AgentRecBench is a public text-based benchmark for LLM recommendation agents, but its headline claim of agent superiority is undercut by its own tables.
Collaborative filtering recom- mender systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
AgentRecBench is a public text-based benchmark for LLM recommendation agents, but its headline claim of agent superiority is undercut by its own tables.