mlsanityData to 14 Oct 2026

Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent

arXiv 2506.23485 ↗First posted 30 Jun 2025cs.CL cs.AI cs.IRcited by 17

On the map: LLM reasoning → LLM reasoning for recommendation

also in 1 more
Abstract (arXiv)

Interactive recommendation is a typical information-seeking task that allows users to interactively express their needs through natural language and obtain personalized recommendations. Large language model-powered (LLM-powered) agents have become a new paradigm in interactive recommendations, effectively capturing users' real-time needs and enhancing personalized experiences. However, due to limited planning and generalization capabilities, existing formulations of LLM-powered interactive recommender agents struggle to effectively address diverse and complex user intents, such as intuitive, unrefined, or occasionally ambiguous requests. To tackle this challenge, we propose a novel thought-augmented interactive recommender agent system (TAIRA) that addresses complex user intents through distilled thought patterns. Specifically, TAIRA is designed as an LLM-powered multi-agent system featuring a manager agent that orchestrates recommendation tasks by decomposing user needs and planning subtasks, with its planning capacity strengthened through Thought Pattern Distillation (TPD), a thought-augmentation method that extracts high-level thoughts from the agent's and human experts' experiences. Moreover, we designed a set of user simulation schemes to generate personalized queries of different difficulties and evaluate the recommendations based on specific datasets. Through comprehensive experiments conducted across multiple datasets, TAIRA exhibits significantly enhanced performance compared to existing methods. Notably, TAIRA shows a greater advantage on more challenging tasks while generalizing effectively on novel tasks, further validating its superiority in managing complex user intents within interactive recommendation systems. The code is publicly available at:https://github.com/Alcein/TAIRA.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning. Builds on 20 of its 60 references that are in the map. First posted on arXiv 30 Jun 2025.

Builds on

20 of 60 references.

References · 20

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  4. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
  5. 2024Understanding the planning of LLM agents: A surveycited by 421
  6. 2023Recommender AI Agent: Integrating Large Language Models for Interactive Recommendationscited by 131
  7. 2024Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Modelscited by 91
  8. 2023Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Searchcited by 75
  9. 2024KnowAgent: Knowledge-Augmented Planning for LLM-Based Agentscited by 61
  10. 2024A Multi-Agent Conversational Recommender Systemcited by 43
  11. 2023A Large Language Model Enhanced Conversational Recommender Systemcited by 31
  12. 2021ConvFiT: Conversational Fine-Tuning of Pretrained Language Modelscited by 25
8 more
  1. 2024User Intent Recognition and Satisfaction with Large Language Models: A User Study with ChatGPTcited by 19
  2. 2025RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discoverycited by 19
  3. 2023Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPTcited by 16
  4. 2024Scaling New Frontiers: Insights into Large Recommendation Modelscited by 13
  5. 2025TD3: Tucker Decomposition Based Dataset Distillation Method for Sequential Recommendationcited by 13
  6. 2025Generative Large Recommendation Models: Emerging Trends in LLMs for Recommendationcited by 13
  7. 2024Incorporating External Knowledge and Goal Guidance for LLM-based Conversational Recommender Systemscited by 8
  8. 2025Prompting is not Enough: Exploring Knowledge Integration and Controllable Generationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 14.

17 papers.

Sort:

By area:

  1. 2025CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steeringcited by 13
  2. 2025Multi-Agent Collaborative Filtering: Orchestrating Users and Items for Agentic Recommendationscited by 10
  3. 2025SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignmentcited by 9
  4. 2026Why Thinking Hurts: Diagnosing and Rectifying Linguistic Inertia in Large Language Models for Recommendationcited by 9
  5. 2026SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized Generationcited by 6
  6. 2026EXACT: Explicit Attribute-Guided Decoding-Time Personalizationcited by 4
  7. 2026SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utilitycited by 4
  8. 2026Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibrationcited by 4
  9. 2026RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systemscited by 4
  10. 2026Autonomous Information Seeking: A Roadmap for Agentic Recommender Systemscited by 4
  11. 2026Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillationcited by 3
  12. 2026IE as Cache: Information Extraction Enhanced Agentic Reasoningcited by 3
5 more
  1. 2026AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMscited by 1
  2. 2026Generative Data Transformation: From Mixed to Unified Datacited by 0
  3. 2026Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Rankingcited by 0
  4. 2026Attacking and Defending Multi-Agent Collaborative Filtering Systems Through Connectivitycited by 0
  5. 2026AgentRecommender: LLM Agents Enable Customizable Recommender Systems on the User Sidecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on LLM-powered Agents for Recommender Systems
  2. 2025AgentRec: Next-Generation LLM-Powered Multi-Agent Collaborative Recommendation with Adaptive Intelligence
  3. 2025AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
  4. 2025Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models
  5. 2025A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval
  6. 2025ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation
  7. 2026Personalized Recommendation Tool Learning via Autonomous Language Agents
  8. 2023On Generative Agents in Recommendation