mlsanityData to 14 Oct 2026

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

arXiv 2601.09771 ↗First posted 14 Jan 2026cs.AIcited by 1

On the map: LLM agents and tool use → Agentic recommender systems

Abstract (arXiv)

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).

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use. Builds on 9 of its 21 references that are in the map. First posted on arXiv 14 Jan 2026.

Builds on

9 of 21 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations31 Aug

Other references · 8

  1. 2023A Survey on Large Language Models for Recommendationcited by 379
  2. 2023TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendationcited by 337
  3. 2022Prompting Is Programming: A Query Language for Large Language Modelscited by 110
  4. 2023On the Calibration of Large Language Models and Alignmentcited by 73
  5. 2024Enhancing Recommendation Diversity by Re-ranking with Large Language Modelscited by 19
  6. 2025Verifiable Format Control for Large Language Model Generationscited by 17
  7. 2023Generative Slate Recommendation with Reinforcement Learningcited by 13
  8. 2024Evaluating the Ability of Large Language Models to Generate Verifiable Specifications in VeriFastcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Autonomous Information Seeking: A Roadmap for Agentic Recommender Systemscited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2026τ-Rec: A Verifiable Benchmark for Agentic Recommender Systems
  2. 2026RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents
  3. 2026LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing
  4. 2026RecThinker: An Agentic Framework for Tool-Augmented Reasoning in Recommendation
  5. 2026Reasoning with Evidence, Not Merely Rationales: Verifiable Preference Proofs for LLM-Based Recommendation
  6. 2025The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems
  7. 2024Leveraging LLM Reasoning Enhances Personalized Recommender Systems
  8. 2026SAGER: Self-Evolving User Policy Skills for Recommendation Agent