AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Diagnostic-Guided Dynamic Profile Optimization for LLM-based User Simulators in Sequential Recommendation

Hongyang Liu, Zhu Sun, Tianjun Wei, Yan Wang, Jiajie Zhu, Xinghua Qu

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Knowledge-augmented question answering · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
iterative step-by-step profile optimization instead of one-shot (ablation)DGDPO · BooksF1: 0.2753 -> 0.3235Improved
use specialized fine-tuned diagnostic LLM instead of a general-purpose LLM (ablation)DGDPO · BooksF1: 0.2760 -> 0.3235Improved
add defect-specific fine-tuning of the diagnostic LLM (ablation)DGDPO · BooksF1: 0.2885 -> 0.3235Improved
add domain-adaptive pre-training of the diagnostic LLM (ablation)DGDPO · BooksF1: 0.3183 -> 0.3235Improved
use specialized Qwen3-0.6B diagnostic module vs prompting GPT-4o-mini for defect identificationdiagnostic module · profile defect identification (average over datasets)accuracy (%): 62.78% -> 92.20%Improved
scale specialized diagnostic LLM from Qwen3-0.6B to Qwen3-1.7B (ablation)DGDPO · BooksF1: 0.3235 -> 0.3170Hurt
raise initial/optimization split ratio alpha from 0.6 to 0.8 (ablation)DGDPO · BooksF1: 0.3235 -> 0.3001Hurt
lower split ratio alpha from 0.6 to 0.5 (ablation)DGDPO · BooksF1: 0.3235 -> 0.3212Hurt
update profile during multi-round interaction with ground truth item (ablation)DGDPO with sequential recommenders · Books (multi-round, Precision)PrecisionImproved
update profile during multi-round interaction without ground truth (simulator's own choice) with FPMC (ablation)DGDPO with FPMC · Books (multi-round, Precision)PrecisionHurt
use DGDPO over strongest baseline (AgentCF)user simulator · BooksPrecision: 0.1598 -> 0.2058Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy