PCN-Rec: Agentic Proof-Carrying Negotiation for Reliable Governance-Constrained Recommendation

TL;DR

PCN-Rec introduces a proof-carrying negotiation framework for recommender systems that ensures governance constraints are reliably satisfied through structured certificates and verification, improving compliance and auditability.

Contribution

It presents a novel negotiation pipeline combining natural language reasoning with deterministic enforcement and verification for governance-constrained recommendations.

Findings

Achieves 98.55% pass rate on feasible users.

Maintains high utility with only 0.021 drop in NDCG@10.

Outperforms baseline without verification/repair.

Abstract

Modern LLM-based recommenders can generate compelling ranked lists, but they struggle to reliably satisfy governance constraints such as minimum long-tail exposure or diversity requirements. We present PCN-Rec, a proof-carrying negotiation pipeline that separates natural-language reasoning from deterministic enforcement. A base recommender (MF/CF) produces a candidate window of size W, which is negotiated by two agents: a User Advocate optimizing relevance and a Policy Agent enforcing constraints. A mediator LLM synthesizes a top-N slate together with a structured certificate (JSON) describing the claimed constraint satisfaction. A deterministic verifier recomputes all constraints from the slate and accepts only verifier-checked certificates; if verification fails, a deterministic constrained-greedy repair produces a compliant slate for re-verification, yielding an auditable trace. On MovieLens-100K with governance constraints, PCN-Rec achieves a 98.55% pass rate on feasible users (n = 551, W = 80) versus a one-shot single-LLM baseline without verification/repair, while preserving utility with only a 0.021 absolute drop in NDCG@10 (0.403 vs. 0.424); differences are statistically significant (p < 0.05).