Persistent Memory for Language Models

Follow this topic Ask about this topic

Momentum

35 papers in the last four weeks, up 400% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 190

Oct 8, 2026cs.CL

DPPM: Dual-Path Parametric Memory for Personalized Language Models

Long-term personalization requires language models to use interaction history to track users' preferences across sessions. Parametric memory encodes this interaction history into model parameters or adapters, reducing the need to include it in the inference context. However, independent context compilation leaves cross-session integration unspecified, while recurrent updates can attenuate earlier evidence. To address these challenges, we propose Dual-Path Parametric Memory (DPPM). Its Evidence path directly pools representations of the interaction history to preserve earlier evidence, while its Delta path sequentially updates an associative state to capture changes. Fusing both outputs produces history-conditioned LoRA adapters that combine evidence accumulation with ordered revision. Across multiple backbones, DPPM outperforms the evaluated baselines, achieving 54.22% on PersonaMem-v2 and 86.79% on PrefEval. These results suggest that DPPM provides a simple and effective design choice for cross-session personalized parametric memory.

Yuhao Chen, Shuochen Liu, Jiayao Shi +7

University of Science and Technology of China · iFLYTEK Research Group

Memory-Augmented Language Models Persistent Memory for Language Models Personalized Language Models Parameter-Efficient Fine-Tuning

Oct 8, 2026cs.LG

TraceRelay: Attention-Aligned Recurrence over Rolling Traces

We present TraceRelay, an attention-aligned recurrent architecture that distributes persistent representations over a rolling sequence of low-dimensional traces. Local right looking attention forms increments from lower-layer representations; delivery is delayed until all attended inputs are in the causal past. A fixed additive phase recurrence accumulates the delayed increments, and left-looking attention reads the resulting residual augmented stream. A stride-wise prefix sum supports parallel prefill and bounded-buffer continuation. We study 36 small-model runs on Equal Repeats, bounded Dyck closing-type prediction, and causal Most-Freq generation, using three seeds per setting. At trained length 256, Equal Repeats models with recurrent phase inheritance reach 98.81-99.69% accuracy versus 50.73-51.63% for separately trained variants without inheritance, despite the latter receiving more updates. Accuracy drops sharply at lengths beyond the training range. At the longest evaluated lengths, models with more dimensions in the middle layer's recurrent traces perform better on Dyck (76.34% versus 55.49% close accuracy at length 4096), whereas models with fewer trace dimensions perform better on five-symbol Most-Freq (70.74% versus 55.60% exact generation at length 1024). These contrasting cases motivate further study of how the size of recurrent representations should be chosen for different tasks, without establishing a general rule across tasks or model configurations.

Sungwoo Goo, Hwi-yeol Yun, Sangkeun Jung

College of Pharmacy, Chungnam National University · Department of Computer Science & Engineering, Chungnam National University

Sequence Modeling Persistent Memory for Language Models Recurrent Transformers Attention Mechanisms Length Generalization

Oct 8, 2026cs.AI

Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies

The memory capabilities of Large Language Models (LLMs) have garnered increasing attention recently. Despite great success achieved, existing retrieval-based memory approaches typically overlook the differences between memories and employ a unified strategy to process all memories, leading to suboptimal performance. Thus, an intuitive question arises: can we categorize memory into different types and select appropriate strategies? However, given the topic-rich, scenario-complex, and boundary-blurred nature of memory scenarios, achieving precise classification of memories is not easy. To address this challenge, we propose a memory multi-class dataset in this paper, termed TriMEM, which provides precise annotations for memory types across diverse scenarios. Building upon this foundation, we propose a novel memory framework, named MemoType, which can adaptively recognize each memory and query type with the learned router model. With the memory and query routing, MemoType can retrieve the memory with corresponding query types and design tailored retrieval strategies, thereby enhancing the retrieval performance. Moreover, we theoretically prove that any single retrieval strategy is subject to a fundamental upper bound on its expected retrieval precision in multi-class corpora, leading to systematic precision degradation. Extensive experiments on three datasets demonstrate that MemoType consistently outperforms existing methods, achieving up to 16.18% improvement in Recall@1.

Yi Wen, Derong Xu, Pengyue Jia +8

City University of Hong Kong · Huawei Noah’s Ark Lab

LLM Agent Memory Persistent Memory for Language Models Classification

Oct 8, 2026cs.AI

What to Admit and How to Present: Governing Persistent Memory in LLM Agents

Persistent memory can improve personalization in LLM agents but can also induce sycophancy and cross-domain leakage. We distinguish two governance decisions: admission, which determines what recalled information enters the working context, and presentation, which determines how admitted information is expressed. We implement two inference-time designs without retraining: factor-compiled admission (FC), which assesses whole memory entries, and permission-semantic admission (PS), which decomposes entries into typed units; both translate adjudicated attributes into eligibility decisions via deterministic policies. We evaluate on a four-backbone development suite and an external benchmark with four tasks of 300 samples each. Relative to verbatim injection, FC and PS reduce pooled judge-assessed failure rates on the external benchmark by 6.7 and 8.8 percentage points (p = 2.7e-7 and 4.1e-12), and development-set cross-domain leakage falls by up to 29.5 percentage points. A query-conditioned gating baseline shows no significant change in objective-fact failure or pooled failure. Under matched admission budgets, PS outperforms random and relevance-based selection on external objective-fact judgment after Holm correction. Holding presentation fixed, tightening admission cuts cross-domain failure by a further 17.5 percentage points (p = 1.6e-4); in contrast, no comparison between two renderings of identical adjudicated outputs survives multiple-comparison correction. Both designs increase personalization failures, and PS misses the preregistered improvement and personalization-preservation criteria. These results support evaluating admission and presentation separately: selection quality provides task-specific safety gains, while preserving beneficial memory use remains unresolved.

