value alignment, self/user relevance, task utility, reliability, and usage history) drawn from cognitive psychology, whose weights are learned from a downstream objective by a gradient-free optimiser, and whose single scalar uniformly controls encoding depth, forget risk, and retrieval rank. We make a methodological point: on LongMemEval, scoring goal relevance against the held-out evaluation question saturates gold-evidence retention at \approx 0.98 -- this measures retrieval, not forgetting. In the realistic blind regime, a learned multi-factor value retains 0.770 \pm 0.011 of gold evidence across 479 usable cases, versus 0.657 for uniform weights, 0.518 for the best single factor, and 0.368 for recency; every paired gap's 95% bootstrap CI is above zero, and a neural network over the same factors ties the linear model. The learned weights are interpretable -- reliability, emotional intensity, and self/user relevance dominate, while query-time goal similarity is correctly down-weighted for the forgetting decision. A controlled synthetic task with planted confounds confirms the learner recovers a separating weighting (1.00 retention) where uniform weighting fails (0.62). The substrate is open-source; all experiments run on a single CPU with no API calls.

AI coding agents often lose project-specific rationale across sessions and may repeat approaches that previously failed. The bottleneck is often not model capability but missing coding agent memory: a durable record of what was decided, tried, and ruled out. We present projectmem, an open-source, local-first memory and judgment layer for AI coding agents, which records development as an append-only, plain-text log of typed events (issues, attempts, fixes, decisions, and notes) and deterministically projects it into compact summaries served through the Model Context Protocol (MCP). When invoked before an edit, a file-scoped advisory precheck returns recorded failures, open issues, and churn for the target file, a design point we call Memory-as-Governance. We evaluate feasibility through an author-run, six-month self-study on two machines, a controlled latency benchmark, and client-compatibility tests. The study contains 3,228 unique events from 27 projects; 56% are issue-lifecycle events, and 86 of 427 distinct issues closed by a recorded fix had at least one failed attempt before the first fix in event-log order. These histories are candidates for later warnings, not evidence that warnings prevented failures. On a synthetic repository, the median analysis time for a 1,500-event log decreased from 42.0 seconds to 79.3 milliseconds, while git subprocesses per check decreased from 1,500 to two and the tested warning output was preserved. The results establish the feasibility of persistent project memory for AI coding agents and motivate a controlled repeat-failure benchmark for measuring whether coding-agent memory prevents repeated failures. Source code is available at https://github.com/riponcm/projectmem.

Large language model (LLM) agents struggle with long-horizon tasks due to their inherent statelessness, requiring all task-relevant information to be encoded in growing input contexts. The resulting degraded reasoning quality, increased inference cost, and higher latency necessitate efficient working memory mechanisms. However, existing approaches either rely on lossy compression or similarity-based retrieval, which often fail to capture temporal structure and causal dependencies required for multi-step agentic tasks. In this work, we present HORMA, a Hierarchical Organize-and-Retrieve Memory Agent that organizes experience into a file-system-like hierarchical structure, where summarized entities are linked to the corresponding raw trajectories, enabling efficient access without losing detailed information. HORMA decomposes working memory into two stages: structured memory construction and navigation-based retrieval. The construction module iteratively refines how experiences are structured by distinguishing between failures caused by missing information and those caused by misleading or overloaded context. The navigation module retrieves task-relevant context by traversing the hierarchy using a lightweight agent trained with reinforcement learning to select minimal yet sufficient context, thereby reducing latency along the critical execution path. Across ALFWorld, LoCoMo, and LongMemEval, HORMA improves task performance under constrained context budgets while requiring at most 22.17% of the baseline token usage in long conversation tasks. Compared to existing methods, it consistently achieves better efficiency-performance trade-offs and generalizes effectively to unseen tasks.

