MedMemoryBench supplies a 2,000-session synthetic medical trajectory dataset and an evaluate-while-constructing streaming protocol to expose memory saturation and reasoning failures in current agent architectures for personalized healthcare.
hub Canonical reference
Personamem-v2: Towards person- alized intelligence via learning implicit user personas and agentic memory
Canonical reference. 80% of citing Pith papers cite this work as background.
22
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 4
dataset 1
citation-polarity summary
years
2026 22representative citing papers
AlpsBench supplies 2500 real-dialogue sequences with verified memories to benchmark LLM extraction, updating, retrieval, and utilization of personalized information.
MemSyco-Bench is a benchmark covering five tasks to evaluate memory-induced sycophancy in LLM agents, testing rejection of invalid memory, scope respect, conflict resolution, update tracking, and valid personalization.
MEMPROBE is a benchmark for direct recovery of hidden user states from LLM agent memory, showing task success and memory recovery as distinct capabilities with moderate recovery scores around 0.6.
User facts are internalized as surgical local edits to a hash-keyed Engram memory table with reasoning skill held in a shared adapter, claimed to match LoRA recall, improve indirect reasoning 5.6x on average, and compose across users with 33,000x smaller footprint than per-user adapters.
DCPM reorganizes LLM agent memory into a cognitive hierarchy driven by a synchronous daytime belief writer and an asynchronous nighttime schema engine, reporting gains on cross-session inference benchmarks.
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.
VisualMem augments text memory with a visual module that resolves identity and durable user facts from images, outperforming prior systems on a new benchmark for explicit and implicit personal visual evidence.
VitaBench 2.0 introduces a benchmark for long-term personalized and proactive agent behavior, with results indicating substantial gaps in current frontier LLMs.
GroupMemBench is a new benchmark exposing that LLM agent memory systems fail on group conversation properties like speaker-grounded tracking and audience-adapted responses, with top systems at 46% accuracy.
PGR expands user queries into plausible future steps via Tree-of-Thought or chains and uses them as retrieval probes, delivering nearly 3x recall gains on the new MemoryQuest benchmark for low-similarity memory retrieval.
LongMemEval-V2 is a new benchmark where AgentRunbook-C reaches 72.5% accuracy on long-term agent memory tasks, beating RAG baselines at 48.5% and basic coding agents at 69.3%.
PIQL integrates privileged information to accelerate convergence, lower loss, and improve generalization in tabular foundation models.
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.
PERMA is a new benchmark using temporally ordered events, text variability, and linguistic alignment to evaluate LLM memory agents on persona consistency beyond simple retrieval.
Training a 9B LLM agent with reinforcement learning to actively navigate a structured multi-granularity memory pyramid yields competitive performance on memory-intensive benchmarks while preserving non-memory capabilities.
Introduces EvoArena benchmark for dynamic LLM agent environments and EvoMem memory paradigm that improves accuracy by 1.5% on EvoArena and gains on GAIA and LoCoMo.
FluxMem evolves memory as a heterogeneous graph via three refinement stages and reports consistent state-of-the-art results on LoCoMo, Mind2Web, and GAIA benchmarks.
δ-mem augments frozen LLMs with an 8x8 online memory state updated by delta-rule learning to generate low-rank attention corrections, delivering 1.10x average gains over the backbone and larger improvements on memory-heavy tasks.
MemPrivacy uses edge-side privacy span detection and semantic placeholders to enable cloud memory management for LLM agents while limiting utility loss to 1.6% and outperforming masking baselines.
GroupGPT decouples intervention timing from response generation via edge-cloud collaboration for multi-user chats, scoring 4.72/5 on the new MUIR benchmark of 2500 segments while cutting token use by up to 3x and adding privacy sanitization.
citing papers explorer
-
MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
MedMemoryBench supplies a 2,000-session synthetic medical trajectory dataset and an evaluate-while-constructing streaming protocol to expose memory saturation and reasoning failures in current agent architectures for personalized healthcare.
