arXiv AI
Aug 5
LeanMem: Simple and Efficient Long-Term Memory for LLM Agents
arXiv:2608. 03463v1 Announce Type: new Abstract: Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history.
JustMem: Just-Enough Memory Access for Long-Term Conversations
JustMem is a new memory system for long‑term conversational AI that stores conversation history as compact atomic memories and adapts its access strategy to each query. It introduces two dimensions of memory access—discovery breadth and reading fidelity—implemented through LOOKUP for local evidence, COMPOSE for distributed evidence, and REPLAY for fidelity‑sensitive evidence. Experiments on LoCoMo and LongMemEval‑S show that JustMem outperforms competing memory systems in accuracy and recall while using fewer generative‑model tokens for memory construction and inference.
Related stories
arXiv AI
Oct 5
APDMem: Agent-Controlled Progressive Disclosure for Query-Adaptive Long-Term Memory
APDMem is a hierarchical long‑term memory system for personalized LLM assistants that uses progressive disclosure to retrieve conversation history. It organizes memory into four layers—thematic summaries, personalized key facts, turn‑level evidence notes, and raw messages—and a controller reads from the top layer, drilling down only when necessary. This approach balances cost and fidelity, allowing simple queries to finish early while deeper inspection is triggered for complex or exact‑evidence requests, and a note synthesizer structures retrieved evidence before answer generation. Experiments on LongMemEval show APDMem performs strongly while accessing only 8% of the total conversations.
arXiv Computation and Language
Sep 1
UTILMEM: Benchmarking Evidence Utilization in Long-Term Conversational Memory
UTILMEM is a new diagnostic benchmark that tests how conversational agents use long‑term memory, focusing on reasoning over dense histories, spotting implicitly relevant memories, synthesizing distributed evidence, and resisting interference from similar distractors. It contains 1,717 instances across five domains and evaluates a range of retrieval‑based and memory‑augmented systems. The study shows that strong performance on traditional factual recall does not guarantee effective memory utilization, highlighting a gap between retrieving information and integrating it into coherent, task‑oriented outputs.
arXiv Computation and Language
Sep 14
CueMem: Cue-Guided Context Reconstruction for Long-Term Conversational Memory
CueMem is a cue‑guided framework for long‑term conversational memory that reconstructs query‑relevant dialogue context from compressed memory records. Instead of treating memory units as self‑contained evidence, it extracts fine‑grained cues linked to their source turns and, at query time, expands from these cues over a turn graph to rebuild a compact evidence context. Experiments on LoCoMo and LongMemEval show that CueMem outperforms baseline memory methods, reduces input tokens and latency, and improves long‑term conversational question answering.
arXiv Computation and Language
Sep 15
Where to Look and What to Use: Retrieve-Localize-Generate for Long-Term Conversational Memory Question Answering
arXiv:2609.07093v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) enables large language models (LLMs) to answer questions by accessing external knowledge and has been widely a...
arXiv Computation and Language
3d ago
Chain on Demand: Deferred Evidence Organization for Long-Term Conversational Memory
The paper introduces Chain on Demand (CoD), a query‑time evidence organization framework that builds a temporary evidence chain from an unchanged turn‑level memory. CoD allocates a fixed anchor budget based on query relevance, lexical diversity, and new query terms, then restores each anchor’s same‑session neighborhood deterministically. In evaluations on LoCoMo and LongMemEval‑S, CoD achieves high accuracy, demonstrating that long‑term conversational memory can remain unchanged while deferring evidence organization until the query is known.
arXiv Computation and Language
Oct 22
DiaLong: Benchmarking Reminiscence in Long-Context Dialogues
DiaLong is a new long‑context dialogue benchmark that tests transformer‑based Large Language Models’ ability to retain and recall memories. The dataset contains 100 human‑created conversations, expanded with LLMs to exceed lengths of existing datasets, and includes a fact‑recall task where models must classify 40 candidate facts as true or false. Experiments show current LLMs and memory‑enhancement methods still struggle, indicating a need for improved memory performance in extended conversations.
arXiv AI
Oct 19
From Memory Hits to Answerable Evidence: Query-Conditioned Memory Compilation for Long-Term Agent Memory
The paper introduces MemCompile, a query‑conditioned evidence compilation framework designed to improve long‑term conversational memory. It uses an Address Plane to locate relevant support via compact descriptors and capacity‑aware cells, then normalizes retrieval hits into stable SourcePacket identities. An Evidence Plane allocates a bounded evidence budget across packets, admits limited additional support, and produces answer‑ready context, achieving 80.52% Judge Accuracy on LoCoMo and improving the quality‑cost Pareto frontier.
arXiv AI
Sep 4
When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agents
The paper introduces LOCOMO-CONV, a conversational memory benchmark that expands on the existing LoCoMo dataset with four query styles—dialog, implicit, counterfactual, and composed—designed to evaluate memory systems in realistic conversational settings. Experiments across five memory systems reveal that conversational framing uncovers significant retrieval gaps missed by traditional QA benchmarks, particularly for implicit and composed queries, and that strong retrieval does not necessarily translate into higher response quality. The study also highlights silent grounding in implicit queries, where memory enhances contextual grounding without explicitly presenting the gold fact, suggesting a need for reasoning-based memory elaboration.
arXiv Computation and Language
Oct 15
LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation
arXiv:2608.12990v2 Announce Type: replace Abstract: Long-horizon LLM agents must preserve information from past interactions to support future tasks. Existing memory systems typically rely on eager c...
arXiv Computation and Language
Oct 28
ETAMem: Decoupling and Aligning Heterogeneous Memory for Long-Term Conversational Agents
ETAMem is a multi‑view memory framework designed to improve long‑term conversational agents by decoupling heterogeneous information and aligning memory representations with distinct characteristics. It parses conversational data into atomic units, identifies affective content, and organizes these units into three complementary hierarchical views—Event, Affect, and Time—using adaptively calibrated thresholds. Retrieval is performed via entropy‑based allocation of query budgets across views, enabling hierarchical search within each view. Experiments on LoCoMo and LongMemEval‑S show that ETAMem surpasses state‑of‑the‑art baselines with relative accuracy gains of 12.46% and 7.96%, while remaining token‑efficient, and analyses confirm the complementary benefits of the different memory views.
arXiv Machine Learning
Sep 4
MemoryLACE: Memory Lifecycle-Aware Consolidation and Evidence Retrieval
MemoryLACE (MemLACE) is a lightweight memory framework that explicitly models the lifecycle of textual evidence—capturing sparse merge, supersession, and contradiction relations—while preserving atomic natural‑language memories and their provenance. Unlike traditional systems that retrieve memories independently, MemLACE reconstructs relation‑aware evidence units that expose current, historical, supporting, and conflicting evidence for downstream reasoning. In benchmark evaluations (BEAM and StructMemEval) using both open‑weight and proprietary LLM backbones, MemLACE achieves the highest overall performance among same‑backbone comparisons and reduces BEAM runtime by 66.6% compared to the strongest reflective‑memory baseline, Hindsight.