Large Language Models (LLMs) are increasingly expected to interact with users over long time horizons. However, due to their finite context window, LLMs cannot retain all past interactions, making long-term memory management essential for storing, updating, and retrieving historical information beyond the context limit. Although recent memory systems attempt to address this issue by storing historical information externally, existing approaches suffer from three key limitations: flat text-based memory organizations fail to capture explicit relations among memories, structured memory systems often destructively overwrite evolving facts, and current retrieval mechanisms remain query-agnostic and passive when evidence is incomplete. REAL constructs long-term conversational memory as a temporal and confidence-aware directed property graph, where each atomic fact is represented with entities, relations, valid-time intervals, confidence scores, and exploration intent labels. During memory construction, REAL adopts a non-destructive temporal update strategy that preserves parallel fact versions and their validity intervals, enabling faithful tracking of fact evolution. During retrieval, REAL anchors query-relevant root entities, decouples their exploration intents, and performs semantic evaluator-guided hybrid beam search to extract compact memory subgraphs. It further incorporates counterfactual inference to repair unreliable retrieval states and recover missing memory evidence through implicit logical relations. Comprehensive experiments demonstrate that REAL substantially improves long-term memory performance over flat-text, graph-based, and existing memory baselines, achieving an average improvement of 22.72%.

Long-term LLM agents need persistent memory that can track changing facts and provide relevant evidence across sessions. Existing memory systems often store observations as isolated records, summaries, or indexed fragments, which makes evidence aggregation, fact revision, and memory maintenance difficult. We propose Infini Memory, a maintainable text-based persistent memory architecture that treats agent memory as topic-structured documents. Each topic document serves as a semantic unit for collecting related evidence, preserving metadata, and revising facts over time. New observations are first staged in a buffer and periodically consolidated into coherent textual contexts. At inference time, an agentic retrieval procedure lets the LLM read memory through iterative tool calls rather than a single retrieval step. On MemoryAgentBench, Infini Memory achieves 64.7% overall score. Ablations show that topic-structured maintenance and iterative evidence inspection improve complementary aspects of long-term memory use.

Long-horizon language agents accumulate observations, reasoning traces, and retrieved facts exceeding context windows, making memory retention a fundamental resource-allocation problem. Existing systems treat retention as local and do not model long-term consequences under observability constraints. To fill this gap, we formulate memory retention as a constrained stochastic optimization with budget feasibility, evidence utility, and delayed costs including miss, reacquisition, and stale penalties. We show this multi-step problem is NP-hard, making exact solution intractable. Moreover, deployment decisions must be made under partial observability. To address these challenges, we propose OSL-MR (Observability-Safe Learning for Memory Retention), a learning-augmented framework that enforces a strict separation between online-observable features and offline-available supervision. OSL-MR combines an evidence learner trained from realized evidence with a Mixed-Score heuristic that serves as a deployable online-safe baseline and an inductive prior. The policy learns query-conditioned evidence from interaction data and remains deployable under the same constraints. Experiments on LoCoMo and LongMemEval show OSL-MR outperforms recency-based, Generative Agents-style, and other heuristic baselines, especially under tight budgets. The Mixed-Score prior improves precision and recall, and sensitivity analysis shows robustness across cost settings. On small solvable instances, single-step optimization is insufficient to anticipate future demand shifts, while OSL-MR stays significantly closer to the dynamic-programming optimum, confirming the necessity of the sequential formulation and reinforcing our learning-guided approximation. These results establish constrained stochastic optimization and optimization-guided learning as a principled foundation for memory management in long-horizon agents.

Memory is essential for enabling large language model (LLM) agents to handle long-horizon reasoning tasks. Existing memory mechanisms are largely centralized, typically organizing retrieved information and interaction history within a single model context. This design imposes a fundamental trade-off: scaling reasoning trajectories risks context overload, whereas aggressive content pruning may result in irreversible information loss. Seeking a better trade-off, we draw inspiration from human cognitive systems, especially the functional complementarity between the prefrontal cortex (executive control) and the hippocampus (memory management), suggesting that such a trade-off need not be inherent, but may instead stem from centralized memory organization. To this end, we propose ActiveMem, a heterogeneous framework that decouples agent memory from the core reasoning process. Specifically, a high-level Planner utilizes distilled semantic gists to execute reasoning, while a lightweight, distributed memory system operates in parallel to actively accumulate and consolidate these gists throughout the task. Experiments on BrowseComp-Plus and GAIA show that ActiveMem achieves state-of-the-art accuracy with significantly reduced overhead, demonstrating the effectiveness of distributed active memory for long-horizon reasoning.

