MemTrace shows that evidence utilization, not retrieval, is the dominant failure mode in LLM long-term memory systems across tested configurations.
Beyond goldfish memory: Long-term open- domain conversation
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
ReasoningBank distills generalizable reasoning strategies from agent successes and failures to enable self-evolution, with memory-aware test-time scaling amplifying gains over raw-trajectory or success-only memory on web and software benchmarks.
LongMemEval benchmarks long-term memory in chat assistants, revealing 30% accuracy drops across sustained interactions and proposing indexing-retrieval-reading optimizations that boost performance.
C-DIC achieves stable latency and perplexity over hundreds of dialogue turns via incremental per-thread compression with cross-turn revision.
An extended annotation scheme with new categories and attributes plus a Gemma-300M-based multi-head classifier achieves 81.6% macro F1 on personal fact classification, outperforming few-shot LLM baselines by nearly 9 points with lower compute.
CL-bench Life shows frontier language models achieve only 13.8% average success on real-life context tasks, with the best model at 19.3%.
HiGMem combines hierarchical event-turn memory with LLM-guided selection to retrieve concise relevant evidence from long dialogues, improving F1 scores and cutting retrieved turns by an order of magnitude on the LoCoMo10 benchmark.
G-Long uses graph-enhanced triplet memory and attention-aware scoring from a T5 summarizer to achieve up to 9.8% better response quality on MSC and 40.8% better retrieval recall on LME with lower overhead.
Memory-R2 proposes LoGo-GRPO to fix unfair trajectory comparisons in RL training of memory-augmented LLM agents by combining global end-to-end rewards with local rerollouts from identical memory states.
UserGPT introduces a generative LLM framework with a behavior simulation engine, semantization module, and DF-GRPO post-training that scores 0.7325 on tag prediction and 0.7528 on summary generation on HPR-Bench while compressing records by up to 97.9%.
citing papers explorer
-
MemTrace: Probing What Final Accuracy Misses in Long-Term Memory
MemTrace shows that evidence utilization, not retrieval, is the dominant failure mode in LLM long-term memory systems across tested configurations.
-
ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
ReasoningBank distills generalizable reasoning strategies from agent successes and failures to enable self-evolution, with memory-aware test-time scaling amplifying gains over raw-trajectory or success-only memory on web and software benchmarks.