SOURCE-LINKED INTELLIGENCE

BTS-AgentBench: A Deterministic, Replayable Pipeline from Read-Only Telemetry Logs to Agent Benchmarks

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

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 instantiated as BTS-AgentBench. The pipeline normalizes BTS metadata and raw histories into a read-only tool store, compiles static tasks with tool-derived gold answers and evidence, and lifts retained tasks into typed, bounded operator-facing episodes. The 532-row release adds clarification, goal revision, timestamp policy, quality-gated reporting, and evidence attribution while pres

Read original source ↗ Open in workspace

recordType: paper
region: Global

Evidence & attribution

arXiv · AI, language, vision and robotics · 2026-08-27T16:35:52.000Z

First collected: 2026-09-21T08:32:02.028Z. This is not the publication date.