{"slug": "apeb-benchmarking-personalization-ability-of-large-language-model-agents", "title": "APeB: Benchmarking Personalization Ability of Large Language Model Agents", "summary": "Researchers introduced APeB, a benchmark for evaluating personalization in LLM-powered agents, finding that models struggle with raw, underspecified queries due to ineffective use of interaction histories. A proposed pipeline, VQRA, improved performance, highlighting the need for better history-utilization modules.", "body_md": "arXiv:2607.03162v1 Announce Type: new\nAbstract: LLM-powered agents struggle with personalization when users issue raw, underspecified queries. In this setting, agents must infer latent intent, extract preferences from noisy interaction histories, and select among competing alternatives. Existing benchmarks rarely test this capability, as they often rely on user-refined queries or simplified histories. We introduce personalized product search (PPS), a testbed for agentic personalization under raw queries and diverse histories. We construct Agent Personalized Benchmark (APeB) from action logs, pairing underspecified intents with rich histories and user-viewed candidate items. Evaluating state-of-the-art LLMs with multi-step agent workflows, we find that models handle explicit queries well but struggle with early-stage queries requiring intent and preference discovery. Rubric analysis attributes this gap mainly to ineffective history use. A simple history-aware query-refinement pipeline, VQRA, yields consistent gains, highlighting the need for dedicated history-utilization modules in personalized agents.", "url": "https://wpnews.pro/news/apeb-benchmarking-personalization-ability-of-large-language-model-agents", "canonical_source": "https://arxiv.org/abs/2607.03162", "published_at": "2026-07-07 04:00:00+00:00", "updated_at": "2026-07-07 04:04:19.689453+00:00", "lang": "en", "topics": ["large-language-models", "ai-agents", "natural-language-processing", "ai-research"], "entities": ["APeB", "VQRA", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/apeb-benchmarking-personalization-ability-of-large-language-model-agents", "markdown": "https://wpnews.pro/news/apeb-benchmarking-personalization-ability-of-large-language-model-agents.md", "text": "https://wpnews.pro/news/apeb-benchmarking-personalization-ability-of-large-language-model-agents.txt", "jsonld": "https://wpnews.pro/news/apeb-benchmarking-personalization-ability-of-large-language-model-agents.jsonld"}}