arXiv:2604. 10842v3 Announce Type: replace-cross Abstract: LLM-powered coding agents increasingly rely on tool-use protocols such as the Model Context Protocol (MCP) to read and write files on a developer's workstation.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2607. 11149v1 Announce Type: new Abstract: LLM agent benchmarks measure task completion, reliability, and inference cost, but not the persistent data an agent run leaves on disk, including logs, context snapshots, checkpoints, and debug traces.
LLM agent benchmarks measure task completion, reliability, and inference cost, but not the persistent data an agent run leaves on disk, including logs, context snapshots, checkpoints, and debug traces. We introduce AgentFootprint, a cross-framework benchmark of post-run agent storage footprint.
arXiv:2607. 11098v1 Announce Type: cross Abstract: Tool-using LLM agents are mostly evaluated assuming all tools work.
arXiv:2608. 08453v1 Announce Type: new Abstract: Under the current standard, Agent Skills are SKILL.
Tool-using language-model agents are governed not only by task prompts but also by persistent system-side instructions that specify tools, arguments, policies, execution protocols, and recovery. Compressing these agent control contexts (ACCs) can reduce input cost and context use, yet existing prompt-compression evaluations do not reveal whether the resulting control remains operationally reliable.
Under the current standard, Agent Skills are SKILL. md files that combine instructions with supporting resources, enabling Large Language Model (LLM) agents to reuse procedures beyond a single conversation.