Introduces IMLogic benchmark for implicit logical memory retrieval and RootMem framework that distills user histories into root memories and routes them via LLM to improve personalized LLM accuracy.
On memory construction and retrieval for personalized conversational agents
11 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
11
Pith papers citing it
1
external citations · external index
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
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.
Explicit bank, retrieval, and QA state roles reduce ghost-memory failures on conflict-heavy LTP and improve some temporal scores on LoCoMo, with host-dependent gains.
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.
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
-
Towards Root Memories: Benchmarking and Enhancing Implicit Logical Memory Retrieval for Personalized LLMs
Introduces IMLogic benchmark for implicit logical memory retrieval and RootMem framework that distills user histories into root memories and routes them via LLM to improve personalized LLM accuracy.
-
ElasticMem: Latent Memory as a Learnable Resource for LLM Agents
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.
-
A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory
Explicit bank, retrieval, and QA state roles reduce ghost-memory failures on conflict-heavy LTP and improve some temporal scores on LoCoMo, with host-dependent gains.
-
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
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: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
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.
-
MGRetrieval: Memory-Guided Reflective Retrieval for Long-Term Dialogue Agents
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.
-
Improving Multi-turn Dialogue Consistency with Self-Recall Thinking
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: LLM-Enhanced Recommendation with Hierarchical Semantic Understanding and Group-Aware Alignment
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.
-
From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs
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.
-
Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation
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 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.