Chang Liu, Deliang Ding

Pazhou Laboratory Guangzhou, China

Agent Memory Management Persistent Memory for Language Models LLM Agent Safety Privacy Leakage in Language Models

Oct 7, 2026cs.CL

Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute

A large language model can only use the text that fits in its context window, and it recomputes its internal key-value (KV) state for a prompt every time the prompt is sent. We test a memory layer, the public package galahad-kv, that saves the KV state of each block of about 16,000 tokens to encrypted local NVMe disk and loads it back later, byte-exact, without recomputing it. We ran it on 50,000,000 tokens of real public text, served through vLLM on one NVIDIA H100, with Gemma 4 12B and Gemma 4 31B. Every block we probed was loaded back from the encrypted store with no recompute (100 of 100, at depths from 0 to 50M tokens) on both models. Loading a block was 2.8x to 4.3x faster than recomputing it and used 8.8x to 12.3x less GPU energy, and GPU memory stayed flat over the whole 50M-token stream. Asked about facts planted millions of tokens earlier, the 12B model gave the right answer 82 times out of 100 and the 31B model 98 times out of 100. Neither model made up an answer. The limits are as follows. This is reuse of stored state, not a wider attention window: one block is loaded at a time, and how well a question is answered depends on the model. Writing the memory is a one-time cost, and the store takes terabytes of local NVMe disk. We describe the test protocol, which is built to resist common ways of gaming long-context benchmarks, and give a single-GPU reproduction that uses public software and a free licence for the package.

Sietse Schelpe

Corbenic AI

Persistent Memory for Language Models KV-Cache Reuse LLM Inference Acceleration Long-Context Language Model Evaluation

Oct 7, 2026cs.CL

Cache the Encoder Within:Compact, Reusable Memory across LLM Queries

Repeated queries over shared documents incur redundant encoding, while caching model states introduces persistent storage costs. Building on CoMem's intermediate-state interface, EncBank treats a pretrained LLM's lower layers as a reusable document encoder and compactly stores their outputs for an adapted upper-layer reader. A self-distilled suffix adapter is shared across storage precisions within each backbone, without quantization-specific retraining. Across five benchmark suites on three Qwen backbones spanning different sizes and full-attention and hybrid architectures, 4-bit storage keeps each reported benchmark aggregate within one score point of native-precision EncBank. In a fixed Qwen3-8B workload, it retains 28.1% of the native-precision persistent GPU store. Separate native-precision controls yield a 1.40x selected-pack prefill speedup over same-evidence, same-adapter text replay, at a 3.12-point RULER accuracy cost. A native-precision Qwen3.8-27B configuration also passes 70 of 89 Terminal-Bench 2.1 tasks. EncBank thus combines reusable computation with compact memory, while task fidelity and end-to-end benefits remain dependent on the workload, preparation costs, and reuse frequency.

Hanzuo Liu, Chunyu Liu, Chaofan Lin +2

Tsinghua University

Persistent Memory for Language Models Memory-Augmented Language Models LLM Inference Acceleration

Oct 6, 2026cs.CL

Towards In-Parameter Memory Augmentation for Large Language Models

Recently Large Language Models (LLMs) and LLM-based agents increasingly need to incorporate knowledge acquired after pretraining, e.g., domain facts, user preferences, documents, and interaction experience. In-context learning (ICL) and ICL-based agent harness remain flexible, but they consume context capacity and incur repeated discretized encoding cost that grows with context length. \textbf{In-parameter memory} offers a complementary substrate: reusable memory information is represented in model parameters, adapters, or other parameter-like objects that are composed into the forward pass at inference time. This survey focuses on methods that augment LLMs with such parametric memory at deployment: a memory-bearing parameter object is plugged into the forward pass during inference, whether it is acquired before or during deployment. We organize the landscape with two orthogonal axes: \textbf{Parameter Placement}, which includes Embedding, Attention, FFN layers, or Hybrid when two or more layers are used; and \textbf{Parameter Acquisition Time}, which distinguishes methods whose memory object is acquired during deployment (online) from those acquired before it (offline). We clarify boundaries, conduct comparisons, and discuss open directions in interference, safety, co-design with ICL, and recursive self-improvement.

Haoyu Huang, Zhongwei Xie, Jiaxin Bai +6

The Hong Kong University of Science and Technology · Hong Kong Baptist University

Memory-Augmented Language Models Persistent Memory for Language Models

Oct 6, 2026cs.AI

Persistent Memory in Multi-Agent LLM Inference: What It Costs, What It Buys, and When You Can Tell

Decomposing long-context inference across cooperating agents bounds the active KV cache per call rather than total evidence, which matters when KV-cache memory binds. Many such systems add a persistent tier storing and recalling reasoning traces, usually validated by an ablation reporting an accuracy gain. We measure both on one three-tier agent architecture. Decomposition delivers: peak KV working set of 14.3 MiB per query against 35.5 and 35.3 MiB for single-pass and retrieval-augmented baselines. The persistent tier does not: across eight controlled dataset pairs at n=100 per arm it costs +0.368 MiB [+0.167, +0.590] of peak cache and produces no detectable accuracy change (+0.015, 95% CI [-0.011, +0.046]). We argue the null is structural: single-question benchmarks supply each item with its own evidence and score it independently, and correctness requires resetting stored traces between conditions, so recall has nothing informative to retrieve. Reaching it took four measurement corrections -- three inflating the apparent benefit, the fourth making an effect that size look resolvable -- none visible in the results table. We give the conditions an agent-memory ablation must satisfy and detection procedures that need no knowledge of the specific defect.

