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.
hub Canonical reference
arXiv preprint arXiv:2311.08719 , year=
Canonical reference. 100% of citing Pith papers cite this work as background.
18
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 5
method 1
citation-polarity summary
polarities
background 5representative citing papers
RBI-Eval shows LLMs integrate sensitive memory under benign prompts at rates 8.9-82.9% higher than no-memory baselines, with retrieval systems reducing but not eliminating the effect.
Empirical evaluation of eight memory condensation strategies on 480 DiscoveryBench tasks finds no significant impact on hypothesis quality but domain-dependent differences in token efficiency.
HAGE proposes a trainable weighted graph memory framework with LLM intent classification, dynamic edge modulation, and RL optimization that improves long-horizon reasoning accuracy in agentic LLMs over static baselines.
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.
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.
Opal enables private long-term memory for personal AI by decoupling reasoning to a trusted enclave with a lightweight knowledge graph and piggybacking reindexing on ORAM accesses.
WorkflowGen reuses trajectory experiences via node-level and workflow-level extraction plus three-tier semantic routing to cut token use over 40% and raise success 20% on medium-similarity queries versus real-time planning baselines.
TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.
Introduces Parametric Memory Law as power law for LoRA memory capacity and MemFT threshold-guided optimization for better memory fidelity.
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.
SafeHarbor introduces a hierarchical memory-augmented guardrail with adversarial rule extraction and entropy-driven self-evolution to balance safety and utility in LLM agents.
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.
AtomMem introduces atomic-fact extraction, hierarchical event structures, and an associative memory graph to build stable long-term memory for LLM agents, claiming SOTA results on the LoCoMo benchmark.
A survey that provides a taxonomy of methods for improving planning in LLM-based agents across task decomposition, plan selection, external modules, reflection, and memory.
A survey that defines agent skills as reusable procedural artifacts and reviews methods, resources, and applications across their representation, acquisition, retrieval, and evolution stages.
A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.
This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.
citing papers explorer
-
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.
-
When Should Memory Stay Silent: Measuring Memory-Use Boundaries in Memory-Augmented Conversational Agents
RBI-Eval shows LLMs integrate sensitive memory under benign prompts at rates 8.9-82.9% higher than no-memory baselines, with retrieval systems reducing but not eliminating the effect.
-
Evaluating Memory Condensation Strategies for Coding Agents in Data-Driven Scientific Discovery
Empirical evaluation of eight memory condensation strategies on 480 DiscoveryBench tasks finds no significant impact on hypothesis quality but domain-dependent differences in token efficiency.
-
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
HAGE proposes a trainable weighted graph memory framework with LLM intent classification, dynamic edge modulation, and RL optimization that improves long-horizon reasoning accuracy in agentic LLMs over static baselines.
-
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.
-
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.
-
Opal: Private Memory for Personal AI
Opal enables private long-term memory for personal AI by decoupling reasoning to a trusted enclave with a lightweight knowledge graph and piggybacking reindexing on ORAM accesses.
-
WorkflowGen:an adaptive workflow generation mechanism driven by trajectory experience
WorkflowGen reuses trajectory experiences via node-level and workflow-level extraction plus three-tier semantic routing to cut token use over 40% and raise success 20% on medium-similarity queries versus real-time planning baselines.
-
Trust Region On-Policy Distillation
TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.
-
How LoRA Remembers? A Parametric Memory Law for LLM Finetuning
Introduces Parametric Memory Law as power law for LoRA memory capacity and MemFT threshold-guided optimization for better memory fidelity.
-
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.
-
SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
SafeHarbor introduces a hierarchical memory-augmented guardrail with adversarial rule extraction and entropy-driven self-evolution to balance safety and utility in LLM agents.
-
AtomMem: Building Simple and Effective Memory System for LLM Agents via Atomic Facts
AtomMem introduces atomic-fact extraction, hierarchical event structures, and an associative memory graph to build stable long-term memory for LLM agents, claiming SOTA results on the LoCoMo benchmark.
-
A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
A survey that defines agent skills as reusable procedural artifacts and reviews methods, resources, and applications across their representation, acquisition, retrieval, and evolution stages.