ECPO: Evidence-Coupled Policy Optimization for Verifier-Audited Candidate Ranking
cs.AI, cs.LG
Submitted: 2026-05-21
Updated: 2026-10-16
Comments: 42 pages, 1 figure. Revised manuscript; updated authorship and corresponding author information
License: http://creativecommons.org/licenses/by/4.0/
The gist: Ranking systems used for decision support should expose evidence that can be audited independently of the model's ranking scores.
Terminology
Abstract
Ranking systems used for decision support should expose evidence that can be audited independently of the model's ranking scores. We study a closed-roster setting in which a policy jointly emits a Top- K ranking and candidate-linked, span-grounded evidence bundles. Evidence-Coupled Policy Optimization (ECPO) combines listwise utility, certificate validity, and an evidence-cycle reward that removes answer-bearing fields before deterministic recovery. On MAVEN-ERE and RAMS, ECPO improves verifier-audited traceability, rank-blind recovery, and human comparative support relative to matched controls in the tested provenance settings. The gains persist under held-out evaluators, other 8B/14B backbones, and a HotpotQA answer-ranking interface. Ordinary NDCG and runtime remain explicit trade-offs.
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems