AgenticRec: End-to-End Tool-Integrated Policy Optimization for Ranking-Oriented Recommender Agents

• URL: http://arxiv.org/abs/2603.21613v1
• Date: Mon, 23 Mar 2026 06:18:56 GMT
• Title: AgenticRec: End-to-End Tool-Integrated Policy Optimization for Ranking-Oriented Recommender Agents
• Abstract summary: We present AgenticRec, a ranking-oriented agentic recommendation framework.<n>We design a suite of recommendation-specific tools integrated into a ReAct loop to support evidence-grounded reasoning.<n>We introduce Progressive Preference Refinement to resolve fine-grained preference ambiguities.
• Score: 26.289918893920984
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recommender agents built on Large Language Models offer a promising paradigm for recommendation. However, existing recommender agents typically suffer from a disconnect between intermediate reasoning and final ranking feedback, and are unable to capture fine-grained preferences. To address this, we present AgenticRec, a ranking-oriented agentic recommendation framework that optimizes the entire decision-making trajectory (including intermediate reasoning, tool invocation, and final ranking list generation) under sparse implicit feedback. Our approach makes three key contributions. First, we design a suite of recommendation-specific tools integrated into a ReAct loop to support evidence-grounded reasoning. Second, we propose theoretically unbiased List-Wise Group Relative Policy Optimization (list-wise GRPO) to maximize ranking utility, ensuring accurate credit assignment for complex tool-use trajectories. Third, we introduce Progressive Preference Refinement (PPR) to resolve fine-grained preference ambiguities. By mining hard negatives from ranking violations and applying bidirectional preference alignment, PPR minimizes the convex upper bound of pairwise ranking errors. Experiments on benchmarks confirm that AgenticRec significantly outperforms baselines, validating the necessity of unifying reasoning, tool use, and ranking optimization.

Related papers

• F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking [79.49893545611779]
  Large Language Models (LLMs) can generate a subset and order it within a single autoregressive pass.<n>This flexibility introduces a new optimization challenge: the model must search an output space while receiving utility feedback only after the full ranked list is generated.<n>This credit assignment gap makes end-to-end optimization unstable and sample-inefficient.<n>We propose a unified framework that performs both within a single autoregressive rollout and optimize them end-to-end via factorized group-relative policy optimization.
  arXiv  Detail & Related papers  (2026-05-13T04:52:33Z)
• HARPO: Hierarchical Agentic Reasoning for User-Aligned Conversational Recommendation [10.766058469348382]
  We propose HARPO, an agentic framework that reframes conversational recommendation as a structured decision-making process.<n>HarPO integrates hierarchical preference learning that decomposes recommendation quality into interpretable dimensions.<n>We demonstrate consistent improvements over strong baselines on recommendation-centric metrics.
  arXiv  Detail & Related papers  (2026-04-11T06:07:15Z)
• Verifiable Reasoning for LLM-based Generative Recommendation [106.7765000777685]
  Reasoning in Large Language Models (LLMs) has recently shown strong potential in enhancing generative recommendation.<n>We propose a novel textbftextitreason-verify-recommend paradigm, which interleaves reasoning with verification to provide reliable feedback.<n>Experiments on four real-world datasets demonstrate that VRec substantially enhances recommendation effectiveness and scalability without compromising efficiency.
  arXiv  Detail & Related papers  (2026-03-08T16:55:45Z)
• ChainRec: An Agentic Recommender Learning to Route Tool Chains for Diverse and Evolving Interests [28.077112874506934]
  ChainRec is an agentic recommender that uses a planner to dynamically select reasoning tools.<n> Experiments on AgentRecBench across Amazon, Yelp, and Goodreads show that ChainRec consistently improves Avg HR@1,3,5 over strong baselines.
  arXiv  Detail & Related papers  (2026-02-11T03:50:36Z)
• R$^2$ec: Towards Large Recommender Models with Reasoning [59.32598867813266]
  We propose R$2$ec, a unified large recommender model with intrinsic reasoning capability.<n>R$2$ec introduces a dual-head architecture that supports both reasoning chain generation and efficient item prediction in a single model.<n>To overcome the lack of annotated reasoning data, we design RecPO, a reinforcement learning framework.
  arXiv  Detail & Related papers  (2025-05-22T17:55:43Z)
• In-context Ranking Preference Optimization [65.5489745857577]
  We propose an In-context Ranking Preference Optimization (IRPO) framework to optimize large language models (LLMs) based on ranking lists constructed during inference.<n>We show IRPO outperforms standard DPO approaches in ranking performance, highlighting its effectiveness in aligning LLMs with direct in-context ranking preferences.
  arXiv  Detail & Related papers  (2025-04-21T23:06:12Z)
• Preference Diffusion for Recommendation [50.8692409346126]
  We propose PreferDiff, a tailored optimization objective for DM-based recommenders.<n> PreferDiff transforms BPR into a log-likelihood ranking objective to better capture user preferences.<n>It is the first personalized ranking loss designed specifically for DM-based recommenders.
  arXiv  Detail & Related papers  (2024-10-17T01:02:04Z)
• Permutative Preference Alignment from Listwise Ranking of Human Judgments [40.23480751285947]
  We develop an end-to-end alignment algorithm by approximating NDCG with a differentiable surrogate loss.<n>We show that NDCG-based approaches improve ranking accuracy more effectively than B-T-based methods.
  arXiv  Detail & Related papers  (2024-10-06T03:49:28Z)
• Recommendation Systems with Distribution-Free Reliability Guarantees [83.80644194980042]
  We show how to return a set of items rigorously guaranteed to contain mostly good items. Our procedure endows any ranking model with rigorous finite-sample control of the false discovery rate. We evaluate our methods on the Yahoo! Learning to Rank and MSMarco datasets.
  arXiv  Detail & Related papers  (2022-07-04T17:49:25Z)
• A Differentiable Ranking Metric Using Relaxed Sorting Operation for Top-K Recommender Systems [1.2617078020344619]
  A recommender system generates personalized recommendations by computing the preference score of items, sorting the items according to the score, and filtering top-K items with high scores. While sorting and ranking items are integral for this recommendation procedure, it is nontrivial to incorporate them in the process of end-to-end model training. This incurs the inconsistency issue between existing learning objectives and ranking metrics of recommenders. We present DRM that mitigates the inconsistency and improves recommendation performance by employing the differentiable relaxation of ranking metrics.
  arXiv  Detail & Related papers  (2020-08-30T10:57:33Z)
• SetRank: A Setwise Bayesian Approach for Collaborative Ranking from Implicit Feedback [50.13745601531148]
  We propose a novel setwise Bayesian approach for collaborative ranking, namely SetRank, to accommodate the characteristics of implicit feedback in recommender system. Specifically, SetRank aims at maximizing the posterior probability of novel setwise preference comparisons. We also present the theoretical analysis of SetRank to show that the bound of excess risk can be proportional to $sqrtM/N$.
  arXiv  Detail & Related papers  (2020-02-23T06:40:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.