Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-07-26 · source-backed
KAIST's Yang, Ki, Lee, Choo, and Park target a gap where existing personalization suites either give fully explicit prompts or hand agents pre-abstracted profiles, while real users give underspecified instructions and the context lives in messy history (arXiv 2607.20482). Their PACMem baseline decomposes raw history into factual memories (per-session summaries) and preference memories (recurring behavioral patterns), retrieving from both at inference and consistently outperforming prior memory-based approaches on both task types.
Each link below shares sources, entities, or timing with this story.
Same source domain / Shared topic / Tension
Reported by the same outlet (arxiv.org); overlapping topics (agent, baseline, benchmark, context, history); pushes against this story (versus).
Reported by the same outlet (arxiv.org); overlapping topics (agent, baseline, clean, memory); pushes against this story (versus).
Same source domain / Shared topic
Reported by the same outlet (arxiv.org); overlapping topics (agent, behavioral, context, existing, memory).
Same source domain / Shared topic / Tension
Reported by the same outlet (arxiv.org); overlapping topics (agent, behavioral, benchmark); pushes against this story (but).
Reported by the same outlet (arxiv.org); overlapping topics (agent, context, memory); pushes against this story (but).
Reported by the same outlet (arxiv.org); overlapping topics (agent, behavioral, memory); pushes against this story (but).
Reported by the same outlet (arxiv.org); overlapping topics (agent, benchmark, clean); pushes against this story (against).
Same source domain / Shared topic
Reported by the same outlet (arxiv.org); overlapping topics (agent, context, history, memory).