ChainRec: An Agentic Recommender Learning to Route Tool Chains for Diverse and Evolving Interests

• URL: http://arxiv.org/abs/2602.10490v1
• Date: Wed, 11 Feb 2026 03:50:36 GMT
• Title: ChainRec: An Agentic Recommender Learning to Route Tool Chains for Diverse and Evolving Interests
• Abstract summary: 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.
• Score: 28.077112874506934
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) are increasingly integrated into recommender systems, motivating recent interest in agentic and reasoning-based recommendation. However, most existing approaches still rely on fixed workflows, applying the same reasoning procedure across diverse recommendation scenarios. In practice, user contexts vary substantially-for example, in cold-start settings or during interest shifts, so an agent should adaptively decide what evidence to gather next rather than following a scripted process. To address this, we propose ChainRec, an agentic recommender that uses a planner to dynamically select reasoning tools. ChainRec builds a standardized Tool Agent Library from expert trajectories. It then trains a planner using supervised fine-tuning and preference optimization to dynamically select tools, decide their order, and determine when to stop. Experiments on AgentRecBench across Amazon, Yelp, and Goodreads show that ChainRec consistently improves Avg HR@{1,3,5} over strong baselines, with especially notable gains in cold-start and evolving-interest scenarios. Ablation studies further validate the importance of tool standardization and preference-optimized planning.

Related papers

• The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows [72.9051182568928]
  We present ReASearch, a unified framework for reasoning-driven optimization.<n>With a shared agent loop and domain-specific tools, ReASearch instantiates the exact same scaffold to optimize prompts, programs, and ML.<n>We observe that complex search behaviors emerge naturally from the agent's reasoning process.
  arXiv  Detail & Related papers  (2026-08-07T02:15:39Z)
• AgenticRec: End-to-End Tool-Integrated Policy Optimization for Ranking-Oriented Recommender Agents [26.289918893920984]
  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.
  arXiv  Detail & Related papers  (2026-03-23T06:18:56Z)
• RecThinker: An Agentic Framework for Tool-Augmented Reasoning in Recommendation [63.74915464611075]
  RecThinker is an agentic framework for tool-augmented reasoning in recommendation.<n>We develop a suite of specialized tools for RecThinker, enabling the model to acquire user item-side and collaborative information.
  arXiv  Detail & Related papers  (2026-03-10T16:07:17Z)
• RecNet: Self-Evolving Preference Propagation for Agentic Recommender Systems [109.9061591263748]
  RecNet is a self-evolving preference propagation framework for recommender systems.<n>It proactively propagates real-time preference updates across related users and items.<n>In the backward phase, the feedback-driven propagation optimization mechanism simulates a multi-agent reinforcement learning framework.
  arXiv  Detail & Related papers  (2026-01-29T12:14:31Z)
• Listwise Preference Diffusion Optimization for User Behavior Trajectories Prediction [41.53271688465831]
  We formulate User Behavior Trajectory Prediction (UBTP) as a new task setting that explicitly models long-term user preferences.<n>We introduce Listwise Preference Diffusion Optimization (LPDO), a diffusion-based training framework that directly optimize structured preferences over entire item sequences.<n>To rigorously evaluate multi-step prediction quality, we propose the task-specific metric Sequential Match (SeqMatch), which measures exact trajectory agreement, and adopt Perplexity (PPL), which assesses probabilistic fidelity.
  arXiv  Detail & Related papers  (2025-11-01T12:16:24Z)
• AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems [17.329692234349768]
  Agentic recommender systems are powered by Large Language Models (LLMs)<n>LLMs' advanced reasoning and role-playing capabilities enable autonomous, adaptive decision-making.<n>The field currently lacks standardized evaluation protocols to assess these methods.
  arXiv  Detail & Related papers  (2025-05-26T07:45:11Z)
• 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)
• ThinkRec: Thinking-based recommendation via LLM [19.398302729633397]
  ThinkRec is a thinking-based framework that shifts LLM4Rec from System 1 to System 2 (rational system)<n> ThinkRec introduces a thinking activation mechanism that augments item metadata with keyword summarization and injects synthetic reasoning traces.<n>By dynamically assigning weights to expert models based on users' latent features, ThinkRec adapts its reasoning path to individual users, thereby enhancing precision and personalization.
  arXiv  Detail & Related papers  (2025-05-21T04:25:18Z)
• 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)
• On Generative Agents in Recommendation [58.42840923200071]
  Agent4Rec is a user simulator in recommendation based on Large Language Models. Each agent interacts with personalized recommender models in a page-by-page manner.
  arXiv  Detail & Related papers  (2023-10-16T06:41:16Z)
• MISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendation [61.45986275328629]
  We propose MISSRec, a multi-modal pre-training and transfer learning framework for sequential recommendation. On the user side, we design a Transformer-based encoder-decoder model, where the contextual encoder learns to capture the sequence-level multi-modal user interests. On the candidate item side, we adopt a dynamic fusion module to produce user-adaptive item representation.
  arXiv  Detail & Related papers  (2023-08-22T04:06:56Z)
• Meta-Wrapper: Differentiable Wrapping Operator for User Interest Selection in CTR Prediction [97.99938802797377]
  Click-through rate (CTR) prediction, whose goal is to predict the probability of the user to click on an item, has become increasingly significant in recommender systems. Recent deep learning models with the ability to automatically extract the user interest from his/her behaviors have achieved great success. We propose a novel approach under the framework of the wrapper method, which is named Meta-Wrapper.
  arXiv  Detail & Related papers  (2022-06-28T03:28:15Z)
• Adaptive Sampling using POMDPs with Domain-Specific Considerations [9.670635276589248]
  We investigate improving Monte Carlo Tree Search based solvers for adaptive sampling problems. We propose improvements in rollout allocation, the action exploration algorithm, and plan commitment. We show that it is possible to greatly reduce the number of rollouts by increasing the number of actions taken from a single planning tree.
  arXiv  Detail & Related papers  (2021-09-23T19:00:02Z)
• Controllable Multi-Interest Framework for Recommendation [64.30030600415654]
  We formalize the recommender system as a sequential recommendation problem. We propose a novel controllable multi-interest framework for the sequential recommendation, called ComiRec. Our framework has been successfully deployed on the offline Alibaba distributed cloud platform.
  arXiv  Detail & Related papers  (2020-05-19T10:18:43Z)

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.