ElasticMem enables LLM agents to learn adaptive latent memory retrieval and elastic budget allocation, improving QA accuracy by 24-26% and ALFWorld success by 27-66% over baselines with lower token cost.
On memory construction and retrieval for personalized conversational agents
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
verdicts
UNVERDICTED 10roles
background 4polarities
background 4representative citing papers
The paper defines and evaluates Trojan Hippo attacks on LLM agent memory, showing 85-100% success in data exfiltration across backends and reduced rates with defenses at varying utility costs.
Memory-R1 uses PPO and GRPO to train a Memory Manager (ADD/UPDATE/DELETE/NOOP) and Answer Agent that together outperform baselines on long-context QA benchmarks after training on only 152 examples.
ATMA adds state labels and evidence packets to existing memory systems to reduce ghost memory failures, with reported gains on a new LTP benchmark and LoCoMo.
MGRetrieval grounds reflective retrieval in historical memory structure for long-term dialogue, yielding 8.91% F1 and 11.11% BLEU-1 gains over baselines on LoCoMo with Qwen models.
SRT framework improves multi-turn dialogue F1 by 4.7% and cuts end-to-end latency by 14.7% via dependency construction, capability initialization, and reasoning improvement with recall tokens.
HSUGA improves LLM-enhanced sequential recommendation via staged hierarchical semantic understanding for better preference extraction and group-aware alignment that varies intensity by user activity level.
The paper surveys human memory categories, maps them to LLM memory, and proposes a new three-dimension (object, form, time) categorization into eight quadrants to organize existing work and highlight open problems.
A minimalist retrieval-and-generation framework using turn isolation and query-driven pruning outperforms complex memory systems by directly addressing signal sparsity and dual-level redundancy in dialogues.
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.
citing papers explorer
-
A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory
ATMA adds state labels and evidence packets to existing memory systems to reduce ghost memory failures, with reported gains on a new LTP benchmark and LoCoMo.
-
A Survey of Scaling in Large Language Model Reasoning
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.