# Memory Retrieval

In verbal memory tests, the order of recalled words and the pauses between them carry diagnostic information, but a pause means different things inside a semantic category and at a switch between categories. TrajLift treats a recall episode as a timed trajectory on a semantic hierarchy, uses heat diffusion to lift each word onto several hierarchical scales, and lets the inter-item latency modulate the diffusion time so structure and timing enter one operator. On Hong Kong List Learning Test data from 387 participants after excluding 15 with annotation issues, accuracy on the 30-minute delayed-recall trial was 80.38%, 4.5 percentage points above a handcrafted baseline using recall count alone; the paired difference on the 10-minute trial was not significant.

In verbal memory tests, the order of recalled words and the pauses between them carry diagnostic information, but a pause means different things inside a semantic category and at a switch between categories. TrajLift treats a recall episode as a timed trajectory on a semantic hierarchy, uses heat diffusion to lift each word onto several hierarchical scales, and lets the inter-item latency modulate the diffusion time so structure and timing enter one operator. On Hong Kong List Learning Test data from 387 participants after excluding 15 with annotation issues, accuracy on the 30-minute delayed-recall trial was 80.38%, 4.5 percentage points above a handcrafted baseline using recall count alone; the paired difference on the 10-minute trial was not significant.

Personalized assistants must recover sparse evidence from long conversation histories, while queries vary widely in complexity. APDMem organizes history into four layers, from thematic summaries and personalized key facts down to turn-level evidence notes and raw messages, and a controller reads high-level summaries first, drilling into finer evidence only when needed. On LongMemEval it achieves strong long-context memory reasoning while accessing only 8% of the total conversations.

Personalized assistants must recover sparse evidence from long conversation histories, while queries vary widely in complexity. APDMem organizes history into four layers, from thematic summaries and personalized key facts down to turn-level evidence notes and raw messages, and a controller reads high-level summaries first, drilling into finer evidence only when needed. On LongMemEval it achieves strong long-context memory reasoning while accessing only 8% of the total conversations.

Memorizon proposes a training recipe in which each scored chunk retrieves its own top-k latents by camera co-visibility and their union forms a bounded shared memory bank, so a training sample can cover a span of any length while the attention sequence stays bounded; revisit consistency improves on every split over a sliding-window baseline, and a span long enough to reach the first visit adds further gains at some cost in image quality.

Memorizon proposes a training recipe in which each scored chunk retrieves its own top-k latents by camera co-visibility and their union forms a bounded shared memory bank, so a training sample can cover a span of any length while the attention sequence stays bounded; revisit consistency improves on every split over a sliding-window baseline, and a span long enough to reach the first visit adds further gains at some cost in image quality.

Jev-Mem introduces an agentic memory architecture inspired by System-One/System-Two cognition, in which a dedicated System-One control plane handles memory typing, relation construction, query routing, retrieval-budget allocation, graph traversal, candidate scoring, and adaptive stopping, while System Two is reserved for complex reasoning and answer synthesis; on LoCoMo it reaches an overall LLM-as-a-Judge score of 0.777 (an 11.0% relative gain over the strongest baseline), a memory construction time of 158 seconds (a 6.6 speedup over the fastest competing memory system), and an average query latency of 0.93 seconds (a 36.7% reduction).

Jev-Mem introduces an agentic memory architecture inspired by System-One/System-Two cognition, in which a dedicated System-One control plane handles memory typing, relation construction, query routing, retrieval-budget allocation, graph traversal, candidate scoring, and adaptive stopping, while System Two is reserved for complex reasoning and answer synthesis; on LoCoMo it reaches an overall LLM-as-a-Judge score of 0.777 (an 11.0% relative gain over the strongest baseline), a memory construction time of 158 seconds (a 6.6 speedup over the fastest competing memory system), and an average query latency of 0.93 seconds (a 36.7% reduction).