FirsthandTech
arXiv — cs.AI preprintsInternational12 October 2026

Agent Step Value: Auditing Evaluation-Channel Sensitivity in Black-Box Agent Traces

This is an official announcement record

Firsthand records what arXiv — cs.AI preprints announced and links to the original. The wording below is theirs, not ours.

arXiv:2607.04419v5 Announce Type: replace Abstract: Reusing evaluator-derived step rewards across evaluation channels raises a measurement question: does the assigned direction remain stable? We define Agent Step Value (ASV) as a channel-indexed before/after target-margin gain and identify the state-by-channel interaction from a matched 2x2 design. Across frozen PubMed question-answering transitions, cross-channel gain signs disagree on 48.3% of comparisons, compared with 0.3% for same-channel retries. Transition interactions are nearly balanced in sign (median +0.014; 10% trimmed mean -0.033)
— arXiv — cs.AI preprints

More from arXiv — cs.AI preprints

This content is for informational purposes only and is not professional advice. Specifications, prices, plan tiers, and features change frequently and may differ from what is shown here; verify current details on the manufacturer's or company's official page before purchasing. Ratings are based on analysis of published documentation, not independent lab testing.