Story
arxiv_cs_cl ยท Aug 27, 2026 ยท paper
Source brief
BTS-AgentBench: A Deterministic, Replayable Pipeline from Read-Only Telemetry Logs to Agent Benchmarks
arxiv.orgAug 27, 2026
original source linked
In brief
Industrial sites contain large volumes of read-only telemetry, but few benchmarks specify how to compile these records into executable multi-turn agent tasks. We present a telemetry-to-episode construction method inst...
Feed lens
agent