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.
S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering
arXiv:2605. 28831v2 Announce Type: replace-cross Abstract: Long-horizon memory question answering often requires sparse evidence from heterogeneous histories, including events, object states, visual observations, temporal relations, and causal steps.
Related stories
arXiv AI
Sep 2
EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
arXiv:2609.00551v1 Announce Type: cross Abstract: Multimodal memory offers a scalable interface for long-video question answering, but existing methods often retrieve captions, frames, transcripts, s...
arXiv AI
Aug 11
SodaMem: Evidence-Grounded Temporal Graph Memory for LLM Agents
arXiv:2608. 08055v1 Announce Type: new Abstract: Large language model (LLM) agents that assist users over weeks of conversation must remember what is currently true, not merely what was once said.
arXiv Computation and Language
Aug 31
Entity-Memory Graph Retrieval Improves Evidence Coverage in Long-Conversation Question Answering
Entity-Memory graph retrieval preserves dialogue turns as verbatim memory nodes, links repeated mentions via shared entities, and connects adjacent memories with chronological edges. During retrieval, the system gates through entities, fuses semantics, and performs one‑hop chronological recovery before dense backfill, allowing it to keep neighboring memories that dense cosine ranking might miss. On 1,986 questions from ten LoCoMo conversations, this graph retrieval method increases official evidence recall at top‑k 25 from 79.7468 % to 84.4842 %, with the advantage extending from top‑k 5 to 50, though it does not improve overall final‑answer F1.
arXiv AI
Jun 4
MemoryDocDataSet: A Benchmark for Joint Conversational Memory and Long Document Reasoning
arXiv:2606. 04442v1 Announce Type: cross Abstract: AI systems increasingly need to combine two demanding capabilities: navigating multi-session conversation history and performing deep reading comprehension within long documents.
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...
Hugging Face Trending Papers
Jun 3
MemoryDocDataSet: A Benchmark for Joint Conversational Memory and Long Document Reasoning
AI systems increasingly need to combine two demanding capabilities: navigating multi-session conversation history and performing deep reading comprehension within long documents. Yet no existing benchmark evaluates both simultaneously.
arXiv AI
Aug 20
Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios
Event-Causal RAG (EC‑RAG) is a lightweight retrieval‑augmented framework designed for reasoning over ultra‑long and streaming videos. It segments video streams into semantically complete events using a dual visual‑audio sentinel mechanism, representing each event as a State‑Event‑State (SES) structure that captures pre‑event, event, and post‑event states. During question answering, bidirectional graph retrieval accesses relevant predecessor and successor events from a dual vector‑graph memory, and answers are generated using both this structured memory and the corresponding video evidence. The authors also introduce ECV‑1H, an hour‑scale long‑video QA benchmark with over 150 hours of untrimmed video and 1,251 human‑annotated QA pairs, where EC‑RAG achieves significant accuracy gains across multiple video foundation models while maintaining efficient streaming memory usage on a single RTX 5090 GPU.
arXiv AI
Jul 28
LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory
arXiv:2607. 22690v1 Announce Type: new Abstract: Long-term memory lets LLM agents reuse past interactions, but raw dialogue histories are verbose and information-sparse.
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
4d ago
GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory
arXiv:2605.01688v2 Announce Type: replace-cross Abstract: Long-horizon memory systems increasingly improve how evidence is stored and retrieved, yet the generator must still reason over fragments who...
arXiv AI
Sep 10
When Does Memory Help? A Cost-Aware Evaluation of Long-Term Memory in Tool-Using LLM Agents
The paper introduces MERIT, a benchmark that evaluates the marginal benefit of long‑term memory for tool‑using large language model agents while explicitly accounting for cost. MERIT provides episodic tool‑use tasks across three domains, verifies dependence on earlier‑episode facts, and measures memory operations in tokens and dollars. Experiments on GPT‑4.1‑mini, Claude Haiku 4.5, and Claude Sonnet 5 show that memory can significantly improve task success, but its utility varies widely across models and memory implementations, and full replay is rarely cost‑effective.