AI RESEARCH
NeuroState-Bench: A Human-Calibrated Benchmark for Commitment Integrity in LLM Agent Profiles
arXiv CS.AI
•
ArXi:2605.01847v1 Announce Type: new Outcome-only evaluation under-specifies whether an evaluated agent profile preserves the commitments required to solve a multi-turn task coherently. NeuroState-Bench is a human-calibrated benchmark that operationalizes commitment integrity through benchmark-defined side-query probes rather than inferred hidden activations. The released inventory contains 144 deterministic tasks and 306 benchmark-defined side-query probes spanning eight cognitively motivated failure families, paired clean and distractor variants, and three difficulty bands.