MemTrace shows that evidence utilization, not retrieval, is the dominant failure mode in LLM long-term memory systems across tested configurations.
MEMTRACK: Evalu- ating long-term memory and state tracking in multi-platform dynamic agent environments
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7representative citing papers
Language models show superior memory to humans on psych experiments but can be adjusted via prompting and compaction to forget more human-like, yielding better user simulators.
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.
AgentCollabBench shows that multi-agent reliability is limited by communication topology, with converging-DAG nodes causing synthesis bottlenecks that discard constraints and explain 7-40% of information loss variance.
Schema-aware iterative extraction turns AI memory into a verified system of record, reaching 90-97% accuracy on extraction and end-to-end memory benchmarks where retrieval baselines score 80-87%.
FileGram grounds AI agent personalization in file-system behavioral traces via a data simulation engine, a diagnostic benchmark, and a bottom-up memory architecture.
A self-observed case study of one persistent AI agent in academic research finds cache-dominant token usage and recommends artifact-level evaluation metrics.
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.
-
Simulating Human Memory with Language Models
Language models show superior memory to humans on psych experiments but can be adjusted via prompting and compaction to forget more human-like, yielding better user simulators.
-
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.
-
AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators
AgentCollabBench shows that multi-agent reliability is limited by communication topology, with converging-DAG nodes causing synthesis bottlenecks that discard constraints and explain 7-40% of information loss variance.
-
From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction
Schema-aware iterative extraction turns AI memory into a verified system of record, reaching 90-97% accuracy on extraction and end-to-end memory benchmarks where retrieval baselines score 80-87%.
-
FileGram: Grounding Agent Personalization in File-System Behavioral Traces
FileGram grounds AI agent personalization in file-system behavioral traces via a data simulation engine, a diagnostic benchmark, and a bottom-up memory architecture.
-
Persistent AI Agents in Academic Research: A Single-Investigator Implementation Case Study
A self-observed case study of one persistent AI agent in academic research finds cache-dominant token usage and recommends artifact-level evaluation metrics.