Creates LoCoMo benchmark dataset for very long-term LLM conversational memory and shows current models struggle with lengthy dialogues and long-range temporal dynamics.
hub Canonical reference
Memochat: Tuning llms to use memos for consistent long- range open-domain conversation
Canonical reference. 83% of citing Pith papers cite this work as background.
17
Pith papers citing it
5
external citations · external index
Background
83% of classified citations
hub tools
citation-role summary
background 5
method 1
citation-polarity summary
representative citing papers
BOOKMARKS introduces searchable bookmarks as reusable answers to storyline questions, enabling active initialization and passive synchronization for more consistent role-playing agent memory than recurrent summarization.
MemCoE learns memory organization guidelines via contrastive feedback and then trains a guideline-aligned RL policy for memory updates, yielding consistent gains on personalization benchmarks.
A four-module framework is used to benchmark 12 agent memory systems, showing no architecture dominates and that workload alignment plus localized maintenance drive performance and cost.
HingeMem segments dialogue memory via boundary-triggered hyperedges over four elements and applies query-adaptive retrieval, yielding ~20% relative gains and 68% lower QA token cost versus baselines on LOCOMO.
MemAgent trains an LLM with reinforcement learning to maintain a fixed-size token memory while reading a long document in chunks, and reports near-lossless QA accuracy extrapolating from 32K training context to 3.5M test tokens.
A survey that maps safety risks in personalized LLMs, introduces a unified taxonomy, and highlights three structural inadequacies in existing research on user-invariant safety, isolated techniques, and short-term evaluations.
AFA with identity-aware routing raises persona attribution accuracy from 35.7% to 61.3% on a new synthetic multi-user dialogue dataset.
MemCoT transforms long-context LLM reasoning into an iterative stateful search using multi-view memory for evidence localization and dual short-term memory for guiding decisions, achieving SOTA on LoCoMo and LongMemEval-S benchmarks.
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.
TrustMem introduces a verifier for memory update transitions and preference-guided RL to cut omission, corruption, and hallucination rates in LLM agent memory while reaching SOTA on MemoryAgentBench and HaluMem.
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 consolidating frameworks, data practices, large action models, benchmarks, applications, and research gaps in LLM-brained GUI agents.
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.
A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.
A survey that maps risks along the agent workflow and consolidates metrics and benchmarks for safety, robustness, privacy, and security in agentic AI.
citing papers explorer
-
Evaluating Very Long-Term Conversational Memory of LLM Agents
Creates LoCoMo benchmark dataset for very long-term LLM conversational memory and shows current models struggle with lengthy dialogues and long-range temporal dynamics.
-
BOOKMARKS: Efficient Active Storyline Memory for Role-playing
BOOKMARKS introduces searchable bookmarks as reusable answers to storyline questions, enabling active initialization and passive synchronization for more consistent role-playing agent memory than recurrent summarization.
-
Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
MemCoE learns memory organization guidelines via contrastive feedback and then trains a guideline-aligned RL policy for memory updates, yielding consistent gains on personalization benchmarks.
-
Are We Ready For An Agent-Native Memory System?
A four-module framework is used to benchmark 12 agent memory systems, showing no architecture dominates and that workload alignment plus localized maintenance drive performance and cost.
-
HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues
HingeMem segments dialogue memory via boundary-triggered hyperedges over four elements and applies query-adaptive retrieval, yielding ~20% relative gains and 68% lower QA token cost versus baselines on LOCOMO.
-
MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
MemAgent trains an LLM with reinforcement learning to maintain a fixed-size token memory while reading a long document in chunks, and reports near-lossless QA accuracy extrapolating from 32K training context to 3.5M test tokens.
-
Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs
A survey that maps safety risks in personalized LLMs, introduces a unified taxonomy, and highlights three structural inadequacies in existing research on user-invariant safety, isolated techniques, and short-term evaluations.
-
AFA: Identity-Aware Memory for Preventing Persona Confusion in Multi-User Dialogue
AFA with identity-aware routing raises persona attribution accuracy from 35.7% to 61.3% on a new synthetic multi-user dialogue dataset.
-
MemCoT: Test-Time Scaling through Memory-Driven Chain-of-Thought
MemCoT transforms long-context LLM reasoning into an iterative stateful search using multi-view memory for evidence localization and dual short-term memory for guiding decisions, achieving SOTA on LoCoMo and LongMemEval-S benchmarks.
-
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.
-
TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory
TrustMem introduces a verifier for memory update transitions and preference-guided RL to cut omission, corruption, and hallucination rates in LLM agent memory while reaching SOTA on MemoryAgentBench and HaluMem.
-
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.
-
Large Language Model-Brained GUI Agents: A Survey
A survey consolidating frameworks, data practices, large action models, benchmarks, applications, and research gaps in LLM-brained GUI agents.
-
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.
-
A Survey on the Memory Mechanism of Large Language Model based Agents
A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.
-
Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security
A survey that maps risks along the agent workflow and consolidates metrics and benchmarks for safety, robustness, privacy, and security in agentic AI.
- Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework