Story
arxiv_agent_systems_research · Nov 11, 2026 · paper
arxiv.orgNov 11, 2026
original source linked
In brief
LLM-based recommendation agents can search catalogs, inspect products, ask users, and revise rejected recommendations. However, these behaviors are often governed by hand-designed workflows, while existing training methods optimize isolated components such as query rewriting or l
Feed lens
agenteval