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.
Ross Mitchell
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
years
2026 13representative citing papers
RHELM is a benchmark for LLM long-term memory with dynamic profiles, heterogeneous sources, and 27 memory characteristics that reveals weaknesses in existing models for multi-source aggregation and contextual reasoning.
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.
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%.
Introduces CSTM-Bench with 26 cross-session attack taxonomies, demonstrates recall loss in session-bound and full-log detectors, and proposes a bounded-memory coreset reader with the CSTM metric balancing detection and serving stability.
Cognitive architectures for AI agents require a distinct Knowledge layer with indefinite supersession persistence, separate from Memory decay, Wisdom evidence-gating, and Intelligence ephemerality.
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.
EVAF, a surprise- and valence-gated LoRA mechanism, provides memory depth for goal persistence in language agents via the loop-drift protocol, complementary to retrieval.
RoboMME-Interference measures VLA memory under cross-session interference and finds that all tested systems decay to near their no-memory baseline as unrelated sessions accumulate.
True Memory is a verbatim-event retrieval pipeline running on a single SQLite file that reaches 93% accuracy on LoCoMo multi-session questions, outperforming Mem0, Supermemory, Zep, and matching or exceeding EverMemOS and Hindsight on other long-context benchmarks.
SAFARI uses active investigation via tools and persistent short-term memory to attribute faults in agent trajectories that exceed LLM context windows, reporting 20% gains on Who&When and 0.58 precision at 5x context distance.
LLM agent memory is organized into Storage (preserving trajectories), Reflection (refining them), and Experience (abstracting into reusable knowledge) stages driven by needs for long-range consistency, dynamic adaptation, and continual learning.
Existing memory benchmarks cover at most two of the seven continuity properties from ATANT v1.0, with a median of one and none covering more than two.
citing papers explorer
-
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.
-
Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory
RHELM is a benchmark for LLM long-term memory with dynamic profiles, heterogeneous sources, and 27 memory characteristics that reveals weaknesses in existing models for multi-source aggregation and contextual reasoning.
-
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.
-
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%.
-
Cross-Session Threats in AI Agents: Benchmark, Evaluation, and Algorithms
Introduces CSTM-Bench with 26 cross-session attack taxonomies, demonstrates recall loss in session-bound and full-log detectors, and proposes a bounded-memory coreset reader with the CSTM metric balancing detection and serving stability.
-
The Missing Knowledge Layer in Cognitive Architectures for AI Agents
Cognitive architectures for AI agents require a distinct Knowledge layer with indefinite supersession persistence, separate from Memory decay, Wisdom evidence-gating, and Intelligence ephemerality.
-
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.
-
Memory Depth, Not Memory Access: Selective Parametric Consolidation for Long-Running Language Agents
EVAF, a surprise- and valence-gated LoRA mechanism, provides memory depth for goal persistence in language agents via the loop-drift protocol, complementary to retrieval.
-
RoboMME-Interference: Benchmarking Robot Memory Under Interference
RoboMME-Interference measures VLA memory under cross-session interference and finds that all tested systems decay to near their no-memory baseline as unrelated sessions accumulate.
-
Storage Is Not Memory: A Retrieval-Centered Architecture for Agent Recall
True Memory is a verbatim-event retrieval pipeline running on a single SQLite file that reaches 93% accuracy on LoCoMo multi-session questions, outperforming Mem0, Supermemory, Zep, and matching or exceeding EverMemOS and Hindsight on other long-context benchmarks.
-
SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation
SAFARI uses active investigation via tools and persistent short-term memory to attribute faults in agent trajectories that exceed LLM context windows, reporting 20% gains on Who&When and 0.58 precision at 5x context distance.
-
From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
LLM agent memory is organized into Storage (preserving trajectories), Reflection (refining them), and Experience (abstracting into reusable knowledge) stages driven by needs for long-range consistency, dynamic adaptation, and continual learning.
-
ATANT v1.1: Positioning Continuity Evaluation Against Memory, Long-Context, and Agentic-Memory Benchmarks
Existing memory benchmarks cover at most two of the seven continuity properties from ATANT v1.0, with a median of one and none covering more than two.