# STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning

arXiv: https://arxiv.org/abs/2508.18812 · HTML: https://mlsanity.com/paper/2508.18812/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 17 of its 42 references that are in the map.
- First posted on arXiv 26 Aug 2025.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)
- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)

## Builds on (most cited first, 17 of 17)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems](https://mlsanity.com/paper/2205.08084/) (2022)
- [Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects](https://mlsanity.com/paper/2401.03428/) (2024)
- [Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought](https://mlsanity.com/paper/2501.04682/) (2025)
- [LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application](https://mlsanity.com/paper/2405.03988/) (2024)
- [Item-Language Model for Conversational Recommendation](https://mlsanity.com/paper/2406.02844/) (2024)

## Built on by (most cited first, 5 of 5)

- [AgenticRecTune: Multi-Agent with Self-Evolving Skillhub for Recommendation System Optimization](https://mlsanity.com/paper/2604.26969/) (2026)
- [Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems](https://mlsanity.com/paper/2607.04433/) (2026)
- [Verifiable Reasoning for LLM-based Generative Recommendation](https://mlsanity.com/paper/2603.07725/) (2026)
- [Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendation](https://mlsanity.com/paper/2603.10673/) (2026)
- [CARA: Cognitive Adaptive Recommendation Agent](https://mlsanity.com/paper/2608.16919/) (2026)

## Abstract (arXiv)

While modern recommender systems are instrumental in navigating information abundance, they remain fundamentally limited by static user modeling and reactive decision-making paradigms. Current large language model (LLM)-based agents inherit these shortcomings through their overreliance on heuristic pattern matching, yielding recommendations prone to shallow correlation bias, limited causal inference, and brittleness in sparse-data scenarios. We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities. Each user is modeled as an agent with parallel cognitions: fast response for immediate interactions and slow reasoning that performs chain-of-thought rationales. To cultivate intrinsic slow thinking, we develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping. This hybrid approach scaffolds agents in acquiring foundational capabilities (preference summarization, rationale generation) while enabling dynamic policy adaptation through simulated feedback loops. Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines, despite using only 0.4% of the full training data.