Hochan Son, Kyungdoe Han, Jaehan Koh +3

University of California, Los Angeles · University of Wisconsin · HCLTech America

LLM Inference Efficiency Multi-Agent LLM Systems Persistent Memory for Language Models Memory Agent Benchmarks

Oct 6, 2026cs.SE

When Old Facts Return: Re-Reads, Reverts, and the Limits of Temporal Memory

A memory system can retire an obsolete value and later restore it merely because the same old statement appears again. A re-read of an old source and a genuine revert can produce the same observed sequence of values while requiring opposite current answers. We study this ambiguity on 130 extractor-selected atomic transitions derived from software fixes. In the ordinary transition condition, identity-based temporal memory reaches 98.5% model-judged accuracy with zero observed errors under a literal stale-value proxy. Appending a verbatim re-read of the old statement reduces accuracy to 10.8% and raises the stale-value rate to 88.5%. A guard that refuses to reactivate a previously retired value restores accuracy to 97.7% and reduces that rate to 0.8% in this constructed re-read condition. The guard cannot also recognize a legitimate revert without additional change provenance. Two supporting studies examine exposing retired history to the answer model and supplying current source for changed behavior. An exploratory extraction study over 707 software fixes provides scope context, not a universal coverage estimate. The design implication is to distinguish an observation of a value from evidence that the value changed. Selected inputs, aggregate-only answer records, related-family judges and a post-failure guard evaluation limit the conclusions to the retained experiments.

Neeraj Yadav

Called It Inc.

Persistent Memory for Language Models Temporal Consistency

Oct 4, 2026cs.AI

Memory Canonicalization: A Framework and Benchmark for Cross-Model Drift in Persistent LLM Memory

Persistent memory for Large Language Models (LLMs) has matured rapidly: systems such as MemGPT/Letta, Mem0, and Zep now provide agents with tiered, temporally-aware, model-agnostic external storage, while the Model Context Protocol (MCP) standardizes access to memory servers. A less addressed problem is that an identical stored memory object, retrieved by two different LLMs under otherwise identical conditions, may not be interpreted the same way, factually or emotionally. This paper proposes memory canonicalization: a write-time pipeline that detects ambiguity, conditional structure, and emotional loading in a raw memory object and rewrites it into an explicit, structurally disambiguated canonical form, with emotional valence represented as a separate field rather than inferred from tone. We formalize the pipeline, define a companion Cross-Model Semantic Drift / Emotional Consistency Score benchmark (CMSC-E), and report results from a three-arm pilot using 176 synthetic memory objects and three downstream model families. We find an uncorrected improvement in cross-model emotional consistency for fully canonicalized memory relative to raw memory (+0.050, 95% bootstrap CI [0.013, 0.086], paired t-test p = 0.010), but this result does not survive Bonferroni, Holm, or Benjamini-Hochberg correction across the six comparisons tested. None of the factual-drift (CMSD) comparisons reach significance at any correction level. We report these results as exploratory rather than confirmatory and outline needed follow-up work, including larger samples, independent judge models, human-validated rendering, and preregistration.

Amit Vadnere, Aishwarya Lonarkar

Product Solutions Engineer

Persistent Memory for Language Models

Oct 1, 2026cs.CL

Mem++: Non-Destructive Memory for Long-Term Organizational LLM Agents

Large Language Model (LLM) agents now take part in organizational work, where many authors record decisions across documents over months. Because a revised decision arrives as a new document rather than an edit, answering a question requires knowing which version held at a given time. However, most memory systems compress the record at write time. By distilling each document into facts, notes or graph edges, these methods fix what can be answered before any question is asked. To address this, we propose Mem++, a non-destructive memory framework shifting from write-time distillation to read-time selection. Mem++ stores every document whole with its date and author, and it calls no generative model at write time. At read time, it retrieves only documents dated up to the time a question asks about and fuses lexical and semantic rankings. Unlike systems that overwrite older versions, Mem++ keeps them and leaves the choice to the answering model. Evaluations on the organizational benchmark OrgMemBench demonstrate that Mem++ surpasses the strongest memory system baseline by 8.0 to 13.1 points across two answering models. With gpt-4.1-mini, it also achieves the best overall score, 2.6 points above RAG. In addition, Mem++ achieves the best average LLM-judge score on LoCoMo and ranks second on LongMemEval-S, behind only its entity-graph variant. Code for benchmark evaluation is available at https://github.com/AIDAChip-Inc/mem-plus-plus.

Ahmad Yehia, Aly O. Abdelkareem, Islam Ahmed +4

The University of Texas at Austin · AIDAChip Inc.