-
AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment
AlpsBench supplies 2500 real-dialogue sequences with verified memories to benchmark LLM extraction, updating, retrieval, and utilization of personalized information.
-
MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
MemSyco-Bench is a benchmark covering five tasks to evaluate memory-induced sycophancy in LLM agents, testing rejection of invalid memory, scope respect, conflict resolution, update tracking, and valid personalization.
-
MEMPROBE: Probing Long-Term Agent Memory via Hidden User-State Recovery
MEMPROBE is a benchmark for direct recovery of hidden user states from LLM agent memory, showing task success and memory recovery as distinct capabilities with moderate recovery scores around 0.6.
-
User as Engram: Internalizing Per-User Memory as Local Parametric Edits
User facts are internalized as surgical local edits to a hash-keyed Engram memory table with reasoning skill held in a shared adapter, claimed to match LoRA recall, improve indirect reasoning 5.6x on average, and compose across users with 33,000x smaller footprint than per-user adapters.
-
Memory Beyond Recall: A Dual-Process Cognitive Memory System for Self-Evolving LLM Agents
DCPM reorganizes LLM agent memory into a cognitive hierarchy driven by a synchronous daytime belief writer and an asynchronous nighttime schema engine, reporting gains on cross-session inference benchmarks.
-
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.
-
Personal Visual Memory from Explicit and Implicit Evidence
VisualMem augments text memory with a visual module that resolves identity and durable user facts from images, outperforming prior systems on a new benchmark for explicit and implicit personal visual evidence.
-
VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions
VitaBench 2.0 introduces a benchmark for long-term personalized and proactive agent behavior, with results indicating substantial gaps in current frontier LLMs.
-
GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations
GroupMemBench is a new benchmark exposing that LLM agent memory systems fail on group conversation properties like speaker-grounded tracking and audience-adapted responses, with top systems at 46% accuracy.
-
Thinking Ahead: Prospection-Guided Retrieval of Memory with Language Models
PGR expands user queries into plausible future steps via Tree-of-Thought or chains and uses them as retrieval probes, delivering nearly 3x recall gains on the new MemoryQuest benchmark for low-similarity memory retrieval.
-
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
LongMemEval-V2 is a new benchmark where AgentRunbook-C reaches 72.5% accuracy on long-term agent memory tasks, beating RAG baselines at 48.5% and basic coding agents at 69.3%.
-
Toward Privileged Foundation Models:LUPI for Accelerated and Improved Learning
PIQL integrates privileged information to accelerate convergence, lower loss, and improve generalization in tabular foundation models.
-
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.
-
PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments
PERMA is a new benchmark using temporally ordered events, text variability, and linguistic alignment to evaluate LLM memory agents on persona consistency beyond simple retrieval.
-
From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Space
Training a 9B LLM agent with reinforcement learning to actively navigate a structured multi-granularity memory pyramid yields competitive performance on memory-intensive benchmarks while preserving non-memory capabilities.
-
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
Introduces EvoArena benchmark for dynamic LLM agent environments and EvoMem memory paradigm that improves accuracy by 1.5% on EvoArena and gains on GAIA and LoCoMo.
-
Rethinking Memory as Continuously Evolving Connectivity
FluxMem evolves memory as a heterogeneous graph via three refinement stages and reports consistent state-of-the-art results on LoCoMo, Mind2Web, and GAIA benchmarks.
-
$\delta$-mem: Efficient Online Memory for Large Language Models
δ-mem augments frozen LLMs with an 8x8 online memory state updated by delta-rule learning to generate low-rank attention corrections, delivering 1.10x average gains over the backbone and larger improvements on memory-heavy tasks.
-
MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents
MemPrivacy uses edge-side privacy span detection and semantic placeholders to enable cloud memory management for LLM agents while limiting utility loss to 1.6% and outperforming masking baselines.
-
GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant
GroupGPT decouples intervention timing from response generation via edge-cloud collaboration for multi-user chats, scoring 4.72/5 on the new MUIR benchmark of 2500 segments while cutting token use by up to 3x and adding privacy sanitization.
- Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization