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.
DiaLong: Benchmarking Reminiscence in Long-Context Dialogues
Related stories
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 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
Sep 18
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.
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 AI
Sep 3
Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents
The paper introduces Temporal Semantic Memory (TSM), a framework that improves how large language model agents manage memory by addressing two key shortcomings: temporal inaccuracy and temporal fragmentation. TSM constructs a semantic timeline instead of a dialogue timeline, consolidating temporally continuous and semantically related information into durative memory. During retrieval, it aligns the query’s temporal intent with the semantic timeline, enabling the use of temporally appropriate durative memories and yielding up to a 12.2% accuracy boost over existing methods.
arXiv AI
Jun 9
DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs
arXiv:2601. 07994v5 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly operate over long-form dialogues with frequent topic shifts.
arXiv AI
Sep 11
PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations
PRAGMA is a benchmark designed to evaluate personalized guidance in long‑term conversations. It includes curated longitudinal conversation histories, evidence annotations, and guidance scenarios that reflect evolving user contexts and incorrect assumptions. Experiments show that current retrieval, memory, and long‑context models struggle to recover relevant conversational evidence and to use it effectively for personalized guidance.
arXiv Computation and Language
Oct 8
FTA-Mem: Fact-Time-Affect Anchored Memory for Low-Density Long-Term Dialogue
arXiv:2608.16303v2 Announce Type: replace Abstract: Long-term emotional-support agents require memory mechanisms for personalized understanding across sessions. However, emotional-support dialogue is...
arXiv Computation and Language
4d ago
Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
The paper introduces TriMem, a memory system for lifelong LLM agents that stores raw dialogue segments, extracted atomic facts, and synthesized profiles to preserve detail, enable efficient retrieval, and support deep reasoning. It uses TextGrad-based prompt optimization to iteratively refine extraction and profiling prompts without updating model parameters. Experiments on LoCoMo and PerLTQA show TriMem outperforms strong memory baselines across multiple LLM backbones.
arXiv AI
Jul 24
RUMBA: Russian User Memory Benchmark
arXiv:2607. 21447v1 Announce Type: cross Abstract: The ability to handle long-term memory in LLMs is becoming increasingly critical, yet existing benchmarks remain English-centric and rely on aggregate retrieval metrics, failing to capture interactions between long-range context, temporal information, and reasoning.
arXiv AI
Jun 12
MemRefine: LLM-Guided Compression for Long-Term Agent Memory
arXiv:2606. 13177v1 Announce Type: cross Abstract: 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.