LLM Agent Memory Persistent Memory for Language Models Question Answering Agent Memory Management Temporal QA

Oct 1, 2026cs.CV

FlashBack: Knowing When to Remember in Streaming Vision-Language Models

Streaming vision-language models must process continuously growing video streams under a bounded compute budget, creating a persistent tension between real-time perception and long-term memory. Retrieving historical information provides a natural remedy, yet historical recall is not uniformly beneficial: unnecessary history may introduce irrelevant context into current reasoning and interfere with native real-time perception. Effective streaming memory should therefore address not only what to remember, but also when and how to access it. To this end, we introduce FlashBack, a training-free framework for selective, multi-level memory in streaming vision-language models. Before retrieving history, FlashBack draws on the semantic understanding of the frozen streaming VLM to infer whether a query calls for historical evidence. This assessment determines whether inference remains on the Native trajectory or invokes an isolated Recall trajectory. The Recall trajectory combines recent context with retrieved long-term memory through a query-local Side-KV pathway, preserving local temporal continuity without modifying the persistent Native state. We instantiate FlashBack on StreamingVLM and Mage-VL-4B and evaluate it on OVO-Bench and StreamingBench. The results show improvements on several long-horizon and memory-dependent tasks while largely preserving real-time perception, with performance competitive with strong training-based streaming methods despite requiring no additional training. Our code will be announced later.

Yi Chen, MingMing Yu, Rui-Qi Wang +5

Rightly Robotics, A4X

Memory-Augmented VLMs Vision-Language Models Persistent Memory for Language Models Temporal Video Understanding

Oct 1, 2026cs.CL

Madeleine: Learning Involuntary Recall for Conversational Memory from Simulated Lives

A long-term conversational assistant must recall the right memory at the right moment, yet the memory that matters most is often not similar to what the user says now. Current systems recover such associations by letting an LLM reason at write or read time, at a cost of hundreds to over a thousand LLM calls per memory bank and up to several thousand context tokens per query. We argue that association is a learnable relevance: the pointwise mutual information of memories under how human lives unfold. We introduce Madeleine, which learns amortized association: offline, an LLM life simulator writes simulated lives, whose cue-trigger pairs teach a query encoder a residual association on top of frozen similarity; online, it calls no LLM and plugs into any vector memory by replacing only the query encoder. On LoCoMo-Plus under the official protocol, Madeleine (I) reaches 66.6 when plugged into HyperMem, the highest among all systems evaluated under this protocol; (II) used alone, reaches the score of HyperMem as released (52.4 vs. 52.9) with zero LLM calls and about 1/21 of its answer context; and (III) lifts T-Mem by 26.2 points, significantly outperforms the same untrained backbone inside both systems, and leaves ordinary QA intact on the 4B backbone.

Zhiyun Shi

Nanyang Technological University, Singapore

Memory-Augmented Language Models Persistent Memory for Language Models Long-Term Conversational Memory Associative Memory

Oct 1, 2026cs.CL

Role-aware Heuristic Episodic Attention for Conversational LLMs

Large language models often lose track of persistent instructions and relevant information as multi-turn conversations grow. We study this cumulative contextual decay through three related failure modes: attention pollution, dilution, and drift. We propose REA (Role-aware Heuristic Episodic Attention), a context-management framework that assigns different persistence and representation policies to instructions and episodic interactions. Instructional Memory retains identified global constraints in a dedicated prefix. Episodic Memory preserves user inputs and compresses model replies, while heuristic retrieval selects raw text, compressed representations, or omission for each historical turn. On Long-MT-Bench+, REA improves the judge score from 6.32 to 7.36 on a 10-point scale, a 16.5% relative gain over the Vanilla baseline, and reduces average latency by 2.91

\times

. Additional evaluations show aggregate gains on three backbones spanning 1.7B-7B parameters and on Chinese and English role-playing tasks. These results support role-aware context management as a practical approach to maintaining conversational continuity and instruction adherence.

Wanyang Hong, Zhaoning Zhang, Yi Chen +5

National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, National University of Defense Technology, Changsha, China.

Memory-Augmented Language Models Long-Context Language Model Inference Persistent Memory for Language Models Long-Term Conversational Memory LLM Context Management

Oct 1, 2026cs.AI

MemFit: Efficient Long-Term Agentic Memory

Long-term memory systems for large language models (LLMs) have gained popularity for extending reasoning capabilities across applications. Current memory systems rely on LLM agents to organize and consolidate memory, resulting in costly, inefficient write operations. To address this limitation, we propose MemFit, a long-term memory system for conversational agents that reduces the cost and latency of memory operations. Unlike existing systems that rely on expensive LLM calls for memory construction or discard surface-level details through compression, MemFit stores each turn verbatim in an append-only store with near-instantaneous, LLM-free insertion, indexing turns with segment summaries rather than replacing them. Additionally, MemFit uses an LLM-free, multi-path retrieval strategy that combines lexical and semantic signals with cross-encoder reranking over caption- augmented episodes in both textual and multimodal settings. Empirical results on three widely used benchmarks, LoCoMo, MemGallery, and LongMemEval-S, show that MemFit achieves state-of-the-art performance while reducing memory construction time and cost several-fold, providing a scalable and efficient solution for persistent agentic memory.

