arXiv:2606. 26116v1 Announce Type: cross Abstract: A brand whose customers use both ChatGPT and Claude for product recommendations faces a strategic choice: a single optimization playbook, or one per provider?
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2608. 10008v1 Announce Type: cross Abstract: LLM recommenders for top-$K$ item suggestion regularly emit titles outside the target catalog.
arXiv:2606. 17443v1 Announce Type: new Abstract: Large language models (LLMs) are becoming a major way for consumers to find products, but we do not yet understand how brands compete in this new channel.
Enterprise practitioners read agent leaderboards as if they ranked agent capability. We show, across three open agent-trace benchmarks (TheAgentCompany, $τ^2$-bench, and AppWorld), that the agent main effect accounts for less than 3% of total variance in every dataset and check type, while the agent-by-task interaction accounts for 7-23%.
Agent evaluations tell us that a model picked the wrong tool, but rarely why. We introduce canary tools: diagnostic probe tools planted in an agent's Model Context Protocol (MCP) tool set, each engineered to probe one specific tool-selection weakness.
arXiv:2608. 11323v1 Announce Type: new Abstract: Enterprise practitioners read agent leaderboards as if they ranked agent capability.
arXiv:2606. 27288v1 Announce Type: new Abstract: Multi-model LLM systems such as routing, voting, cascades, fusion, and mixture-of-agents are used to beat single-model accuracy.