MemJoin benchmarks cross-session privacy leaks in agent memory
In 288 synthetic cases, a complete history reveals a sensitive relation that no single session contains.
Stories per day · 30 days
6 stories, newest first · one card per story
Stories tagged #long-term-memory
Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy
MemAdapter calibrates retrieved memories with counterfactual reasoning to reduce sycophancy in long-memory LLM agents.
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
RealCompanion benchmarks whether agents truly use months of real companion chats to understand a person.
APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants
APM-Bench evaluates persistent memory for streaming video assistants across 104 multi-session trajectories.
Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations
VoxPolyMem's interaction-aware memory and agentic retrieval score 85.0 on multi-party spoken-conversation benchmark VoxPolyBench.
Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision
Researchers propose workspace tokens, a lightweight latent robot memory distilled from train-time VLM saliency queries, improving policy performance without in-loop VLM calls.