Mitchell Piehl, Muchao Ye

Department of Computer Science The University of Iowa

LLM Agent Memory Persistent Memory for Language Models Long-Term Conversational Memory Agent Memory Management

Sep 30, 2026cs.CL

Working Around the Compute Ceiling: Byte-Exact Memory in Galahad Makes LLM Reading a One-Time Cost LLM Reading a One-Time Cost

A transformer language model performs a bounded amount of computation per token, and recent work by Vishal Sikka, former CEO of Infosys, argues that this bound limits which tasks a model can carry out or verify (arXiv:2507.07505). We ask how much of the budget beneath that ceiling is spent on work the model has already done. Serving is stateless across requests: a model that answers a second question about a document recomputes the document's attention state from the first token. On seven real-world datasets, 98.7% of prompt tokens were text the model had already read. We present Galahad, a memory layer for vLLM, SGLang and llama.cpp that makes this reading a one-time cost. Taliesin saves the model's key-value (KV) state for a block of text and loads it on the next request that contains the same bytes, instead of recomputing it. Blaise keeps the documents themselves and passes the model only the section a question needs. On a recall test with 100 facts hidden in a 97,000-token corpus (Gemma 4 31B), Taliesin alone let the model attend to the whole corpus and answered 98 of 100 on llama.cpp at 3.0 s and 572 J per question, against 10 of 100, 9.3 s and 2,754 J for the same model without Galahad, which could hold only the last 12,000 tokens. With Blaise added, the model read about 668 tokens per question and answered 100 of 100 on all three runtimes at 0.59-0.64 s and 200-213 J; a tuned RAGFlow pipeline answered 77. Storing the corpus is a one-time cost of about 100 s and 28 kJ, whose energy is recovered after 13 questions. Restored state is bit-identical: all 262,144 output logits matched after restart, rehydration and hot-load. Galahad worked with all 30 models we tested under vLLM, and it fails closed: any load that does not pass its checks is recomputed. Together these results move LLM serving from stateless to stateful inference.

Sietse Schelpe

Corbenic AI

LLM Serving Long-Context Language Model Inference Persistent Memory for Language Models LLM Inference Acceleration KV-Cache Reuse

Sep 29, 2026cs.CL

Learning What to Remember: Long-horizon Counterfactual Memory Optimization

Persistent textual memory allows language models to carry information across long interactions, but learning what to remember is fundamentally a credit-assignment problem. A memory rewrite may only become useful many steps later, while much of the observed utility may be inherited from information already stored before the rewrite. We introduce Memory Gain Policy Optimization (MGPO), which isolates the incremental value of each memory rewrite by crediting it for its marginal contribution to current and future downstream utility. This turns delayed memory utility into a direct learning signal for optimizing what information should persist. We study MGPO on document-level information extraction, where structured supervision makes the effects of individual memory updates directly measurable. MGPO improves extraction while reducing average memory length by nearly 80% relative to the initial memory policy before optimization. The learned memory policy also supports reuse and transfer across domains, downstream models without further training. These results show that effective memory learning depends not only on preserving useful information, but on identifying which memory updates create lasting incremental value.

Jiaming Tang, Mingyan Liu, Armin Sarabi

Department of Electrical Engineering and Computer Science, University of Michigan

Memory-Augmented Language Models Persistent Memory for Language Models LLM Memory Policy Learning

Sep 29, 2026cs.CL

Learning to Retrieve Missing Evidence for Long-Term Memory QA

Long-term memory enables language models to use past interactions in future conversations. However, evidence needed to answer a question may be scattered across distant turns, while the question itself omits clues needed to locate it. Retrieved facts can reveal these clues, motivating retrieval decisions conditioned on evidence already found. We introduce MERA (Missing-Evidence Retrieval Augmentation), which separates globally searchable memory from a question-specific evidence state. Verified evidence guides subsequent retrieval without restricting access to the global memory. We train a lightweight planner through reinforcement learning, rewarding queries that recover previously missing evidence. MERA achieves strong answer accuracy across Qwen3-30B and GPT-4o-mini backbones. With Qwen3-30B for evidence processing and answer generation, the trained 0.6B planner achieves 77.40% accuracy on LoCoMo and 71.29% on LongMemEval-S, exceeding a 30B planner without retrieval-grounded training by 4.10% and 3.96%, respectively. On LoCoMo, later retrieval rounds increase cumulative evidence recall from 55.5% to 80.5%.

Yi-Xuan Deng, Yi Zhang, Wei Liu +2

Tsinghua University

Persistent Memory for Language Models Question Answering RL for IR Long-Term Conversational Memory Evidence Retrieval

Sep 29, 2026cs.CL

AMU:Admission and Memory Update for Personalized Conversations---Structured Memory with SLM Guided Control

Large language models (LLMs) have become the foundation of personalized assistants, but maintaining persistent user memory across long-term interactions remains challenging. Existing memory systems often focus on storage, retrieval, or consolidation, while memory writing remains less controlled: transient requests, duplicate statements, and outdated user states may enter memory and later be retrieved for personalization. In this paper, we present AMU: Admission and Memory Update for Personalized Conversations, an SLM-guided (Small language model guided) structured framework for writing-time memory control. AMU uses structured memory filtering to decide what should enter memory and SLM-guided storage management to determine whether an admitted record should be stored separately, discarded as a duplicate, or fused as an update. We evaluate AMU in a controlled memory writing and retrieval setting. Experimental results show that AMU maintains cleaner and more retrievable personalized memories.

