2026-10-26T11:03:18Z https://lifeofresearch.com/oai2

oai:lifeofresearch.com:140 2026-10-26T08:13:34Z type:preprint openaire

PECA v3: Evidence-Gated Anticipatory Execution: Separating Requirement Compliance, Predictive Utility, and Commit Authorization in AI Agents RM369 AI agents instruction following speculative execution runtime verification auditability action contracts reversibility reward hacking Anticipation can help an AI agent prepare useful work before a requirement is fully specified, but a predictor can also create the very obligations the agent then tries to satisfy. PECA v3 refactors Prefix-Conditioned Execution and Cumulative Audit around a strict separation among confirmed requirements, provisional predictions, and the mutable artifact with its provenance. The controller preserves the state triple (R_h,R_p,S), but makes the distinction operational: compliance is judged only against active, evidence-supported requirements in R_h; predictions in R_p are evaluated separately for utility, calibration, and waste; and external or consequential changes pass through action-specific authorization and commit gates. Each action carries a contract covering evidence, preconditions, expected effects, verification, side effects, reversibility, and commit criteria. The design favors preparation useful across several plausible futures, permits isolated branch-specific speculation only when its expected value is positive, and combines material-cycle checkpoints with event-triggered reviews. The nested 3-6-9 cadence is retained as an ablatable scheduling hypothesis, not a source of correctness. This paper defines the architecture and a controlled evaluation plan. It reports no live-model performance results and makes no claim that the proposed controller is superior until matched, independently evaluated experiments establish that fact. Life of Research 2026-10-26 info:eu-repo/semantics/preprint https://lifeofresearch.com/preprints/140 eng https://lifeofresearch.com/preprints/140/files/148/PECA_v3_Evidence_Gated_Anticipatory_Execution.pdf application/pdf https://creativecommons.org/licenses/by/4.0/ info:eu-repo/semantics/openAccess