arXiv:2607. 02873v1 Announce Type: cross Abstract: Large language model agents driving security tool suites over the Model Context Protocol are increasingly common.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2606. 01416v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents rely on orchestration layers that coordinate planning, retrieval, tool invocation, validation, memory, and recovery.
arXiv:2608. 14863v1 Announce Type: cross Abstract: LLM-based coding agents have advanced rapidly on single-process SWE tasks, with frontier models now clustering in the high-70s on SWE-bench Verified.
arXiv:2608. 04719v1 Announce Type: new Abstract: Agent evaluations tell us that a model picked the wrong tool, but rarely why.
arXiv:2605. 27898v2 Announce Type: replace Abstract: As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential.
arXiv:2512. 16310v3 Announce Type: replace-cross Abstract: LLM-based agents increasingly use multiple external tools to complete complex tasks.
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.