Tao Hwang, Yishi Diao

Independent Researcher · Nanchang University

Conversational Memory Persistent Memory for Language Models Personalized Language Models Long-Term Conversational Memory Agent Memory Management

Sep 29, 2026cs.AI

CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory

Long-context reasoning is essential for complex and long-horizon tasks, yet the performance of large language models (LLMs) degrades as context length increases. Recent approaches address this by processing input chunk by chunk while maintaining a bounded textual memory in model context. However, premature information compression can discard critical details essential for subsequent reasoning. In this paper, we introduce Commit-on-Evidence Memory (CoEM), which learns when to convert source evidence into compact memory facts. Specifically, under a fixed context-memory budget, CoEM preserves potentially useful source excerpts verbatim in a pending set, allowing subsequent context to clarify their relevance before irreversible compression. As new context arrives, a learned policy revisits each pending excerpt and decides whether to promote it to the committed memory, retain it for further consideration, or discard it. A frozen verifier ensures proposed facts are accepted only if supported by retained excerpts and current context. To further guide effective memory management, we train this policy using reinforcement learning by combining fine-grained, step-level evidence rewards with final answer rewards. Extensive experiments demonstrate that CoEM consistently improves long-context reasoning. When evaluated on 6,400 documents long-context input, CoEM outperforms the strongest memory baseline by 10.4-11.4 F1 points on Qwen3.5-9B. Code repository: https://github.com/benmagnifico/CoEM.

Jingguang Li, Yebo Wu, Zuyi Guo +7

Korea Advanced Institute of Science & Technology · University of Macau · Massachusetts Institute of Technology

Memory-Augmented Language Models Persistent Memory for Language Models LLM Context Management

Sep 28, 2026cs.CL

Mnemon: Raw Records, Fast Judgments, Slow Thoughts

Long-term memory lets an LLM assistant use a history it can no longer reread, and most memory systems build it by rewriting conversations into facts, graphs or typed memories at write time. We argue that the work of memory divides, as thinking does, into two systems. Most of it is fast System 1 work: many small, independent yes/no judgments about records, such as whether a record is needed or no longer current, which a decision model makes by the dozen in a third of a second. Only a little is slow System 2 work: writing a few search queries, naming what the reply needs and composing the answer, which an LLM does well but slowly. We present Mnemon, a memory agent built on this division. It keeps conversations as raw, dated records; an LLM (System 2) plans searches over them, a decision model, Jev (System 1), judges what the searches return, and rules with explicit budgets turn the judgments into a small View for an unchanged answering model. A background pass consolidates each record once into topic timelines, value histories and standing instructions linked to the records, so that questions about a whole conversation reach evidence their own searches miss. Because nothing is decided about a record when it is written, the same agent can read any store that returns dated records. With gpt-4.1-mini answering, as in a public re-evaluation of 14 systems, Mnemon scores 91.7% on LoCoMo, the highest among them, and 83.8% on LongMemEval-S, from under 4k tokens of context per question, with the lowest effective cost index on LoCoMo. With a reasoning model answering, it reaches 92.2% on LoCoMo and 94.4% on LongMemEval-S, the latter on par with the best published results. From 100K to 10M tokens of history on BEAM, its cost per question grows by a factor of 1.11. On the same records, Jev separates gold evidence better than two LLMs and is 3-11 times faster.

Guangren Wang

Persistent Memory for Language Models Memory Agent Benchmarks Long-Term Conversational Memory Agent Memory Management Memory-Augmented Language Model Agents

Sep 28, 2026cs.LG

GenMem: Generative Symbolic Memory for Self-Evolving Harness

Long-term memory supports the self-evolution of LLM agents by retaining experience and skills across tasks and enabling their retrieval, reuse, and revision in subsequent long-horizon decision-making. Yet existing memory management approaches remain limited to discriminative retrieval and to address the sparse, hierarchical, and highly redundant structure of reusable experience: only a small, task-dependent subset of trajectories and memories warrants retention, retrieval, or revision. Learning these operations is further complicated by sparse, delayed, and indirect task-level feedback, with weak supervision across the memory lifecycle. Moreover, continual memory evolution introduces an architectural tension as addressing invariance: stored experience is perpetually revised, yet the addressing interface consumed by learned retrieval policies must remain stable. To address, we present GenMem, which reformulates memory management as generative symbolic addressing. Its core mechanism is the Symbolic Identifier (SID), a multi-level discrete token tuple drawn from a Cartesian-product address space that factorizes a million-scale sparse memory space using fewer than one hundred discrete symbols. Instead of generating ever-changing raw content, the memory agent learns to generate SIDs, while memory evolution rewrites the payload at a fixed address without shifting the address itself. Architecturally, GenMem couples a MemRetriever and a MemEvolver within a multi-agent harness, trained via GRPO with dense process and outcome rewards with two-channels optimization. Under offline memory evolution, experiments spanning ALFWorld, WebShop, multi-hop QA, medical reasoning, and deep research evaluate GenMem against strong memory-augmented baselines...

Xinke Jiang, Tao Feng, Weixuan Xu +7

National Engineering Research Center of Software Engineering, Peking University, Beijing, China · School of Computer Science, Peking University, Beijing, China · Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China +2

LLM Agent Memory Persistent Memory for Language Models Agent Memory Management Self-Evolving Agents

Sep 28, 2026cs.CL

Remember by Asking: Retrieval-Induced Memory Evolution for LLM Agents

Long-term memory is essential for language agents to maintain coherent and effective behavior over extended, multi-session interactions. Existing memory systems mainly use retrieval at read time, while write-time memory formation still relies on direct extraction or compression. However, when future information needs are unknown, compressing an entire interaction in one pass can overlook locally important details that may matter later. To this end, we introduce RIME, a retrieval-induced memory framework that shifts memory construction from monolithic compression toward evidence-centered integration. RIME uses generic self-questions to retrieve focused dialogue evidence and grounds memory formation in both the retrieved evidence and relevant historical memories, which are jointly reconciled into an evolving memory bank with temporal and provenance information. At inference time, compressed memory serves as the primary rather than the sole source of evidence: when it cannot support an answer, RIME retrieves relevant source dialogue together with its local context to recover information omitted during memory formation, without resorting to full-history processing. Extensive experiments on LoCoMo with Qwen3-235B-A22B and GPT-5.6 Sol show that RIME consistently achieves the best performance across all three quality metrics among the compared methods, while requiring substantially fewer query-time LLM tokens.

