Paper Detail

TRACER: Balancing Stability-Plasticity-Cognitivity Trilemma for LLM Enhanced Continual Recommendation

WooJoo Kim, HyunSik Yoo, JunYoung Kim, JaeHyung Lim, SeongKu Kang, HwanJo Yu

arxiv Score 16.5

Published 2026-08-17 · First seen 2026-08-18

Research Track A

Abstract

Continual recommendation aims to capture evolving user interests from streaming data but struggles with sparsity. LLM enhancers mitigate this with semantic knowledge, but naive integration creates a new conflict. We identify this as the Stability-Plasticity-Cognitivity (SPC) Trilemma, where generalized LLM semantic priors (Cognitivity) conflict with retaining personalized historical preferences (Stability) and adapting to individual interest shifts (Plasticity). To address this, we propose Trilemma-Responsive Adaptive Continual Enhancement for Recommendation (TRACER). TRACER synergistically combines three specialized modules, each targeting stability, plasticity, or cognitivity, while preventing any single lemma from dominating. This holistic design enables semantic knowledge to support history retention and adaptation to evolving interests without disrupting continual learning. Across five real-world datasets, TRACER effectively harmonizes the SPC trilemma and outperforms state-of-the-art baselines by up to 14.38%. Our code is available at https://github.com/woo-joo/TRACER_CIKM26.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{kim2026tracer,
  title = {TRACER: Balancing Stability-Plasticity-Cognitivity Trilemma for LLM Enhanced Continual Recommendation},
  author = {WooJoo Kim and HyunSik Yoo and JunYoung Kim and JaeHyung Lim and SeongKu Kang and HwanJo Yu},
  year = {2026},
  abstract = {Continual recommendation aims to capture evolving user interests from streaming data but struggles with sparsity. LLM enhancers mitigate this with semantic knowledge, but naive integration creates a new conflict. We identify this as the Stability-Plasticity-Cognitivity (SPC) Trilemma, where generalized LLM semantic priors (Cognitivity) conflict with retaining personalized historical preferences (Stability) and adapting to individual interest shifts (Plasticity). To address this, we propose Trile},
  url = {https://arxiv.org/abs/2608.16075},
  keywords = {cs.IR},
  eprint = {2608.16075},
  archiveprefix = {arXiv},
}

Metadata

{}