Language-agent "memory palace" systems anchor each memory to a world coordinate, on the intuition that geometry adds something text cannot. We make that intuition testable and report three results. First, the memory-palace default of folding spatial proximity into a linear blend beside recency and importance does not help and can hurt: in a pre-registered recall experiment the shipped blend fails its own frozen test (mean Delta-Hit@5 -0.0375, Wilcoxon p=0.306), sitting at a position-blind baseline, while a geometry-led weighting wins decisively (+0.3208, p<10^-15): geometry must lead recall when the query regime is spatial. Second, memory recall and visibility must be separated: recall is occlusion-blind by design (you correctly remember the next room behind a wall), while visibility is a perception predicate over stored geometry that the live system never computed. A one-line ray-versus-voxel digital differential analyzer (DDA), re-pointed from the gaze ray the agent already casts, supplies it: text and the live FoV cone both score 0.000 on 849 behind-wall targets while cone-plus-DDA reaches 0.982 (exact McNemar p<10^-6); coordinate recall separately resolves near-duplicate locations a cosine null cannot (1.000 vs 0.533, n=150). Third, the visibility predicate is confirmed live under a git-committed pre-registration (SPMEM-OCC-LIVE-v1: eight scripted worlds, automated oracle scoring, 96 behind-wall targets, false-visible 1.000->0.000, pooled exact McNemar p=2.5x10^-29), a run that surfaced and fixed a real relay anchor defect. We concede that occlusion-needs-geometry is near-tautological; the contribution is the measurement and isolation, separating what spatial memory must store from how it is read. These pilots power a frozen confirmatory study (SPMEM-ZERO-REAL-PREREG-v1); the full human-authored multi-world study with blind raters remains future work.

Foundation-model agents are increasingly long-lived systems that remember users across interactions, making memorization an explicit deployment-time function rather than solely a property of model weights. Existing work addresses parametric memorization or audits fixed memory configurations, but does not characterize how memory-design choices jointly shape personalization utility, extraction risk, and deletion fidelity. We study this surface as deployment-time memorization, formulating agent memory as a privacy-utility frontier measured by Personalization Recall (PR) and Adversarial Extraction Rate (AER), and sweeping three memory-design knobs: summarization aggressiveness, retrieval breadth (k), and deletion mode. We further introduce the Forgetting Residue Score (FRS) to quantify whether deleted information remains recoverable from derived memory tiers. On LongMemEval, key-fact summarization reduces canary extraction by 76% on Gemma 3 12B and 64% on GPT-4o-mini while preserving nearly all personalization recall; critically, once content is compressed away, increasing k no longer restores leakage. The same compression, however, induces a deletion-fidelity failure: raw-only deletion leaves derived summary copies recoverable in approximately 20% of instances, and only full-pipeline purge or tombstone redaction drives worst-tier residue to zero. Together, these results establish that persistent agent memory must be evaluated as a first-class memorization mechanism -- assessed by what it helps agents recall, what it makes extractable, and what it can truly erase.

Long-term memory for an LLM agent is more than retrieving the right passage at the right time. Current memory systems collapse belief revision, causal coupling, and cross-domain abstraction into a single retrieval surface tuned for surface recall, and consequently struggle on implicit personalisation that requires reasoning over how a user has evolved. We propose DCPM, which reorganises agent memory along a cognitive capability hierarchy ascending from raw inputs and atomic facts, through diachronic belief trajectories and identity, to domain schemas, latent intentions and cross-domain patterns. The hierarchy is driven by two processes inheriting the architectural split of dual-process theory: a synchronous daytime writer (System1) that records belief revisions as doubly linked supersedes chains, and an asynchronous nighttime engine (System2) that induces schemas and intentions and sweeps for cross-domain collisions abstracted into higher-level core schemas. On LongMemEval, PersonaMem and PersonaMem-v2, enabling System2 contributes most where the benchmark rewards implicit cross-session inference (up to +5.20 on PersonaMem-v2) and least on span recall, matching the architectural prediction.

Modern large language model (LLM) agents can use external tools to help users solve complex tasks. However, for problems that require learning from long-term historical events or from previous agent-environment interactions, LLM agents are required to use memory mechanisms to store and retrieve experiences. While sophisticated memory systems exist for dialogue agents, few studies have empirically examined how to improve agents' tool-using capabilities through past user-agent conversations. We propose MemToolAgent, a framework that improves tool use through memory management. Our approach contains a memory extraction module that processes past experiences into structured memory entries, and a retrieval module that dynamically selects a subset of the stored memory entries. This enables more personalized and accurate responses aligned with user preferences and feedback without requiring LLM fine-tuning. In summary, this work has three main contributions: (1) a unified memory entry format that improves both general-purpose and personalized tool use without LLM fine-tuning, (2) a reflection-based memory extraction that uses environment and user feedback to distill wrong executions into critiques to store, and (3) a retrieval module that chooses how many past experiences to use based on the memory similarity distribution. MemToolAgent achieves 29%, 80%, and 17% relative improvements compared to strong baselines on the WorkBench, NESTFUL, and PEToolBench benchmarks, respectively.

Memory is the key component for transforming a stateless LLM into a persistent, evolving agent through experience accumulation, long-horizon planning, and continual self-improvement. Existing memory systems typically take the LLM as the center and design memory operations tailored to a specific backbone. In practice, however, users frequently switch between LLMs, for example using Claude for coding and GPT for writing across tasks, or routing different steps to different backbones within a single task for cost-effective trade-offs. As a result, memory written by one model often needs to be consumed by another. Making upstream memory effectively adapt to and activate downstream LLMs remains a critical yet underexplored problem. To bridge this gap, we shift the perspective from LLM-centric memory design to \emph{memory-centric LLM adaptation}. Specifically, we approach the above upstream-downstream memory adaptation problem from both the write and read sides, and design two profile-conditioned operators that are jointly trained to optimize how memory is stored and presented for better task completion. To ensure the learned operators generalize across a broad set of LLMs, we propose a minimum-gain sampling curriculum that prioritizes the least-served LLMs during training. To better measure the operators' actual contribution rather than the LLM's own capability, we design a performance-gap reward that compares against a naive memory baseline. Experiments on HotpotQA, 2WikiMultihopQA, and MuSiQue demonstrate that our model consistently outperforms baselines and remains robust under unseen-model replacement.

Large Language Models (LLMs) show promise as tool-using agents but remain limited in long-horizon tasks that require remembering, organizing, and reusing knowledge. Prior memory approaches aim to resolve the situation, but mainly focus on storing factual information. Recent work on procedural memory improves task reuse, yet often reduces to replaying past successes without addressing failure cases or online scalability. We introduce a unified and automatic memory framework that integrates semantic, episodic, and procedural memory in a bi-level design combining short-term and long-term stores. A multi-agent architecture with actor, memory, and critic agents enables automatic memory generation, reward annotation, and adaptive retrieval. Long-term memory is managed through reward-based evaluation, merging, and pruning, ensuring scalability and continual improvement. Experiments across various environments show that our approach improves robustness and success on long multi-turn tasks compared to existing baselines. This work highlights the importance of comprehensive, adaptive memory for advancing LLM-based agents.

LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories. Realizing this at scale requires agents to persistently store, retrieve, and update their own memory across sessions. A rich ecosystem of agent memory systems has emerged spanning flat retrieval, LLM-mediated extraction, consolidating fact stores, and agentic control flows. Yet, their system-level behavior remains uncharacterized. We present the first systems characterization of agent memory. First, we introduce a system-oriented taxonomy classifying agent memory systems along four axes. Second, we build a phase-aware profiling harness attributing cost to construction, retrieval, and generation. Third, we characterize ten representative systems across two benchmark suites, uncovering how design choices shift cost across the write and read paths. Finally, we derive 10 system recommendations covering construction scheduling, capability floors, amortization via query volume, freshness-latency tradeoffs, and fleet-scale management.