Wanqi Zhou, Jiawei Lu, Yang Wang +4

Chang’an University

LLM Agent Memory Persistent Memory for Language Models Long-Term Conversational Memory Agent Memory Management

Sep 28, 2026cs.LG

Coding Agent Memory Post-training: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via Reinforcement Learning

Language-model agents increasingly tackle long-horizon tasks whose interaction histories exceed the model's active context. Recent work has begun to use reinforcement learning to make memory control part of the policy, often relying on predefined memory tools within domain-specific training environments of relatively short horizons. This setup ties learned memory behavior to environment-specific interfaces that lie outside the base model's pre-training and must be learned from scratch, so even after post-training, agents struggle to use memory in long-horizon tasks. To address these limitations, we introduce Coding Agent Memory Gym (CAMG), a suite of long-horizon agentic-RL environments spanning Shop, Coding, DeepResearch, and AutoResearch. Alongside each environment's native task interface, CAMG provides executable shell access and an episode-persistent workspace, enabling agents to create, revise, search, and reuse files as memory throughout an episode. We also introduce CAMG-RL, which trains a single policy jointly across all four environments with fully asynchronous PPO, learning this file-based memory behavior directly from downstream task reward, and we train CAMG-RL-4B and CAMG-RL-9B from Qwen3.5 models of matching size. On SWE-bench Verified and MLE-bench Lite, CAMG-RL-4B and CAMG-RL-9B are competitive with Qwen3.5-35B-A3B and Qwen3.5-122B-A10B, respectively.

Lirui Luo, Kelong Mao, Heming Xia +10

LLM Agent Memory Persistent Memory for Language Models RL Post-Training Long-Horizon Agent Tasks RL for LLM Agents Memory-Augmented Language Model Agents

Sep 28, 2026cs.AI

Stashbird: Efficient Speaker-Indexed Memory for Conversational Agents

AI agents require memory that preserves information across user-agent exchanges, user-to-user conversations, and group conversations with or without agent participation, while supporting updates as evidence changes or is removed. We present Stashbird, an agent memory system that links source episodes to derived memory state through explicit provenance. Stashbird organizes memory into episodic records, semantic relations, community summaries, and persisted graph state, with lifecycle operations for incremental updates and episode-level deletion. We evaluate question-answering accuracy and model-facing workload across four long-term memory benchmarks. On LoCoMo, Stashbird uses 76.4x fewer ingestion prompt tokens than Graphiti. Compared with reproduced Hindsight on the same benchmark, it uses 8.1x fewer retrieval prompt tokens, with accuracy 1.6 percentage points lower. It achieves higher accuracy than Hindsight on LongMemEval-S and GroupMemBench and comparable accuracy on EverMemBench.

Chidera Biringa, Lucas Yannul, Xiaowen Wang +5

Microsoft

Persistent Memory for Language Models Graph-Based Agent Memory Long-Term Conversational Memory Agent Memory Management

Sep 27, 2026cs.MA

TRACE: Governing Memory Validity in Evolving Multi-Agent Systems

Persistent memory lets language-model agents carry information across long-running collaborations, but leaves a lifecycle question open: what may a returning agent still act on once the shared state has changed? A memory can be correctly retrieved, relevant to the current task, and faithful to its source, and nonetheless be inadmissible for action: an itinerary saved before a pause still names the hotel the team has since replaced. We formalize this as temporal memory admission and present TRACE, a training-free layer that treats re-entry as an eligibility decision rather than a storage or retrieval operation, reconciling a departure checkpoint against absence-period updates, resolving explicit and implicit invalidation, and releasing a bounded Return View only when it covers the returning role's open obligations. We evaluate TRACE under three actor models on Memora, STALE Type II, and a derived ManBench-Return setting, each recast as return episodes: one agent departs, four teammates change the shared state, and the agent rejoins. What separates methods is not overall accuracy but whether one can retain valid memory and reject stale memory at once, and no single-policy baseline can: Restore (reinstate the departure checkpoint in full) admits stale state, Reset (start the return from an empty memory) discards valid state, each bottoming out at 0% on one of the two. TRACE is the only method high on both, reaching 92.6-98.3% valid-information availability with 98.4-99.5% invalid-information rejection on ManBench-Return, within 3.8 points of the best baseline's overall accuracy. On STALE Type II it improves Overall over the strongest comparison policy by 22.3 (Qwen), 18.5 (Gemini), and 27.5 (DeepSeek) points at roughly 2.3 times their tokens, while a write-time consolidation pipeline is more accurate still at 3.99 times TRACE's.

