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.
Perltqa: A personal long-term memory dataset for memory classification, retrieval, and synthesis in question answering.CoRR, abs/2402.16288
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
support 1representative citing papers
MRMMIA is a multi-recall-probe membership inference attack that extracts signals from chat agent memory and outperforms baselines in black-, gray-, and white-box settings.
MemLens benchmark shows long-context LVLMs lose accuracy with length while memory agents lose visual fidelity, with multi-session reasoning below 30% for most systems and neither approach solving the task alone.
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%.
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.
LMEB benchmark shows that embedding models' performance on traditional retrieval does not transfer to long-horizon memory tasks, larger models do not always perform better, and LMEB measures capabilities orthogonal to MTEB.
LATTE improves personalized LLM generation by forecasting peer-anchored relative preference trajectories and injecting the forecast via a State to Token Bridge, raising ROUGE-L from 0.219-0.245 to 0.259 on Amazon Reviews 2023 over static and compression baselines.
ProAct uses idle compute to anticipate user needs via dialogue history and memory, achieving 14.8% fewer turns, 11.7% less user effort, and 28.1% fewer hallucinations than reactive baselines on the new ProActEval benchmark.
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.
SelRoute routes queries to type-specific retrieval pipelines, achieving Recall@5 of 0.800 with a 109M model on LongMemEval_M and outperforming LLM-augmented baselines including a strong zero-ML lexical method.
EngramaBench shows structured graph memory outperforms full-context prompting on cross-space reasoning in long conversations but scores lower overall than full-context and higher than vector retrieval.
The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle with equally sophisticated long outputs.
citing papers explorer
-
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.