LLM-based agents increasingly tackle long-horizon tasks with interdependent decisions, where each action reshapes future constraints and intermediate errors can cascade. Existing RAG and agent memory systems organize histories by semantic similarity, retrieving content-relevant entries at decision time. We argue that this design mismatches execution-state dependencies: it fragments decision trajectories and mixes valid and erroneous traces, hindering coherent state reconstruction and error isolation. We propose MAGE (Memory as Agent-Guided Exploration), an active execution-state manager that stores interactions in a hierarchical state tree. The agent derives its state from the active root-to-current path, combining subgoal summaries, recent traces, and hints from prior branches. Four coupled operations maintain the tree: Grow records new traces, Compress summarizes completed subgoals, Maintain validates summaries, and Revise restores a target boundary and resumes on a new branch. This design bounds context growth while preserving state integrity and isolating flawed segments from the active path. Experiments on MemoryArena show that MAGE improves the average task success rate by 7.8--20.4 pp over baselines, while reducing token consumption by 55.1%.

Long-term memory enables language model agents to support personalized interactions, but it remains unclear when available memories warrant integration into responses. Existing memory evaluations emphasize retrieval accuracy and downstream task utility, while overlooking whether retrieved sensitive memory content is warranted in the current turn. We introduce RBI-Eval, a controlled measurement study built around a probe set that compares model behavior with and without access to sensitive memory under identical benign prompts. We evaluate four base LLMs against a matched no-memory reference across four memory-access settings: full-context exposure and three retrieval systems. Our results reveal substantial behavioral divergence. With memory available, the separation score for sensitive-memory integration decreases by 8.9%--26.6% relative to the matched no-memory reference for GPT-5.4-mini, but by 51.1%--82.9% for Claude-Sonnet-4.6, DeepSeek-V4-Flash, and Qwen3.5-9B. Control experiments on DeepSeek and GPT-5.4-mini show this effect is specific to sensitive content, rather than general personalization. Retrieval systems reduce exposure but do not eliminate integration once sensitive memory reaches the generator. These findings suggest safe personalization requires memory-aware decisions at both retrieval and generation time.

Personal AI agents increasingly rely on long-term memory to provide persistent personalization across sessions. However, existing memory pipelines are largely driven by semantic similarity: memory data close to the current query is retrieved and injected into the model context. This creates a critical trustworthiness gap, since a semantically related memory may still be contextually inappropriate, leading to threats such as cross-domain leakage, sycophancy, tool-call drift, or memory-induced jailbreaks. In this paper, we study memory search as a trust boundary in personal AI agents. We evaluate representative agentic memory frameworks, including A-Mem, Mem0, and MemOS, together with OpenClaw, a real-world personal-agent environment with persistent state and tool-use capability. Our results show that long-term memory is not merely a utility layer, but a durable control channel that can reshape how agents interpret tasks and execute actions, leaving them highly susceptible to the aforementioned threats. To mitigate these vulnerabilities, we propose MemGate, a lightweight and deployable memory plug-in for trustworthy memory search, with only 9M parameters and a 35.1MB footprint. MemGate is inserted between the vector memory store and the backbone LLM, requiring no LLM modification, memory-database rewriting, or inference-time LLM judge. It applies a query-conditioned neural gate to candidate memory representations, turning raw similarity search into task-conditioned memory admission. Across multiple mainstream memory frameworks, real-world agent settings, and diverse LLM backbones, MemGate reduces memory-induced threats while preserving long-term memory utility.

Despite recent progress, LLM agents still struggle with reasoning over long interaction histories. While current memory-augmented agents rely on a static retrieve-then-reason paradigm, this rigid pipeline design prevents them from dynamically adapting memory access to intermediate evidence discovered during inference. To bridge this gap, we propose MRAgent, a framework that combines an associative memory graph with an active reconstruction mechanism. We represent memory as a Cue-Tag-Content graph, where associative tags serve as semantic bridges connecting fine-grained cues to memory contents. Operating on this structure, our active reconstruction mechanism integrates LLM reasoning directly into memory access, allowing the agent to iteratively explore and prune retrieval paths based on accumulated evidence. This ensures that memory retrieval is dynamically adapted to the reasoning context while avoiding combinatorial explosion caused by unconstrained expansion. Experiments on the LoCoMo benchmark and LongMemEval benchmark demonstrate significant improvements over strong baselines (up to 23%), while substantially reducing token and runtime cost, highlighting the effectiveness of active and associative reconstruction for long-horizon memory reasoning.

Long-horizon agents can archive large histories, but future answers still incur retrieval, rereading, and context costs. When retained memory misses answer-relevant evidence, the system must return to larger portions of the raw history. We study budgeted evidence survival: before the query is known, which source evidence should be retained so that it remains recoverable and usable under a fixed retained source-evidence token budget? We instantiate this setting as Budgeted Pre-Query Retention, where memory is written during ingestion and later read without access to the full raw stream. We introduce EMBER, a learned retention policy that constructs a compact, source-backed evidence state. EMBER stores evidence capsules: verbatim source excerpts paired with retrieval keys and update metadata, preserving both grounding and read-time access. Post-query outcome feedback trains the writer to preserve evidence across the ingestion-retrieval-answer chain. On LongMemEval-RR, our LongMemEval-derived retained-evidence protocol, EMBER-14B reaches 0.3017 F1 at the 8192-token retained-evidence comparison point, compared with 0.1765 for the strongest non-EMBER budgeted baseline. Across retained source-evidence budgets, EMBER improves F1, Retain-Recall, and Read-Recall, indicating that long-horizon memory depends on retaining evidence within the budget rather than rereading larger histories.

Large language models (LLMs) have enabled powerful software engineering (SE) agents capable of navigating complex codebases and resolving real-world issues. However, these agents remain fundamentally episodic: they fail to retain, refine, and reuse experiences across tasks, repeatedly reconstructing context from scratch and reproducing similar mistakes. Even with memory support, they offer no remedy for the absence of a principled, task-agnostic \textit{memory utility}, making them difficult to evaluate rigorously or generalize across agents and settings. To tackle these limitations, we introduce \ours, a closed-loop framework for memory augmentation in SE agents. \ours grounds memory utility in \textit{validated downstream impact}, establishing utility as both a task-agnostic \textbf{evaluation benchmark} and an annotation-free \textbf{optimization signal}. Through complementary evaluation on \textit{single-episode} and \textit{cross-episode} memory augmentation, results demonstrate that \ours consistently improves SE agents across settings, achieving absolute gains of up to $\uparrow5.25\%$ in success rate and $\uparrow4.63\%$ in resolve efficiency, while substantially reducing computational cost by $\geq9.79\%$. Our project page: https://xhguo7.github.io/MemOp/.

RAMPART is a compile-time memory model and pure in-RAM block registry for LLM-based agents. Context assembly is a programmable runtime operation where content is compiled from a structured registry under explicit policy for ordering, inclusion, and eviction. Five composable primitives (promote, gate, write, evict, rollback) act on named addressable blocks before compilation at zero prompt-token cost. Provenance tags and non-evictable authorship flags implement a permissioned memory model with block-level ownership. Controlled probes with Qwen3-8B Q4 show that compile-time placement and the structural relationship between blocks and the task query affect task success, with the cliff falling at roughly the seventh block position when the task follows the registry and the twelfth when it precedes. Grouping the critical block with content-adjacent neighbours and promoting the group as a unit lifts task success by tens of percentage points at positions where single-block placement fails. Cross-model replication on Qwen2.5-7B, Llama-3.1-8B, Mistral-7B-v0.3, and Qwen3-14B shows the content-priming effect appears at the same absolute positions across families, with magnitude varying with model strength. Block grouping raises Mistral's mean pass rate roughly fivefold at the hardest registry size, and a smaller model with the intervention can outperform a larger model without it in the mid-registry zone. Relevance gating reduces prompt cost by 67.8% while recovering 83% of the promoted-condition success rate. Schema eviction produces 0% invocations against 100% with the schema present, a property policy-based approaches cannot guarantee by construction. Shared-registry coordination reduces inter-agent communication to a method call at zero coordination token cost.