Wenjun Xiong, Shengtao Zhang, Shangding Gu +5

Shanghai Jiao Tong University · MemTensor(Shanghai) Technology Co., Ltd. · UC Berkeley +1

LLM Agent Memory Persistent Memory for Language Models Memory Agent Benchmarks Multi-Agent Systems Agent Memory Management

Sep 27, 2026cs.LG

SchemaMem: Schema-Indexed Recurrent Memory for Delayed State Retrieval

Attention provides direct access to past representations, but retaining an ever-growing history is costly. Recurrent models bound persistent state, yet must preserve selected information while processing subsequent inputs. We introduce SchemaMem, an attention-based recurrent memory architecture combining chunk-local attention with a persistent, schema-indexed phase state. Learned schema embeddings provide a shared representational reference for reading and writing. Reads use the current state, whereas writes use the layer input and static schema embeddings, excluding direct feedback from that layer's own state. Chunk-boundary commits aggregate bounded phase increments through forward computation. The same parameters also support full-history attention training before and during recurrent training. We studied selective updates, preservation, and delayed retrieval in a controlled address--value task, comparing three-layer models with approximately matched parameter counts and persistent-state dimensions. Across nine address/value settings and three training seeds, SchemaMem has higher mean written-value retention at four times the maximum training delay than both baselines, which are trained toward a higher in-range accuracy target. Updated-value recovery favors SchemaMem in all nine settings against Mamba-3 and seven against Gated DeltaNet. Defaults consistently favor Gated DeltaNet over SchemaMem at that delay, and SchemaMem requires substantially more optimization steps. These results identify a promising retention--optimization trade-off in schema-indexed recurrence.

Sungwoo Goo, Hwi-yeol Yun, Sangkeun Jung

College of Pharmacy, Chungnam National University Daejeon, Republic of Korea · Department of Computer Science & Engineering, Chungnam National University Daejeon, Republic of Korea

Memory-Augmented Neural Networks Persistent Memory for Language Models Recurrent Neural Networks Attention Mechanisms Associative Memory

Sep 27, 2026cs.AI

LSTMem: Hierarchical Long Short-Term Online Memory for Large Language Models

Large language models increasingly serve as long-horizon assistants and agents, where they must both accumulate information across interactions and make the relevant parts available when later requests depend on them. Existing compact online memories typically use a single persistent state both to accumulate history and to serve readout, so what the memory stores cannot be controlled separately from what it exposes to the current computation. We propose LSTMem, an LSTM-inspired online memory that instead equips each layer of a frozen LLM with two matrix-valued states: a cell state that accumulates history and a hidden state whose readouts correct the backbone's attention. Input and forget gates control what the cell stores, while an output gate separately controls what the cell exposes through the hidden state. LSTMem further connects memory across depth through forward hidden-state propagation and block-end feedback, and uses higher-layer reconstruction gradients to refine lower-layer cell states before rebuilding hidden states from shallow to deep layers. Across memory benchmarks on Qwen3-4B-Instruct, LSTMem consistently improves MemoryAgentBench, LoCoMo, and HotpotQA over the plain backbone. Comparisons further show that the LSTM-based memory formulation outperforms an associative-memory counterpart, while removing cross-layer hidden-memory propagation degrades performance. These results demonstrate the benefits of separating memory accumulation from memory expression and organizing memory hierarchically across model depth. The code is available at https://github.com/Longchentong/LSTMem.

Xianglong Shi, Ruijie Yang, Sirui Zhao +4

University of Science and Technology of China

Memory-Augmented Language Models Persistent Memory for Language Models LLM Memory Memory-Augmented Language Model Agents

Sep 24, 2026cs.AI

C3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Tasks

Long-horizon tasks require preserving and later recovering cross-session evidence under a bounded, query-blind memory budget. Existing compression can discard fine-grained visual cues or conflate semantically similar but incompatible observations. We present C3M, a cross-session multimodal memory organization that maintains a bounded active index over persistent source text-image evidence. Relation-aware updates consolidate safe redundancy while preserving complementary and incompatible records. At query time, budgeted routing selects useful index pages and expands their associated source evidence under a fixed reader budget. Together, these mechanisms establish a compact, provenance-preserving multimodal memory organization for cross-session long-horizon tasks, retaining temporal distinctions and source links required for reliable downstream reasoning. Code is available at https://github.com/HuzhouNLP/C3M.

Xueshu Chen, Yan Wang, Zihao Xue +5

Huzhou Normal University · Alibaba Group · University of Waterloo

Multimodal Memory Persistent Memory for Language Models

Sep 22, 2026cs.CL

MemoryAthena: Adaptive Routing over Latent and Generated Memories

Learned-memory methods store information in an explicit table and consume it through a separate reader, allowing addressing, storage, and reading to be modified independently. We study whether useful memory can also be generated rather than only retrieved. MemoryAthena uses three pathways: direct Engram retrieval (E), generation from retrieved Engram cues (GE), and generation from causal backbone states without consulting the memory table (GH). Generated memory is conditionally useful: it can complement E in one context but interfere with it in another. MemoryAthena therefore treats E as an anchor and learns when a generated representation should intervene. With the backbone, memory, generators, and readers frozen, a lightweight causal routing head is trained from counterfactual future-token likelihood advantages of GE and GH relative to E. At inference time, an admitted candidate modifies the E residual through bounded interpolation, while rejection recovers the direct pathway exactly. On question answering, MemoryAthena raises the five-task average from 37.65 to 39.28 over the direct pathway of the same checkpoint, while the six-task general-NLP average increases from 76.73 to 79.13. The complete memory-side system contains approximately 201M parameters, excluding the frozen backbone. Further analyses show complementary strengths among E, GE, and GH across tasks and inputs. These results support generated memory as a selective correction to direct retrieval and highlight routing when, which, and how strongly to intervene as the central challenge.

Mingyuan Li, Guangsheng Yu, Juyuan Zhang +4

ELLIS Institute of Finland · University of Turku · University of Technology Sydney +2

Memory-Augmented Language Models Persistent Memory for Language Models